diff --git a/test/test_download.py b/test/test_download.py index fd7752cdd..6f00a4ded 100755 --- a/test/test_download.py +++ b/test/test_download.py @@ -160,7 +160,7 @@ def try_rm_tcs_files(tcs=None): force_generic_extractor=params.get('force_generic_extractor', False)) except (DownloadError, ExtractorError) as err: # Check if the exception is not a network related one - if not isinstance(err.exc_info[1], (TransportError, UnavailableVideoError)) or (isinstance(err.exc_info[1], HTTPError) and err.exc_info[1].code == 503): + if not isinstance(err.exc_info[1], (TransportError, UnavailableVideoError)) or (isinstance(err.exc_info[1], HTTPError) and err.exc_info[1].status == 503): err.msg = f'{getattr(err, "msg", err)} ({tname})' raise diff --git a/test/test_networking.py b/test/test_networking.py index 147a4ff49..b60ed283b 100644 --- a/test/test_networking.py +++ b/test/test_networking.py @@ -1057,14 +1057,15 @@ def test_compat_request(self): urllib_req = urllib.request.Request('http://foo.bar', data=b'test', method='PUT', headers={'X-Test': '1'}) urllib_req.add_unredirected_header('Cookie', 'bob=bob') urllib_req.timeout = 2 - - req = ydl.urlopen(urllib_req).request - assert req.url == urllib_req.get_full_url() - assert req.data == urllib_req.data - assert req.method == urllib_req.get_method() - assert 'X-Test' in req.headers - assert 'Cookie' in req.headers - assert req.extensions.get('timeout') == 2 + with warnings.catch_warnings(): + warnings.simplefilter('ignore', category=DeprecationWarning) + req = ydl.urlopen(urllib_req).request + assert req.url == urllib_req.get_full_url() + assert req.data == urllib_req.data + assert req.method == urllib_req.get_method() + assert 'X-Test' in req.headers + assert 'Cookie' in req.headers + assert req.extensions.get('timeout') == 2 with pytest.raises(AssertionError): ydl.urlopen(None) @@ -1362,7 +1363,9 @@ def test_get_header(self): def test_compat(self): res = Response(io.BytesIO(b''), url='test://', status=404, headers={'test': 'test'}) - assert res.code == res.getcode() == res.status - assert res.geturl() == res.url - assert res.info() is res.headers - assert res.getheader('test') == res.get_header('test') + with warnings.catch_warnings(): + warnings.simplefilter('ignore', category=DeprecationWarning) + assert res.code == res.getcode() == res.status + assert res.geturl() == res.url + assert res.info() is res.headers + assert res.getheader('test') == res.get_header('test') diff --git a/test/test_networking_utils.py b/test/test_networking_utils.py index f9f876af3..ef46f79ed 100644 --- a/test/test_networking_utils.py +++ b/test/test_networking_utils.py @@ -8,11 +8,13 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +import contextlib import io import platform import random import ssl import urllib.error +import warnings from yt_dlp.cookies import YoutubeDLCookieJar from yt_dlp.dependencies import certifi @@ -202,20 +204,58 @@ def test_compat_http_error(self): assert isinstance(error, HTTPError) assert isinstance(error, urllib.error.HTTPError) - assert error.code == 403 - assert error.getcode() == 403 - assert error.hdrs is error.response.headers - assert error.info() is error.response.headers - assert error.headers is error.response.headers - assert error.filename == error.response.url - assert error.url == error.response.url - assert error.geturl() == error.response.url + @contextlib.contextmanager + def raises_deprecation_warning(): + with warnings.catch_warnings(record=True) as w: + warnings.simplefilter('always') + yield + + if len(w) == 0: + pytest.fail('Did not raise DeprecationWarning') + if len(w) > 1: + pytest.fail(f'Raised multiple warnings: {w}') + + if not issubclass(w[-1].category, DeprecationWarning): + pytest.fail(f'Expected DeprecationWarning, got {w[-1].category}') + w.clear() + + with raises_deprecation_warning(): + assert error.code == 403 + + with raises_deprecation_warning(): + assert error.getcode() == 403 + + with raises_deprecation_warning(): + assert error.hdrs is error.response.headers + + with raises_deprecation_warning(): + assert error.info() is error.response.headers + + with raises_deprecation_warning(): + assert error.headers is error.response.headers + + with raises_deprecation_warning(): + assert error.filename == error.response.url + + with raises_deprecation_warning(): + assert error.url == error.response.url + + with raises_deprecation_warning(): + assert error.geturl() == error.response.url # Passthrough file operations - assert error.read() == b'test' - assert not error.closed - # Technically Response operations are also passed through, which should not be used. - assert error.get_header('test') == 'test' + with raises_deprecation_warning(): + assert error.read() == b'test' + + with raises_deprecation_warning(): + assert not error.closed + + with raises_deprecation_warning(): + # Technically Response operations are also passed through, which should not be used. + assert error.get_header('test') == 'test' + + # Should not raise a warning + error.close() @pytest.mark.skipif( platform.python_implementation() == 'PyPy', reason='garbage collector works differently in pypy') diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index 29a18aef0..850eb8ae0 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -33,7 +33,7 @@ from .extractor.common import UnsupportedURLIE from .extractor.openload import PhantomJSwrapper from .minicurses import format_text -from .networking import Request, RequestDirector +from .networking import HEADRequest, Request, RequestDirector from .networking.common import _REQUEST_HANDLERS from .networking.exceptions import ( HTTPError, @@ -41,6 +41,7 @@ RequestError, SSLError, _CompatHTTPError, + network_exceptions, ) from .plugins import directories as plugin_directories from .postprocessor import _PLUGIN_CLASSES as plugin_pps @@ -80,7 +81,6 @@ ExtractorError, FormatSorter, GeoRestrictedError, - HEADRequest, ISO3166Utils, LazyList, MaxDownloadsReached, @@ -122,7 +122,6 @@ locked_file, make_archive_id, make_dir, - network_exceptions, number_of_digits, orderedSet, orderedSet_from_options, @@ -135,7 +134,6 @@ sanitize_filename, sanitize_path, sanitize_url, - std_headers, str_or_none, strftime_or_none, subtitles_filename, @@ -158,6 +156,7 @@ HTTPHeaderDict, clean_headers, clean_proxies, + std_headers, ) from .version import CHANNEL, RELEASE_GIT_HEAD, VARIANT, __version__ @@ -4019,6 +4018,9 @@ def urlopen(self, req): if isinstance(req, str): req = Request(req) elif isinstance(req, urllib.request.Request): + self.deprecation_warning( + 'Passing a urllib.request.Request object to YoutubeDL.urlopen() is deprecated. ' + 'Use yt_dlp.networking.common.Request instead.') req = urllib_req_to_req(req) assert isinstance(req, Request) @@ -4242,7 +4244,7 @@ def _write_thumbnails(self, label, info_dict, filename, thumb_filename_base=None ret.append((thumb_filename, thumb_filename_final)) t['filepath'] = thumb_filename except network_exceptions as err: - if isinstance(err, urllib.error.HTTPError) and err.code == 404: + if isinstance(err, HTTPError) and err.status == 404: self.to_screen(f'[info] {thumb_display_id.title()} does not exist') else: self.report_warning(f'Unable to download {thumb_display_id}: {err}') diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index b81277a57..991dbcda7 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -57,11 +57,11 @@ read_stdin, render_table, setproctitle, - std_headers, traverse_obj, variadic, write_string, ) +from .utils.networking import std_headers from .YoutubeDL import YoutubeDL _IN_CLI = False diff --git a/yt_dlp/compat/_deprecated.py b/yt_dlp/compat/_deprecated.py index 342f1f80d..14d37b236 100644 --- a/yt_dlp/compat/_deprecated.py +++ b/yt_dlp/compat/_deprecated.py @@ -8,7 +8,6 @@ compat_b64decode = base64.b64decode -compat_HTTPError = urllib.error.HTTPError compat_urlparse = urllib.parse compat_parse_qs = urllib.parse.parse_qs compat_urllib_parse_unquote = urllib.parse.unquote diff --git a/yt_dlp/compat/_legacy.py b/yt_dlp/compat/_legacy.py index 83bf869a8..912907a02 100644 --- a/yt_dlp/compat/_legacy.py +++ b/yt_dlp/compat/_legacy.py @@ -70,6 +70,7 @@ def compat_setenv(key, value, env=os.environ): compat_HTMLParser = compat_html_parser_HTMLParser = html.parser.HTMLParser compat_http_client = http.client compat_http_server = http.server +compat_HTTPError = urllib.error.HTTPError compat_input = input compat_integer_types = (int, ) compat_itertools_count = itertools.count diff --git a/yt_dlp/downloader/external.py b/yt_dlp/downloader/external.py index d4045e58f..e307502db 100644 --- a/yt_dlp/downloader/external.py +++ b/yt_dlp/downloader/external.py @@ -10,6 +10,7 @@ from .fragment import FragmentFD from ..compat import functools +from ..networking import Request from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor from ..utils import ( Popen, @@ -25,7 +26,6 @@ encodeFilename, find_available_port, remove_end, - sanitized_Request, traverse_obj, ) @@ -357,13 +357,12 @@ def aria2c_rpc(self, rpc_port, rpc_secret, method, params=()): 'method': method, 'params': [f'token:{rpc_secret}', *params], }).encode('utf-8') - request = sanitized_Request( + request = Request( f'http://localhost:{rpc_port}/jsonrpc', data=d, headers={ 'Content-Type': 'application/json', 'Content-Length': f'{len(d)}', - 'Ytdl-request-proxy': '__noproxy__', - }) + }, proxies={'all': None}) with self.ydl.urlopen(request) as r: resp = json.load(r) assert resp.get('id') == sanitycheck, 'Something went wrong with RPC server' diff --git a/yt_dlp/downloader/f4m.py b/yt_dlp/downloader/f4m.py index 306f92192..28cbba016 100644 --- a/yt_dlp/downloader/f4m.py +++ b/yt_dlp/downloader/f4m.py @@ -3,11 +3,11 @@ import itertools import struct import time -import urllib.error import urllib.parse from .fragment import FragmentFD from ..compat import compat_etree_fromstring +from ..networking.exceptions import HTTPError from ..utils import fix_xml_ampersands, xpath_text @@ -312,7 +312,7 @@ def real_download(self, filename, info_dict): self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) - man_url = urlh.geturl() + man_url = urlh.url # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244 # and https://github.com/ytdl-org/youtube-dl/issues/7823) @@ -407,8 +407,8 @@ def real_download(self, filename, info_dict): if box_type == b'mdat': self._append_fragment(ctx, box_data) break - except urllib.error.HTTPError as err: - if live and (err.code == 404 or err.code == 410): + except HTTPError as err: + if live and (err.status == 404 or err.status == 410): # We didn't keep up with the live window. Continue # with the next available fragment. msg = 'Fragment %d unavailable' % frag_i diff --git a/yt_dlp/downloader/fragment.py b/yt_dlp/downloader/fragment.py index 069815326..b4b680dae 100644 --- a/yt_dlp/downloader/fragment.py +++ b/yt_dlp/downloader/fragment.py @@ -1,24 +1,19 @@ import concurrent.futures import contextlib -import http.client import json import math import os import struct import time -import urllib.error from .common import FileDownloader from .http import HttpFD from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 from ..compat import compat_os_name -from ..utils import ( - DownloadError, - RetryManager, - encodeFilename, - sanitized_Request, - traverse_obj, -) +from ..networking import Request +from ..networking.exceptions import HTTPError, IncompleteRead +from ..utils import DownloadError, RetryManager, encodeFilename, traverse_obj +from ..utils.networking import HTTPHeaderDict class HttpQuietDownloader(HttpFD): @@ -75,7 +70,7 @@ def report_skip_fragment(self, frag_index, err=None): def _prepare_url(self, info_dict, url): headers = info_dict.get('http_headers') - return sanitized_Request(url, None, headers) if headers else url + return Request(url, None, headers) if headers else url def _prepare_and_start_frag_download(self, ctx, info_dict): self._prepare_frag_download(ctx) @@ -457,7 +452,7 @@ def download_fragment(fragment, ctx): frag_index = ctx['fragment_index'] = fragment['frag_index'] ctx['last_error'] = None - headers = info_dict.get('http_headers', {}).copy() + headers = HTTPHeaderDict(info_dict.get('http_headers')) byte_range = fragment.get('byte_range') if byte_range: headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1) @@ -477,7 +472,7 @@ def error_callback(err, count, retries): if not self._download_fragment( ctx, fragment['url'], info_dict, headers, info_dict.get('request_data')): return - except (urllib.error.HTTPError, http.client.IncompleteRead) as err: + except (HTTPError, IncompleteRead) as err: retry.error = err continue except DownloadError: # has own retry settings diff --git a/yt_dlp/downloader/hls.py b/yt_dlp/downloader/hls.py index ab7d496d4..d4b3f0320 100644 --- a/yt_dlp/downloader/hls.py +++ b/yt_dlp/downloader/hls.py @@ -75,7 +75,7 @@ def real_download(self, filename, info_dict): self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME) urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url)) - man_url = urlh.geturl() + man_url = urlh.url s = urlh.read().decode('utf-8', 'ignore') can_download, message = self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')), None diff --git a/yt_dlp/downloader/http.py b/yt_dlp/downloader/http.py index 45d094721..f5237443e 100644 --- a/yt_dlp/downloader/http.py +++ b/yt_dlp/downloader/http.py @@ -1,10 +1,14 @@ import os import random import time -import urllib.error from .common import FileDownloader -from ..networking.exceptions import CertificateVerifyError, TransportError +from ..networking import Request +from ..networking.exceptions import ( + CertificateVerifyError, + HTTPError, + TransportError, +) from ..utils import ( ContentTooShortError, RetryManager, @@ -14,10 +18,10 @@ encodeFilename, int_or_none, parse_http_range, - sanitized_Request, try_call, write_xattr, ) +from ..utils.networking import HTTPHeaderDict class HttpFD(FileDownloader): @@ -36,10 +40,7 @@ class DownloadContext(dict): ctx.stream = None # Disable compression - headers = {'Accept-Encoding': 'identity'} - add_headers = info_dict.get('http_headers') - if add_headers: - headers.update(add_headers) + headers = HTTPHeaderDict({'Accept-Encoding': 'identity'}, info_dict.get('http_headers')) is_test = self.params.get('test', False) chunk_size = self._TEST_FILE_SIZE if is_test else ( @@ -110,10 +111,10 @@ def establish_connection(): if try_call(lambda: range_end >= ctx.content_len): range_end = ctx.content_len - 1 - request = sanitized_Request(url, request_data, headers) + request = Request(url, request_data, headers) has_range = range_start is not None if has_range: - request.add_header('Range', f'bytes={int(range_start)}-{int_or_none(range_end) or ""}') + request.headers['Range'] = f'bytes={int(range_start)}-{int_or_none(range_end) or ""}' # Establish connection try: ctx.data = self.ydl.urlopen(request) @@ -144,17 +145,17 @@ def establish_connection(): self.report_unable_to_resume() ctx.resume_len = 0 ctx.open_mode = 'wb' - ctx.data_len = ctx.content_len = int_or_none(ctx.data.info().get('Content-length', None)) - except urllib.error.HTTPError as err: - if err.code == 416: + ctx.data_len = ctx.content_len = int_or_none(ctx.data.headers.get('Content-length', None)) + except HTTPError as err: + if err.status == 416: # Unable to resume (requested range not satisfiable) try: # Open the connection again without the range header ctx.data = self.ydl.urlopen( - sanitized_Request(url, request_data, headers)) - content_length = ctx.data.info()['Content-Length'] - except urllib.error.HTTPError as err: - if err.code < 500 or err.code >= 600: + Request(url, request_data, headers)) + content_length = ctx.data.headers['Content-Length'] + except HTTPError as err: + if err.status < 500 or err.status >= 600: raise else: # Examine the reported length @@ -182,7 +183,7 @@ def establish_connection(): ctx.resume_len = 0 ctx.open_mode = 'wb' return - elif err.code < 500 or err.code >= 600: + elif err.status < 500 or err.status >= 600: # Unexpected HTTP error raise raise RetryDownload(err) @@ -198,9 +199,9 @@ def close_stream(): ctx.stream = None def download(): - data_len = ctx.data.info().get('Content-length') + data_len = ctx.data.headers.get('Content-length') - if ctx.data.info().get('Content-encoding'): + if ctx.data.headers.get('Content-encoding'): # Content-encoding is present, Content-length is not reliable anymore as we are # doing auto decompression. (See: https://github.com/yt-dlp/yt-dlp/pull/6176) data_len = None @@ -345,7 +346,7 @@ def retry(e): # Update file modification time if self.params.get('updatetime', True): - info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.info().get('last-modified', None)) + info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None)) self._hook_progress({ 'downloaded_bytes': byte_counter, diff --git a/yt_dlp/downloader/ism.py b/yt_dlp/downloader/ism.py index a157a8ad9..dd688f586 100644 --- a/yt_dlp/downloader/ism.py +++ b/yt_dlp/downloader/ism.py @@ -2,9 +2,9 @@ import io import struct import time -import urllib.error from .fragment import FragmentFD +from ..networking.exceptions import HTTPError from ..utils import RetryManager u8 = struct.Struct('>B') @@ -271,7 +271,7 @@ def real_download(self, filename, info_dict): write_piff_header(ctx['dest_stream'], info_dict['_download_params']) extra_state['ism_track_written'] = True self._append_fragment(ctx, frag_content) - except urllib.error.HTTPError as err: + except HTTPError as err: retry.error = err continue diff --git a/yt_dlp/downloader/niconico.py b/yt_dlp/downloader/niconico.py index 7d8575c2a..5720f6eb8 100644 --- a/yt_dlp/downloader/niconico.py +++ b/yt_dlp/downloader/niconico.py @@ -5,13 +5,8 @@ from . import get_suitable_downloader from .common import FileDownloader from .external import FFmpegFD -from ..utils import ( - DownloadError, - WebSocketsWrapper, - sanitized_Request, - str_or_none, - try_get, -) +from ..networking import Request +from ..utils import DownloadError, WebSocketsWrapper, str_or_none, try_get class NiconicoDmcFD(FileDownloader): @@ -33,7 +28,7 @@ def real_download(self, filename, info_dict): heartbeat_data = heartbeat_info_dict['data'].encode() heartbeat_interval = heartbeat_info_dict.get('interval', 30) - request = sanitized_Request(heartbeat_url, heartbeat_data) + request = Request(heartbeat_url, heartbeat_data) def heartbeat(): try: diff --git a/yt_dlp/downloader/youtube_live_chat.py b/yt_dlp/downloader/youtube_live_chat.py index 5928fecf0..c7a86374a 100644 --- a/yt_dlp/downloader/youtube_live_chat.py +++ b/yt_dlp/downloader/youtube_live_chat.py @@ -1,8 +1,8 @@ import json import time -import urllib.error from .fragment import FragmentFD +from ..networking.exceptions import HTTPError from ..utils import ( RegexNotFoundError, RetryManager, @@ -10,6 +10,7 @@ int_or_none, try_get, ) +from ..utils.networking import HTTPHeaderDict class YoutubeLiveChatFD(FragmentFD): @@ -37,10 +38,7 @@ def real_download(self, filename, info_dict): start_time = int(time.time() * 1000) def dl_fragment(url, data=None, headers=None): - http_headers = info_dict.get('http_headers', {}) - if headers: - http_headers = http_headers.copy() - http_headers.update(headers) + http_headers = HTTPHeaderDict(info_dict.get('http_headers'), headers) return self._download_fragment(ctx, url, info_dict, http_headers, data) def parse_actions_replay(live_chat_continuation): @@ -129,7 +127,7 @@ def download_and_parse_fragment(url, frag_index, request_data=None, headers=None or frag_index == 1 and try_refresh_replay_beginning or parse_actions_replay) return (True, *func(live_chat_continuation)) - except urllib.error.HTTPError as err: + except HTTPError as err: retry.error = err continue return False, None, None, None diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py index c9166b6b8..98ece8da7 100644 --- a/yt_dlp/extractor/abematv.py +++ b/yt_dlp/extractor/abematv.py @@ -22,7 +22,6 @@ int_or_none, intlist_to_bytes, OnDemandPagedList, - request_to_url, time_seconds, traverse_obj, update_url_query, @@ -137,7 +136,7 @@ def _get_videokey_from_ticket(self, ticket): return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey)) def abematv_license_open(self, url): - url = request_to_url(url) + url = url.get_full_url() if isinstance(url, urllib.request.Request) else url ticket = urllib.parse.urlparse(url).netloc response_data = self._get_videokey_from_ticket(ticket) return urllib.response.addinfourl(io.BytesIO(response_data), headers={ diff --git a/yt_dlp/extractor/adn.py b/yt_dlp/extractor/adn.py index f1f55e87f..b59dbc850 100644 --- a/yt_dlp/extractor/adn.py +++ b/yt_dlp/extractor/adn.py @@ -6,10 +6,8 @@ from .common import InfoExtractor from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7 -from ..compat import ( - compat_HTTPError, - compat_b64decode, -) +from ..compat import compat_b64decode +from ..networking.exceptions import HTTPError from ..utils import ( ass_subtitles_timecode, bytes_to_intlist, @@ -142,9 +140,9 @@ def _perform_login(self, username, password): self._HEADERS = {'authorization': 'Bearer ' + access_token} except ExtractorError as e: message = None - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: resp = self._parse_json( - e.cause.read().decode(), None, fatal=False) or {} + e.cause.response.read().decode(), None, fatal=False) or {} message = resp.get('message') or resp.get('code') self.report_warning(message or self._LOGIN_ERR_MESSAGE) @@ -195,14 +193,14 @@ def _real_extract(self, url): }) break except ExtractorError as e: - if not isinstance(e.cause, compat_HTTPError): + if not isinstance(e.cause, HTTPError): raise e - if e.cause.code == 401: + if e.cause.status == 401: # This usually goes away with a different random pkcs1pad, so retry continue - error = self._parse_json(e.cause.read(), video_id) + error = self._parse_json(e.cause.response.read(), video_id) message = error.get('message') if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country': self.raise_geo_restricted(msg=message) diff --git a/yt_dlp/extractor/adobepass.py b/yt_dlp/extractor/adobepass.py index 722a534ed..5eed0ca22 100644 --- a/yt_dlp/extractor/adobepass.py +++ b/yt_dlp/extractor/adobepass.py @@ -2,11 +2,11 @@ import json import re import time -import urllib.error import xml.etree.ElementTree as etree from .common import InfoExtractor from ..compat import compat_urlparse +from ..networking.exceptions import HTTPError from ..utils import ( NO_DEFAULT, ExtractorError, @@ -1394,7 +1394,7 @@ def post_form(form_page_res, note, data={}): form_page, urlh = form_page_res post_url = self._html_search_regex(r']+action=(["\'])(?P.+?)\1', form_page, 'post url', group='url') if not re.match(r'https?://', post_url): - post_url = compat_urlparse.urljoin(urlh.geturl(), post_url) + post_url = compat_urlparse.urljoin(urlh.url, post_url) form_data = self._hidden_inputs(form_page) form_data.update(data) return self._download_webpage_handle( @@ -1619,7 +1619,7 @@ def extract_redirect_url(html, url=None, fatal=False): hidden_data['history'] = 1 provider_login_page_res = self._download_webpage_handle( - urlh.geturl(), video_id, 'Sending first bookend', + urlh.url, video_id, 'Sending first bookend', query=hidden_data) provider_association_redirect, urlh = post_form( @@ -1629,7 +1629,7 @@ def extract_redirect_url(html, url=None, fatal=False): }) provider_refresh_redirect_url = extract_redirect_url( - provider_association_redirect, url=urlh.geturl()) + provider_association_redirect, url=urlh.url) last_bookend_page, urlh = self._download_webpage_handle( provider_refresh_redirect_url, video_id, @@ -1638,7 +1638,7 @@ def extract_redirect_url(html, url=None, fatal=False): hidden_data['history'] = 3 mvpd_confirm_page_res = self._download_webpage_handle( - urlh.geturl(), video_id, 'Sending final bookend', + urlh.url, video_id, 'Sending final bookend', query=hidden_data) post_form(mvpd_confirm_page_res, 'Confirming Login') @@ -1652,7 +1652,7 @@ def extract_redirect_url(html, url=None, fatal=False): hidden_data['history_val'] = 1 provider_login_redirect_page_res = self._download_webpage_handle( - urlh.geturl(), video_id, 'Sending First Bookend', + urlh.url, video_id, 'Sending First Bookend', query=hidden_data) provider_login_redirect_page, urlh = provider_login_redirect_page_res @@ -1680,7 +1680,7 @@ def extract_redirect_url(html, url=None, fatal=False): }) provider_refresh_redirect_url = extract_redirect_url( - provider_association_redirect, url=urlh.geturl()) + provider_association_redirect, url=urlh.url) last_bookend_page, urlh = self._download_webpage_handle( provider_refresh_redirect_url, video_id, @@ -1690,7 +1690,7 @@ def extract_redirect_url(html, url=None, fatal=False): hidden_data['history_val'] = 3 mvpd_confirm_page_res = self._download_webpage_handle( - urlh.geturl(), video_id, 'Sending Final Bookend', + urlh.url, video_id, 'Sending Final Bookend', query=hidden_data) post_form(mvpd_confirm_page_res, 'Confirming Login') @@ -1699,7 +1699,7 @@ def extract_redirect_url(html, url=None, fatal=False): # based redirect that should be followed. provider_redirect_page, urlh = provider_redirect_page_res provider_refresh_redirect_url = extract_redirect_url( - provider_redirect_page, url=urlh.geturl()) + provider_redirect_page, url=urlh.url) if provider_refresh_redirect_url: provider_redirect_page_res = self._download_webpage_handle( provider_refresh_redirect_url, video_id, @@ -1724,7 +1724,7 @@ def extract_redirect_url(html, url=None, fatal=False): 'requestor_id': requestor_id, }), headers=mvpd_headers) except ExtractorError as e: - if not mso_id and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: + if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401: raise_mvpd_required() raise if '[^/#?]+)' @@ -97,7 +97,7 @@ class CeskaTelevizeIE(InfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) webpage, urlh = self._download_webpage_handle(url, playlist_id) - parsed_url = compat_urllib_parse_urlparse(urlh.geturl()) + parsed_url = compat_urllib_parse_urlparse(urlh.url) site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize') playlist_title = self._og_search_title(webpage, default=None) if site_name and playlist_title: @@ -163,16 +163,16 @@ def _real_extract(self, url): entries = [] for user_agent in (None, USER_AGENTS['Safari']): - req = sanitized_Request( + req = Request( 'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/', data=urlencode_postdata(data)) - req.add_header('Content-type', 'application/x-www-form-urlencoded') - req.add_header('x-addr', '127.0.0.1') - req.add_header('X-Requested-With', 'XMLHttpRequest') + req.headers['Content-type'] = 'application/x-www-form-urlencoded' + req.headers['x-addr'] = '127.0.0.1' + req.headers['X-Requested-With'] = 'XMLHttpRequest' if user_agent: - req.add_header('User-Agent', user_agent) - req.add_header('Referer', url) + req.headers['User-Agent'] = user_agent + req.headers['Referer'] = url playlistpage = self._download_json(req, playlist_id, fatal=False) @@ -183,8 +183,8 @@ def _real_extract(self, url): if playlist_url == 'error_region': raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) - req.add_header('Referer', url) + req = Request(compat_urllib_parse_unquote(playlist_url)) + req.headers['Referer'] = url playlist = self._download_json(req, playlist_id, fatal=False) if not playlist: diff --git a/yt_dlp/extractor/cinetecamilano.py b/yt_dlp/extractor/cinetecamilano.py index 5e770ebac..9cffa11e8 100644 --- a/yt_dlp/extractor/cinetecamilano.py +++ b/yt_dlp/extractor/cinetecamilano.py @@ -1,6 +1,6 @@ import json -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, float_or_none, @@ -40,7 +40,7 @@ def _real_extract(self, url): 'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or '' }) except ExtractorError as e: - if ((isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 500) + if ((isinstance(e.cause, HTTPError) and e.cause.status == 500) or isinstance(e.cause, json.JSONDecodeError)): self.raise_login_required(method='cookies') raise diff --git a/yt_dlp/extractor/ciscowebex.py b/yt_dlp/extractor/ciscowebex.py index 40430505d..85585dffb 100644 --- a/yt_dlp/extractor/ciscowebex.py +++ b/yt_dlp/extractor/ciscowebex.py @@ -33,7 +33,7 @@ def _real_extract(self, url): if rcid: webpage = self._download_webpage(url, None, note='Getting video ID') url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url') - url = self._request_webpage(url, None, note='Resolving final URL').geturl() + url = self._request_webpage(url, None, note='Resolving final URL').url mobj = self._match_valid_url(url) subdomain = mobj.group('subdomain') siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2') @@ -49,7 +49,7 @@ def _real_extract(self, url): 'https://%s.webex.com/webappng/api/v1/recordings/%s/stream' % (subdomain, video_id), video_id, headers=headers, query={'siteurl': siteurl}, expected_status=(403, 429)) - if urlh.getcode() == 403: + if urlh.status == 403: if stream['code'] == 53004: self.raise_login_required() if stream['code'] == 53005: @@ -59,7 +59,7 @@ def _real_extract(self, url): 'This video is protected by a password, use the --video-password option', expected=True) raise ExtractorError(f'{self.IE_NAME} said: {stream["code"]} - {stream["message"]}', expected=True) - if urlh.getcode() == 429: + if urlh.status == 429: self.raise_login_required( f'{self.IE_NAME} asks you to solve a CAPTCHA. Solve CAPTCHA in browser and', method='cookies') diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 63156d3ac..d44918776 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -31,8 +31,12 @@ from ..cookies import LenientSimpleCookie from ..downloader.f4m import get_base_url, remove_encrypted_media from ..downloader.hls import HlsFD -from ..networking.common import HEADRequest, Request -from ..networking.exceptions import network_exceptions +from ..networking import HEADRequest, Request +from ..networking.exceptions import ( + HTTPError, + IncompleteRead, + network_exceptions, +) from ..utils import ( IDENTITY, JSON_LD_RE, @@ -729,7 +733,7 @@ def extract(self, url): e.ie = e.ie or self.IE_NAME, e.traceback = e.traceback or sys.exc_info()[2] raise - except http.client.IncompleteRead as e: + except IncompleteRead as e: raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url)) except (KeyError, StopIteration) as e: raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url)) @@ -788,16 +792,19 @@ def IE_NAME(cls): @staticmethod def __can_accept_status_code(err, expected_status): - assert isinstance(err, urllib.error.HTTPError) + assert isinstance(err, HTTPError) if expected_status is None: return False elif callable(expected_status): - return expected_status(err.code) is True + return expected_status(err.status) is True else: - return err.code in variadic(expected_status) + return err.status in variadic(expected_status) def _create_request(self, url_or_request, data=None, headers=None, query=None): if isinstance(url_or_request, urllib.request.Request): + self._downloader.deprecation_warning( + 'Passing a urllib.request.Request to _create_request() is deprecated. ' + 'Use yt_dlp.networking.common.Request instead.') url_or_request = urllib_req_to_req(url_or_request) elif not isinstance(url_or_request, Request): url_or_request = Request(url_or_request) @@ -839,7 +846,7 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa try: return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query)) except network_exceptions as err: - if isinstance(err, urllib.error.HTTPError): + if isinstance(err, HTTPError): if self.__can_accept_status_code(err, expected_status): return err.response @@ -973,11 +980,11 @@ def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errno if prefix is not None: webpage_bytes = prefix + webpage_bytes if self.get_param('dump_intermediate_pages', False): - self.to_screen('Dumping request to ' + urlh.geturl()) + self.to_screen('Dumping request to ' + urlh.url) dump = base64.b64encode(webpage_bytes).decode('ascii') self._downloader.to_screen(dump) if self.get_param('write_pages'): - filename = self._request_dump_filename(urlh.geturl(), video_id) + filename = self._request_dump_filename(urlh.url, video_id) self.to_screen(f'Saving request to {filename}') with open(filename, 'wb') as outf: outf.write(webpage_bytes) @@ -1109,7 +1116,7 @@ def _download_webpage( while True: try: return self.__download_webpage(url_or_request, video_id, note, errnote, None, fatal, *args, **kwargs) - except http.client.IncompleteRead as e: + except IncompleteRead as e: try_count += 1 if try_count >= tries: raise e @@ -1806,7 +1813,7 @@ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, quality= return [] manifest, urlh = res - manifest_url = urlh.geturl() + manifest_url = urlh.url return self._parse_f4m_formats( manifest, manifest_url, video_id, preference=preference, quality=quality, f4m_id=f4m_id, @@ -1965,7 +1972,7 @@ def _extract_m3u8_formats_and_subtitles( return [], {} m3u8_doc, urlh = res - m3u8_url = urlh.geturl() + m3u8_url = urlh.url return self._parse_m3u8_formats_and_subtitles( m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol, @@ -2243,7 +2250,7 @@ def _extract_smil_formats_and_subtitles(self, smil_url, video_id, fatal=True, f4 return [], {} smil, urlh = res - smil_url = urlh.geturl() + smil_url = urlh.url namespace = self._parse_smil_namespace(smil) @@ -2266,7 +2273,7 @@ def _extract_smil_info(self, smil_url, video_id, fatal=True, f4m_params=None): return {} smil, urlh = res - smil_url = urlh.geturl() + smil_url = urlh.url return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) @@ -2458,7 +2465,7 @@ def _extract_xspf_playlist(self, xspf_url, playlist_id, fatal=True): return [] xspf, urlh = res - xspf_url = urlh.geturl() + xspf_url = urlh.url return self._parse_xspf( xspf, playlist_id, xspf_url=xspf_url, @@ -2529,7 +2536,7 @@ def _extract_mpd_formats_and_subtitles( return [], {} # We could have been redirected to a new url when we retrieved our mpd file. - mpd_url = urlh.geturl() + mpd_url = urlh.url mpd_base_url = base_url(mpd_url) return self._parse_mpd_formats_and_subtitles( @@ -2900,7 +2907,7 @@ def _extract_ism_formats_and_subtitles(self, ism_url, video_id, ism_id=None, not if ism_doc is None: return [], {} - return self._parse_ism_formats_and_subtitles(ism_doc, urlh.geturl(), ism_id) + return self._parse_ism_formats_and_subtitles(ism_doc, urlh.url, ism_id) def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None): """ diff --git a/yt_dlp/extractor/crackle.py b/yt_dlp/extractor/crackle.py index 46100151a..1ef90b5a0 100644 --- a/yt_dlp/extractor/crackle.py +++ b/yt_dlp/extractor/crackle.py @@ -4,7 +4,7 @@ import time from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, float_or_none, @@ -113,7 +113,7 @@ def _real_extract(self, url): errnote='Unable to download media JSON') except ExtractorError as e: # 401 means geo restriction, trying next country - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: continue raise diff --git a/yt_dlp/extractor/crunchyroll.py b/yt_dlp/extractor/crunchyroll.py index 910504ed2..adb3d5dcf 100644 --- a/yt_dlp/extractor/crunchyroll.py +++ b/yt_dlp/extractor/crunchyroll.py @@ -1,7 +1,7 @@ import base64 -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, float_or_none, @@ -114,7 +114,7 @@ def _call_api(self, path, internal_id, lang, note='api', query={}): result = self._call_base_api( path, internal_id, lang, f'Downloading {note} JSON ({self._API_ENDPOINT})', query=query) except ExtractorError as error: - if isinstance(error.cause, urllib.error.HTTPError) and error.cause.code == 404: + if isinstance(error.cause, HTTPError) and error.cause.status == 404: return None raise diff --git a/yt_dlp/extractor/cultureunplugged.py b/yt_dlp/extractor/cultureunplugged.py index 2fb22800f..9c8509f1f 100644 --- a/yt_dlp/extractor/cultureunplugged.py +++ b/yt_dlp/extractor/cultureunplugged.py @@ -1,10 +1,8 @@ import time from .common import InfoExtractor -from ..utils import ( - int_or_none, - HEADRequest, -) +from ..networking import HEADRequest +from ..utils import int_or_none class CultureUnpluggedIE(InfoExtractor): diff --git a/yt_dlp/extractor/dacast.py b/yt_dlp/extractor/dacast.py index cf683bad4..4e81aa4a7 100644 --- a/yt_dlp/extractor/dacast.py +++ b/yt_dlp/extractor/dacast.py @@ -1,9 +1,9 @@ import hashlib import re import time -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, classproperty, @@ -105,7 +105,7 @@ def _real_extract(self, url): formats = self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls') except ExtractorError as e: # CDN will randomly respond with 403 - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: retry.error = e continue raise diff --git a/yt_dlp/extractor/dailymotion.py b/yt_dlp/extractor/dailymotion.py index 2a44718fb..21263d41b 100644 --- a/yt_dlp/extractor/dailymotion.py +++ b/yt_dlp/extractor/dailymotion.py @@ -3,7 +3,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, OnDemandPagedList, @@ -68,9 +68,9 @@ def _call_api(self, object_type, xid, object_fields, note, filter_extra=None): None, 'Downloading Access Token', data=urlencode_postdata(data))['access_token'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: raise ExtractorError(self._parse_json( - e.cause.read().decode(), xid)['error_description'], expected=True) + e.cause.response.read().decode(), xid)['error_description'], expected=True) raise self._set_dailymotion_cookie('access_token' if username else 'client_token', token) self._HEADERS['Authorization'] = 'Bearer ' + token diff --git a/yt_dlp/extractor/discovery.py b/yt_dlp/extractor/discovery.py index e6e109d5c..75b464353 100644 --- a/yt_dlp/extractor/discovery.py +++ b/yt_dlp/extractor/discovery.py @@ -3,8 +3,8 @@ from .discoverygo import DiscoveryGoBaseIE from ..compat import compat_urllib_parse_unquote +from ..networking.exceptions import HTTPError from ..utils import ExtractorError -from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): @@ -100,9 +100,9 @@ def _real_extract(self, url): self._API_BASE_URL + 'streaming/video/' + video_id, display_id, 'Downloading streaming JSON metadata', headers=headers) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): + if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403): e_description = self._parse_json( - e.cause.read().decode(), display_id)['description'] + e.cause.response.read().decode(), display_id)['description'] if 'resource not available for country' in e_description: self.raise_geo_restricted(countries=self._GEO_COUNTRIES) if 'Authorized Networks' in e_description: diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index cf6d14934..6404752f7 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -2,7 +2,7 @@ import uuid from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -39,7 +39,7 @@ def _get_auth(self, disco_base, display_id, realm, needs_device_id=True): return f'Bearer {token}' def _process_errors(self, e, geo_countries): - info = self._parse_json(e.cause.read().decode('utf-8'), None) + info = self._parse_json(e.cause.response.read().decode('utf-8'), None) error = info['errors'][0] error_code = error.get('code') if error_code == 'access.denied.geoblocked': @@ -87,7 +87,7 @@ def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domai 'include': 'images,primaryChannel,show,tags' }) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: self._process_errors(e, geo_countries) raise video_id = video['data']['id'] @@ -99,7 +99,7 @@ def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domai streaming = self._download_video_playback_info( disco_base, video_id, headers) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: self._process_errors(e, geo_countries) raise for format_dict in streaming: diff --git a/yt_dlp/extractor/eagleplatform.py b/yt_dlp/extractor/eagleplatform.py index 9ebd24d80..739d17912 100644 --- a/yt_dlp/extractor/eagleplatform.py +++ b/yt_dlp/extractor/eagleplatform.py @@ -2,7 +2,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -111,8 +111,8 @@ def _download_json(self, url_or_request, video_id, *args, **kwargs): response = super(EaglePlatformIE, self)._download_json( url_or_request, video_id, *args, **kwargs) except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError): - response = self._parse_json(ee.cause.read().decode('utf-8'), video_id) + if isinstance(ee.cause, HTTPError): + response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id) self._handle_error(response) raise return response diff --git a/yt_dlp/extractor/eitb.py b/yt_dlp/extractor/eitb.py index bd027da6b..66afbb6bb 100644 --- a/yt_dlp/extractor/eitb.py +++ b/yt_dlp/extractor/eitb.py @@ -1,10 +1,6 @@ from .common import InfoExtractor -from ..utils import ( - float_or_none, - int_or_none, - parse_iso8601, - sanitized_Request, -) +from ..networking import Request +from ..utils import float_or_none, int_or_none, parse_iso8601 class EitbIE(InfoExtractor): @@ -54,7 +50,7 @@ def _real_extract(self, url): hls_url = media.get('HLS_SURL') if hls_url: - request = sanitized_Request( + request = Request( 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/', headers={'Referer': url}) token_data = self._download_json( diff --git a/yt_dlp/extractor/eporner.py b/yt_dlp/extractor/eporner.py index a2337979b..aee2dee58 100644 --- a/yt_dlp/extractor/eporner.py +++ b/yt_dlp/extractor/eporner.py @@ -52,7 +52,7 @@ def _real_extract(self, url): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(urlh.geturl()) + video_id = self._match_id(urlh.url) hash = self._search_regex( r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash') diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index 9d871eb28..9f4d3fb78 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -8,6 +8,8 @@ compat_str, compat_urllib_parse_unquote, ) +from ..networking import Request +from ..networking.exceptions import network_exceptions from ..utils import ( ExtractorError, clean_html, @@ -19,11 +21,9 @@ int_or_none, js_to_json, merge_dicts, - network_exceptions, parse_count, parse_qs, qualities, - sanitized_Request, traverse_obj, try_get, url_or_none, @@ -319,7 +319,7 @@ class FacebookIE(InfoExtractor): } def _perform_login(self, username, password): - login_page_req = sanitized_Request(self._LOGIN_URL) + login_page_req = Request(self._LOGIN_URL) self._set_cookie('facebook.com', 'locale', 'en_US') login_page = self._download_webpage(login_page_req, None, note='Downloading login page', @@ -340,8 +340,8 @@ def _perform_login(self, username, password): 'timezone': '-60', 'trynum': '1', } - request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request = Request(self._LOGIN_URL, urlencode_postdata(login_form)) + request.headers['Content-Type'] = 'application/x-www-form-urlencoded' try: login_results = self._download_webpage(request, None, note='Logging in', errnote='unable to fetch login page') @@ -367,8 +367,8 @@ def _perform_login(self, username, password): 'h': h, 'name_action_selected': 'dont_save', } - check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) - check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') + check_req = Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) + check_req.headers['Content-Type'] = 'application/x-www-form-urlencoded' check_response = self._download_webpage(check_req, None, note='Confirming login') if re.search(r'id="checkpointSubmitButton"', check_response) is not None: diff --git a/yt_dlp/extractor/fc2.py b/yt_dlp/extractor/fc2.py index dd5e088fc..ba19b6cab 100644 --- a/yt_dlp/extractor/fc2.py +++ b/yt_dlp/extractor/fc2.py @@ -3,11 +3,11 @@ from .common import InfoExtractor from ..compat import compat_parse_qs from ..dependencies import websockets +from ..networking import Request from ..utils import ( ExtractorError, WebSocketsWrapper, js_to_json, - sanitized_Request, traverse_obj, update_url_query, urlencode_postdata, @@ -57,7 +57,7 @@ def _login(self): } login_data = urlencode_postdata(login_form_strs) - request = sanitized_Request( + request = Request( 'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data) login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in') @@ -66,7 +66,7 @@ def _login(self): return False # this is also needed - login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done') + login_redir = Request('http://id.fc2.com/?mode=redirect&login=done') self._download_webpage( login_redir, None, note='Login redirect', errnote='Login redirect failed') diff --git a/yt_dlp/extractor/filmon.py b/yt_dlp/extractor/filmon.py index 9a93cb984..0cd18f494 100644 --- a/yt_dlp/extractor/filmon.py +++ b/yt_dlp/extractor/filmon.py @@ -1,8 +1,6 @@ from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_HTTPError, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( qualities, strip_or_none, @@ -40,8 +38,8 @@ def _real_extract(self, url): 'https://www.filmon.com/api/vod/movie?id=%s' % video_id, video_id)['response'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): - errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason'] + if isinstance(e.cause, HTTPError): + errmsg = self._parse_json(e.cause.response.read().decode(), video_id)['reason'] raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) raise @@ -124,8 +122,8 @@ def _real_extract(self, url): channel_data = self._download_json( 'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): - errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message'] + if isinstance(e.cause, HTTPError): + errmsg = self._parse_json(e.cause.response.read().decode(), channel_id)['message'] raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) raise diff --git a/yt_dlp/extractor/fox.py b/yt_dlp/extractor/fox.py index 15c0c48c1..8fb4ada6b 100644 --- a/yt_dlp/extractor/fox.py +++ b/yt_dlp/extractor/fox.py @@ -3,10 +3,10 @@ from .common import InfoExtractor from ..compat import ( - compat_HTTPError, compat_str, compat_urllib_parse_unquote, ) +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -68,9 +68,9 @@ def _call_api(self, path, video_id, data=None): 'https://api3.fox.com/v2.0/' + path, video_id, data=data, headers=headers) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: entitlement_issues = self._parse_json( - e.cause.read().decode(), video_id)['entitlementIssues'] + e.cause.response.read().decode(), video_id)['entitlementIssues'] for e in entitlement_issues: if e.get('errorCode') == 1005: raise ExtractorError( @@ -123,8 +123,8 @@ def _real_extract(self, url): try: m3u8_url = self._download_json(release_url, video_id)['playURL'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - error = self._parse_json(e.cause.read().decode(), video_id) + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + error = self._parse_json(e.cause.response.read().decode(), video_id) if error.get('exception') == 'GeoLocationBlocked': self.raise_geo_restricted(countries=['US']) raise ExtractorError(error['description'], expected=True) diff --git a/yt_dlp/extractor/foxsports.py b/yt_dlp/extractor/foxsports.py index f906a1718..8e89ccf84 100644 --- a/yt_dlp/extractor/foxsports.py +++ b/yt_dlp/extractor/foxsports.py @@ -1,6 +1,7 @@ from .common import InfoExtractor from .uplynk import UplynkPreplayIE -from ..utils import HEADRequest, float_or_none, make_archive_id, smuggle_url +from ..networking import HEADRequest +from ..utils import float_or_none, make_archive_id, smuggle_url class FoxSportsIE(InfoExtractor): @@ -35,7 +36,7 @@ def _real_extract(self, url): 'x-api-key': 'cf289e299efdfa39fb6316f259d1de93', }) preplay_url = self._request_webpage( - HEADRequest(data['url']), video_id, 'Fetching preplay URL').geturl() + HEADRequest(data['url']), video_id, 'Fetching preplay URL').url return { '_type': 'url_transparent', diff --git a/yt_dlp/extractor/fujitv.py b/yt_dlp/extractor/fujitv.py index 668bb2743..77e826e2d 100644 --- a/yt_dlp/extractor/fujitv.py +++ b/yt_dlp/extractor/fujitv.py @@ -1,5 +1,5 @@ -from ..utils import HEADRequest from .common import InfoExtractor +from ..networking import HEADRequest class FujiTVFODPlus7IE(InfoExtractor): diff --git a/yt_dlp/extractor/funimation.py b/yt_dlp/extractor/funimation.py index 47c316664..41de85cc6 100644 --- a/yt_dlp/extractor/funimation.py +++ b/yt_dlp/extractor/funimation.py @@ -3,7 +3,7 @@ import string from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, @@ -46,8 +46,8 @@ def _perform_login(self, username, password): })) FunimationBaseIE._TOKEN = data['token'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read().decode(), None)['error'] + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read().decode(), None)['error'] raise ExtractorError(error, expected=True) raise diff --git a/yt_dlp/extractor/gdcvault.py b/yt_dlp/extractor/gdcvault.py index 2878bbd88..4265feb61 100644 --- a/yt_dlp/extractor/gdcvault.py +++ b/yt_dlp/extractor/gdcvault.py @@ -2,13 +2,8 @@ from .common import InfoExtractor from .kaltura import KalturaIE -from ..utils import ( - HEADRequest, - remove_start, - sanitized_Request, - smuggle_url, - urlencode_postdata, -) +from ..networking import HEADRequest, Request +from ..utils import remove_start, smuggle_url, urlencode_postdata class GDCVaultIE(InfoExtractor): @@ -138,8 +133,8 @@ def _login(self, webpage_url, display_id): 'password': password, } - request = sanitized_Request(login_url, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request = Request(login_url, urlencode_postdata(login_form)) + request.headers['Content-Type'] = 'application/x-www-form-urlencoded' self._download_webpage(request, display_id, 'Logging in') start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page') self._download_webpage(logout_url, display_id, 'Logging out') @@ -163,7 +158,7 @@ def _real_extract(self, url): video_url = 'http://www.gdcvault.com' + direct_url # resolve the url so that we can detect the correct extension video_url = self._request_webpage( - HEADRequest(video_url), video_id).geturl() + HEADRequest(video_url), video_id).url return { 'id': video_id, diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index 87cf11d6b..8fa4c6221 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -2431,7 +2431,7 @@ def _real_extract(self, url): 'Accept-Encoding': 'identity', **smuggled_data.get('http_headers', {}) }) - new_url = full_response.geturl() + new_url = full_response.url url = urllib.parse.urlparse(url)._replace(scheme=urllib.parse.urlparse(new_url).scheme).geturl() if new_url != extract_basic_auth(url)[0]: self.report_following_redirect(new_url) @@ -2529,12 +2529,12 @@ def _real_extract(self, url): return self.playlist_result( self._parse_xspf( doc, video_id, xspf_url=url, - xspf_base_url=full_response.geturl()), + xspf_base_url=full_response.url), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles( doc, - mpd_base_url=full_response.geturl().rpartition('/')[0], + mpd_base_url=full_response.url.rpartition('/')[0], mpd_url=url) self._extra_manifest_info(info_dict, url) self.report_detected('DASH manifest') @@ -2572,7 +2572,7 @@ def _extract_embeds(self, url, webpage, *, urlh=None, info_dict={}): info_dict = types.MappingProxyType(info_dict) # Prevents accidental mutation video_id = traverse_obj(info_dict, 'display_id', 'id') or self._generic_id(url) url, smuggled_data = unsmuggle_url(url, {}) - actual_url = urlh.geturl() if urlh else url + actual_url = urlh.url if urlh else url # Sometimes embedded video player is hidden behind percent encoding # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448) diff --git a/yt_dlp/extractor/globo.py b/yt_dlp/extractor/globo.py index a7be2cb76..df98f093c 100644 --- a/yt_dlp/extractor/globo.py +++ b/yt_dlp/extractor/globo.py @@ -8,8 +8,8 @@ from ..compat import ( compat_str, ) +from ..networking import HEADRequest from ..utils import ( - HEADRequest, ExtractorError, float_or_none, orderedSet, diff --git a/yt_dlp/extractor/googledrive.py b/yt_dlp/extractor/googledrive.py index 8a4cd1690..2fdec20f6 100644 --- a/yt_dlp/extractor/googledrive.py +++ b/yt_dlp/extractor/googledrive.py @@ -228,7 +228,7 @@ def add_source_format(urlh): # Using original URLs may result in redirect loop due to # google.com's cookies mistakenly used for googleusercontent.com # redirect URLs (see #23919). - 'url': urlh.geturl(), + 'url': urlh.url, 'ext': determine_ext(title, 'mp4').lower(), 'format_id': 'source', 'quality': 1, diff --git a/yt_dlp/extractor/hketv.py b/yt_dlp/extractor/hketv.py index 10879564f..e026996da 100644 --- a/yt_dlp/extractor/hketv.py +++ b/yt_dlp/extractor/hketv.py @@ -126,7 +126,7 @@ def _real_extract(self, url): # If we ever wanted to provide the final resolved URL that # does not require cookies, albeit with a shorter lifespan: # urlh = self._downloader.urlopen(file_url) - # resolved_url = urlh.geturl() + # resolved_url = urlh.url label = fmt.get('label') h = self._FORMAT_HEIGHTS.get(label) w = h * width // height if h and width and height else None diff --git a/yt_dlp/extractor/hotnewhiphop.py b/yt_dlp/extractor/hotnewhiphop.py index f8570cb86..3007fbb53 100644 --- a/yt_dlp/extractor/hotnewhiphop.py +++ b/yt_dlp/extractor/hotnewhiphop.py @@ -1,11 +1,7 @@ from .common import InfoExtractor from ..compat import compat_b64decode -from ..utils import ( - ExtractorError, - HEADRequest, - sanitized_Request, - urlencode_postdata, -) +from ..networking import HEADRequest, Request +from ..utils import ExtractorError, urlencode_postdata class HotNewHipHopIE(InfoExtractor): @@ -36,9 +32,9 @@ def _real_extract(self, url): ('mediaType', 's'), ('mediaId', video_id), ]) - r = sanitized_Request( + r = Request( 'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata) - r.add_header('Content-Type', 'application/x-www-form-urlencoded') + r.headers['Content-Type'] = 'application/x-www-form-urlencoded' mkd = self._download_json( r, video_id, note='Requesting media key', errnote='Could not download media key') @@ -50,7 +46,7 @@ def _real_extract(self, url): req = self._request_webpage( redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL') - video_url = req.geturl() + video_url = req.url if video_url.endswith('.html'): raise ExtractorError('Redirect failed') diff --git a/yt_dlp/extractor/hotstar.py b/yt_dlp/extractor/hotstar.py index 591e23b8a..324e9f51d 100644 --- a/yt_dlp/extractor/hotstar.py +++ b/yt_dlp/extractor/hotstar.py @@ -6,7 +6,8 @@ import uuid from .common import InfoExtractor -from ..compat import compat_HTTPError, compat_str +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, @@ -233,7 +234,7 @@ def _real_extract(self, url): 'height': int_or_none(playback_set.get('height')), }] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: geo_restricted = True continue diff --git a/yt_dlp/extractor/hrti.py b/yt_dlp/extractor/hrti.py index cfec80d14..57b76e46b 100644 --- a/yt_dlp/extractor/hrti.py +++ b/yt_dlp/extractor/hrti.py @@ -1,13 +1,13 @@ import json from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking import Request +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, ExtractorError, int_or_none, parse_age_limit, - sanitized_Request, try_get, ) @@ -42,7 +42,7 @@ def _initialize_pre_login(self): 'application_version': self._APP_VERSION } - req = sanitized_Request(self._API_URL, data=json.dumps(app_data).encode('utf-8')) + req = Request(self._API_URL, data=json.dumps(app_data).encode('utf-8')) req.get_method = lambda: 'PUT' resources = self._download_json( @@ -73,8 +73,8 @@ def _perform_login(self, username, password): self._login_url, None, note='Logging in', errnote='Unable to log in', data=json.dumps(auth_data).encode('utf-8')) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 406: - auth_info = self._parse_json(e.cause.read().encode('utf-8'), None) + if isinstance(e.cause, HTTPError) and e.cause.status == 406: + auth_info = self._parse_json(e.cause.response.read().encode('utf-8'), None) else: raise diff --git a/yt_dlp/extractor/ign.py b/yt_dlp/extractor/ign.py index e4db7f9fa..64875f8ce 100644 --- a/yt_dlp/extractor/ign.py +++ b/yt_dlp/extractor/ign.py @@ -1,8 +1,9 @@ import re -import urllib.error +import urllib.parse from .common import InfoExtractor from ..compat import compat_parse_qs +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, @@ -27,9 +28,9 @@ def _checked_call_api(self, slug): try: return self._call_api(slug) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404: + if isinstance(e.cause, HTTPError) and e.cause.status == 404: e.cause.args = e.cause.args or [ - e.cause.geturl(), e.cause.getcode(), e.cause.reason] + e.cause.response.url, e.cause.status, e.cause.reason] raise ExtractorError( 'Content not found: expired?', cause=e.cause, expected=True) @@ -226,7 +227,7 @@ def _real_extract(self, url): parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed')) webpage, urlh = self._download_webpage_handle(embed_url, video_id) - new_url = urlh.geturl() + new_url = urlh.url ign_url = compat_parse_qs( urllib.parse.urlparse(new_url).query).get('url', [None])[-1] if ign_url: @@ -323,14 +324,14 @@ def _checked_call_api(self, slug): try: return self._call_api(slug) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError): + if isinstance(e.cause, HTTPError): e.cause.args = e.cause.args or [ - e.cause.geturl(), e.cause.getcode(), e.cause.reason] - if e.cause.code == 404: + e.cause.response.url, e.cause.status, e.cause.reason] + if e.cause.status == 404: raise ExtractorError( 'Content not found: expired?', cause=e.cause, expected=True) - elif e.cause.code == 503: + elif e.cause.status == 503: self.report_warning(error_to_compat_str(e.cause)) return raise diff --git a/yt_dlp/extractor/imggaming.py b/yt_dlp/extractor/imggaming.py index 8e220fd9f..a40aa2176 100644 --- a/yt_dlp/extractor/imggaming.py +++ b/yt_dlp/extractor/imggaming.py @@ -1,7 +1,7 @@ import json from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -52,9 +52,9 @@ def _extract_dve_api_url(self, media_id, media_type): return self._call_api( stream_path, media_id)['playerUrlCallback'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: raise ExtractorError( - self._parse_json(e.cause.read().decode(), media_id)['messages'][0], + self._parse_json(e.cause.response.read().decode(), media_id)['messages'][0], expected=True) raise diff --git a/yt_dlp/extractor/instagram.py b/yt_dlp/extractor/instagram.py index 02335138f..bfc4b7b88 100644 --- a/yt_dlp/extractor/instagram.py +++ b/yt_dlp/extractor/instagram.py @@ -3,9 +3,9 @@ import json import re import time -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, decode_base_n, @@ -442,7 +442,7 @@ def _real_extract(self, url): shared_data = self._search_json( r'window\._sharedData\s*=', webpage, 'shared data', video_id, fatal=False) or {} - if shared_data and self._LOGIN_URL not in urlh.geturl(): + if shared_data and self._LOGIN_URL not in urlh.url: media.update(traverse_obj( shared_data, ('entry_data', 'PostPage', 0, 'graphql', 'shortcode_media'), ('entry_data', 'PostPage', 0, 'media'), expected_type=dict) or {}) @@ -589,7 +589,7 @@ def _extract_graphql(self, data, url): except ExtractorError as e: # if it's an error caused by a bad query, and there are # more GIS templates to try, ignore it and keep trying - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: if gis_tmpl != gis_tmpls[-1]: continue raise diff --git a/yt_dlp/extractor/iprima.py b/yt_dlp/extractor/iprima.py index e58e9c2ee..6dec1510d 100644 --- a/yt_dlp/extractor/iprima.py +++ b/yt_dlp/extractor/iprima.py @@ -81,7 +81,7 @@ def _perform_login(self, username, password): note='Logging in') # a profile may need to be selected first, even when there is only a single one - if '/profile-select' in login_handle.geturl(): + if '/profile-select' in login_handle.url: profile_id = self._search_regex( r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id') @@ -89,7 +89,7 @@ def _perform_login(self, username, password): f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None, query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile') - code = traverse_obj(login_handle.geturl(), ({parse_qs}, 'code', 0)) + code = traverse_obj(login_handle.url, ({parse_qs}, 'code', 0)) if not code: raise ExtractorError('Login failed', expected=True) diff --git a/yt_dlp/extractor/kakao.py b/yt_dlp/extractor/kakao.py index 1f0f0a5d5..43055e89d 100644 --- a/yt_dlp/extractor/kakao.py +++ b/yt_dlp/extractor/kakao.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -101,8 +101,8 @@ def _real_extract(self, url): cdn_api_base, video_id, query=query, note='Downloading video URL for profile %s' % profile_name) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - resp = self._parse_json(e.cause.read().decode(), video_id) + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + resp = self._parse_json(e.cause.response.read().decode(), video_id) if resp.get('code') == 'GeoBlocked': self.raise_geo_restricted() raise diff --git a/yt_dlp/extractor/kick.py b/yt_dlp/extractor/kick.py index be1dfd4b1..d12437242 100644 --- a/yt_dlp/extractor/kick.py +++ b/yt_dlp/extractor/kick.py @@ -1,7 +1,6 @@ from .common import InfoExtractor - +from ..networking import HEADRequest from ..utils import ( - HEADRequest, UserNotLive, float_or_none, merge_dicts, diff --git a/yt_dlp/extractor/kuwo.py b/yt_dlp/extractor/kuwo.py index cfec1c50f..e8a061a10 100644 --- a/yt_dlp/extractor/kuwo.py +++ b/yt_dlp/extractor/kuwo.py @@ -91,7 +91,7 @@ def _real_extract(self, url): webpage, urlh = self._download_webpage_handle( url, song_id, note='Download song detail info', errnote='Unable to get song detail info') - if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage: + if song_id not in urlh.url or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage: raise ExtractorError('this song has been offline because of copyright issues', expected=True) song_name = self._html_search_regex( diff --git a/yt_dlp/extractor/la7.py b/yt_dlp/extractor/la7.py index 36bfaf5c3..a3cd12b00 100644 --- a/yt_dlp/extractor/la7.py +++ b/yt_dlp/extractor/la7.py @@ -1,13 +1,8 @@ import re from .common import InfoExtractor -from ..utils import ( - float_or_none, - HEADRequest, - int_or_none, - parse_duration, - unified_strdate, -) +from ..networking import HEADRequest +from ..utils import float_or_none, int_or_none, parse_duration, unified_strdate class LA7IE(InfoExtractor): diff --git a/yt_dlp/extractor/lbry.py b/yt_dlp/extractor/lbry.py index 23d3daf13..6af64f0df 100644 --- a/yt_dlp/extractor/lbry.py +++ b/yt_dlp/extractor/lbry.py @@ -3,9 +3,9 @@ import urllib.parse from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( ExtractorError, - HEADRequest, OnDemandPagedList, UnsupportedError, determine_ext, @@ -266,7 +266,7 @@ def _real_extract(self, url): # HEAD request returns redirect response to m3u8 URL if available final_url = self._request_webpage( HEADRequest(streaming_url), display_id, headers=headers, - note='Downloading streaming redirect url info').geturl() + note='Downloading streaming redirect url info').url elif result.get('value_type') == 'stream': claim_id, is_live = result['signing_channel']['claim_id'], True diff --git a/yt_dlp/extractor/lecturio.py b/yt_dlp/extractor/lecturio.py index 973764c63..bb059d3a2 100644 --- a/yt_dlp/extractor/lecturio.py +++ b/yt_dlp/extractor/lecturio.py @@ -25,7 +25,7 @@ def _perform_login(self, username, password): self._LOGIN_URL, None, 'Downloading login popup') def is_logged(url_handle): - return self._LOGIN_URL not in url_handle.geturl() + return self._LOGIN_URL not in url_handle.url # Already logged in if is_logged(urlh): diff --git a/yt_dlp/extractor/lego.py b/yt_dlp/extractor/lego.py index 811b44758..46fc7a9b6 100644 --- a/yt_dlp/extractor/lego.py +++ b/yt_dlp/extractor/lego.py @@ -1,7 +1,7 @@ import uuid from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -75,7 +75,7 @@ def _real_extract(self, url): 'videoId': '%s_%s' % (uuid.UUID(video_id), locale), }, headers=self.geo_verification_headers()) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451: + if isinstance(e.cause, HTTPError) and e.cause.status == 451: self.raise_geo_restricted(countries=countries) raise diff --git a/yt_dlp/extractor/limelight.py b/yt_dlp/extractor/limelight.py index e11ec43d6..4e50f106f 100644 --- a/yt_dlp/extractor/limelight.py +++ b/yt_dlp/extractor/limelight.py @@ -1,7 +1,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, float_or_none, @@ -69,8 +69,8 @@ def _call_playlist_service(self, item_id, method, fatal=True, referer=None): item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + error = self._parse_json(e.cause.response.read().decode(), item_id)['detail']['contentAccessPermission'] if error == 'CountryDisabled': self.raise_geo_restricted() raise ExtractorError(error, expected=True) diff --git a/yt_dlp/extractor/linuxacademy.py b/yt_dlp/extractor/linuxacademy.py index 7bb64e17c..0b1644293 100644 --- a/yt_dlp/extractor/linuxacademy.py +++ b/yt_dlp/extractor/linuxacademy.py @@ -2,11 +2,8 @@ import random from .common import InfoExtractor -from ..compat import ( - compat_b64decode, - compat_HTTPError, - compat_str, -) +from ..compat import compat_b64decode, compat_str +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, ExtractorError, @@ -107,7 +104,7 @@ def random_string(): 'sso': 'true', }) - login_state_url = urlh.geturl() + login_state_url = urlh.url try: login_page = self._download_webpage( @@ -119,8 +116,8 @@ def random_string(): 'Referer': login_state_url, }) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read(), None) + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read(), None) message = error.get('description') or error['code'] raise ExtractorError( '%s said: %s' % (self.IE_NAME, message), expected=True) @@ -137,7 +134,7 @@ def random_string(): }) access_token = self._search_regex( - r'access_token=([^=&]+)', urlh.geturl(), + r'access_token=([^=&]+)', urlh.url, 'access token', default=None) if not access_token: access_token = self._parse_json( diff --git a/yt_dlp/extractor/mediasite.py b/yt_dlp/extractor/mediasite.py index fe549c49f..7ea78ab69 100644 --- a/yt_dlp/extractor/mediasite.py +++ b/yt_dlp/extractor/mediasite.py @@ -171,7 +171,7 @@ def _real_extract(self, url): query = mobj.group('query') webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? - redirect_url = urlh.geturl() + redirect_url = urlh.url # XXX: might have also extracted UrlReferrer and QueryString from the html service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( diff --git a/yt_dlp/extractor/megatvcom.py b/yt_dlp/extractor/megatvcom.py index 2f3f11f51..93c7e7dc0 100644 --- a/yt_dlp/extractor/megatvcom.py +++ b/yt_dlp/extractor/megatvcom.py @@ -1,14 +1,14 @@ import re from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( + ExtractorError, clean_html, determine_ext, - ExtractorError, extract_attributes, get_element_by_class, get_element_html_by_id, - HEADRequest, parse_qs, unescapeHTML, unified_timestamp, @@ -160,5 +160,5 @@ def _real_extract(self, url): canonical_url = self._request_webpage( HEADRequest(canonical_url), video_id, note='Resolve canonical URL', - errnote='Could not resolve canonical URL').geturl() + errnote='Could not resolve canonical URL').url return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id) diff --git a/yt_dlp/extractor/mgtv.py b/yt_dlp/extractor/mgtv.py index 06edcb396..31ccf004e 100644 --- a/yt_dlp/extractor/mgtv.py +++ b/yt_dlp/extractor/mgtv.py @@ -1,9 +1,9 @@ import base64 import time -import urllib.error import uuid from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -86,8 +86,8 @@ def _real_extract(self, url): 'type': 'pch5' }, headers=self.geo_verification_headers())['data'] except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read().decode(), None) + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read().decode(), None) if error.get('code') == 40005: self.raise_geo_restricted(countries=self._GEO_COUNTRIES) raise ExtractorError(error['msg'], expected=True) diff --git a/yt_dlp/extractor/minds.py b/yt_dlp/extractor/minds.py index 2fb17920c..27a6e3805 100644 --- a/yt_dlp/extractor/minds.py +++ b/yt_dlp/extractor/minds.py @@ -106,7 +106,7 @@ def _real_extract(self, url): if poster: urlh = self._request_webpage(poster, video_id, fatal=False) if urlh: - thumbnail = urlh.geturl() + thumbnail = urlh.url return { 'id': video_id, diff --git a/yt_dlp/extractor/miomio.py b/yt_dlp/extractor/miomio.py index a0a041ea5..8df8cba19 100644 --- a/yt_dlp/extractor/miomio.py +++ b/yt_dlp/extractor/miomio.py @@ -2,12 +2,8 @@ from .common import InfoExtractor from ..compat import compat_urlparse -from ..utils import ( - xpath_text, - int_or_none, - ExtractorError, - sanitized_Request, -) +from ..networking import Request +from ..utils import ExtractorError, int_or_none, xpath_text class MioMioIE(InfoExtractor): @@ -61,7 +57,7 @@ def _extract_mioplayer(self, webpage, video_id, title, http_headers): 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), video_id) - vid_config_request = sanitized_Request( + vid_config_request = Request( 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), headers=http_headers) diff --git a/yt_dlp/extractor/mtv.py b/yt_dlp/extractor/mtv.py index d91be6270..0d700b9a8 100644 --- a/yt_dlp/extractor/mtv.py +++ b/yt_dlp/extractor/mtv.py @@ -2,16 +2,15 @@ from .common import InfoExtractor from ..compat import compat_str +from ..networking import HEADRequest, Request from ..utils import ( ExtractorError, + RegexNotFoundError, find_xpath_attr, fix_xml_ampersands, float_or_none, - HEADRequest, int_or_none, join_nonempty, - RegexNotFoundError, - sanitized_Request, strip_or_none, timeconvert, try_get, @@ -51,15 +50,15 @@ def _get_thumbnail_url(self, uri, itemdoc): def _extract_mobile_video_formats(self, mtvn_id): webpage_url = self._MOBILE_TEMPLATE % mtvn_id - req = sanitized_Request(webpage_url) + req = Request(webpage_url) # Otherwise we get a webpage that would execute some javascript - req.add_header('User-Agent', 'curl/7') + req.headers['User-Agent'] = 'curl/7' webpage = self._download_webpage(req, mtvn_id, 'Downloading mobile page') metrics_url = unescapeHTML(self._search_regex(r'(.+?)', webpage, 'error reason', default=None) @@ -742,7 +740,7 @@ def _real_extract(self, url): try: mylist = self._call_api(list_id, 'list', {'pageSize': 1}) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: self.raise_login_required('You have to be logged in to get your history') raise return self.playlist_result(self._entries(list_id), list_id, **self._parse_owner(mylist)) @@ -951,8 +949,8 @@ def _real_extract(self, url): 'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9', }) - hostname = remove_start(urlparse(urlh.geturl()).hostname, 'sp.') - cookies = try_get(urlh.geturl(), self._downloader._calc_cookies) + hostname = remove_start(urlparse(urlh.url).hostname, 'sp.') + cookies = try_get(urlh.url, self._downloader._calc_cookies) latency = try_get(self._configuration_arg('latency'), lambda x: x[0]) if latency not in self._KNOWN_LATENCY: latency = 'high' diff --git a/yt_dlp/extractor/njpwworld.py b/yt_dlp/extractor/njpwworld.py index 7b8a526f0..607838133 100644 --- a/yt_dlp/extractor/njpwworld.py +++ b/yt_dlp/extractor/njpwworld.py @@ -51,7 +51,7 @@ def _perform_login(self, username, password): data=urlencode_postdata({'login_id': username, 'pw': password}), headers={'Referer': 'https://front.njpwworld.com/auth'}) # /auth/login will return 302 for successful logins - if urlh.geturl() == self._LOGIN_URL: + if urlh.url == self._LOGIN_URL: self.report_warning('unable to login') return False diff --git a/yt_dlp/extractor/nosvideo.py b/yt_dlp/extractor/nosvideo.py index b6d3ea40c..7e9688c0b 100644 --- a/yt_dlp/extractor/nosvideo.py +++ b/yt_dlp/extractor/nosvideo.py @@ -1,9 +1,9 @@ import re from .common import InfoExtractor +from ..networking import Request from ..utils import ( ExtractorError, - sanitized_Request, urlencode_postdata, xpath_text, xpath_with_ns, @@ -36,8 +36,8 @@ def _real_extract(self, url): 'op': 'download1', 'method_free': 'Continue to Video', } - req = sanitized_Request(url, urlencode_postdata(fields)) - req.add_header('Content-type', 'application/x-www-form-urlencoded') + req = Request(url, urlencode_postdata(fields)) + req.headers['Content-type'] = 'application/x-www-form-urlencoded' webpage = self._download_webpage(req, video_id, 'Downloading download page') if re.search(self._FILE_DELETED_REGEX, webpage) is not None: diff --git a/yt_dlp/extractor/nowness.py b/yt_dlp/extractor/nowness.py index fc9043bce..a3c29f62c 100644 --- a/yt_dlp/extractor/nowness.py +++ b/yt_dlp/extractor/nowness.py @@ -4,10 +4,8 @@ ) from .common import InfoExtractor from ..compat import compat_str -from ..utils import ( - ExtractorError, - sanitized_Request, -) +from ..networking import Request +from ..utils import ExtractorError class NownessBaseIE(InfoExtractor): @@ -40,7 +38,7 @@ def _extract_url_result(self, post): def _api_request(self, url, request_path): display_id = self._match_id(url) - request = sanitized_Request( + request = Request( 'http://api.nowness.com/api/' + request_path % display_id, headers={ 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us', diff --git a/yt_dlp/extractor/nrk.py b/yt_dlp/extractor/nrk.py index 88d08e5e3..384865acc 100644 --- a/yt_dlp/extractor/nrk.py +++ b/yt_dlp/extractor/nrk.py @@ -3,7 +3,8 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError, compat_str +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, @@ -148,7 +149,7 @@ def call_playback_api(item, query=None): try: return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query) raise diff --git a/yt_dlp/extractor/odkmedia.py b/yt_dlp/extractor/odkmedia.py index 2960860d6..b852160b9 100644 --- a/yt_dlp/extractor/odkmedia.py +++ b/yt_dlp/extractor/odkmedia.py @@ -1,7 +1,7 @@ import json -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, GeoRestrictedError, @@ -74,8 +74,8 @@ def _real_extract(self, url): f'https://odkmedia.io/odc/api/v2/playback/{video_info["id"]}/', display_id, headers={'Authorization': '', 'service-name': 'odc'}) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError): - error_data = self._parse_json(e.cause.read(), display_id)['detail'] + if isinstance(e.cause, HTTPError): + error_data = self._parse_json(e.cause.response.read(), display_id)['detail'] raise GeoRestrictedError(error_data) formats, subtitles = [], {} diff --git a/yt_dlp/extractor/odnoklassniki.py b/yt_dlp/extractor/odnoklassniki.py index e63714e84..1be45d8ad 100644 --- a/yt_dlp/extractor/odnoklassniki.py +++ b/yt_dlp/extractor/odnoklassniki.py @@ -7,9 +7,9 @@ compat_urllib_parse_unquote, compat_urllib_parse_urlparse, ) +from ..networking import HEADRequest from ..utils import ( ExtractorError, - HEADRequest, float_or_none, int_or_none, qualities, @@ -448,7 +448,7 @@ def _extract_mobile(self, url): json_data = self._parse_json(unescapeHTML(json_data), video_id) or {} redirect_url = self._request_webpage(HEADRequest( - json_data['videoSrc']), video_id, 'Requesting download URL').geturl() + json_data['videoSrc']), video_id, 'Requesting download URL').url self._clear_cookies(redirect_url) return { diff --git a/yt_dlp/extractor/orf.py b/yt_dlp/extractor/orf.py index e9d23a4d1..cc3c003fa 100644 --- a/yt_dlp/extractor/orf.py +++ b/yt_dlp/extractor/orf.py @@ -2,11 +2,11 @@ import re from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( clean_html, determine_ext, float_or_none, - HEADRequest, InAdvancePagedList, int_or_none, join_nonempty, diff --git a/yt_dlp/extractor/owncloud.py b/yt_dlp/extractor/owncloud.py index e1d5682f8..79fd830bb 100644 --- a/yt_dlp/extractor/owncloud.py +++ b/yt_dlp/extractor/owncloud.py @@ -44,7 +44,7 @@ def _real_extract(self, url): webpage, urlh = self._download_webpage_handle(url, video_id) if re.search(r']+for="password"', webpage): - webpage = self._verify_video_password(webpage, urlh.geturl(), video_id) + webpage = self._verify_video_password(webpage, urlh.url, video_id) hidden_inputs = self._hidden_inputs(webpage) title = hidden_inputs.get('filename') diff --git a/yt_dlp/extractor/packtpub.py b/yt_dlp/extractor/packtpub.py index 51778d8a2..56203306f 100644 --- a/yt_dlp/extractor/packtpub.py +++ b/yt_dlp/extractor/packtpub.py @@ -1,10 +1,7 @@ import json from .common import InfoExtractor -from ..compat import ( - # compat_str, - compat_HTTPError, -) +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, ExtractorError, @@ -54,8 +51,8 @@ def _perform_login(self, username, password): 'password': password, }).encode())['data']['access'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 404): - message = self._parse_json(e.cause.read().decode(), None)['message'] + if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401, 404): + message = self._parse_json(e.cause.response.read().decode(), None)['message'] raise ExtractorError(message, expected=True) raise @@ -70,7 +67,7 @@ def _real_extract(self, url): 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id, 'Downloading JSON video', headers=headers)['data'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: self.raise_login_required('This video is locked') raise diff --git a/yt_dlp/extractor/patreon.py b/yt_dlp/extractor/patreon.py index e93e37eb9..447087436 100644 --- a/yt_dlp/extractor/patreon.py +++ b/yt_dlp/extractor/patreon.py @@ -1,10 +1,10 @@ import itertools -from urllib.error import HTTPError from .common import InfoExtractor from .vimeo import VimeoIE from ..compat import compat_urllib_parse_unquote +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, determine_ext, @@ -37,9 +37,9 @@ def _call_api(self, ep, item_id, query=None, headers=None, fatal=True, note=None item_id, note='Downloading API JSON' if not note else note, query=query, fatal=fatal, headers=headers) except ExtractorError as e: - if not isinstance(e.cause, HTTPError) or mimetype2ext(e.cause.headers.get('Content-Type')) != 'json': + if not isinstance(e.cause, HTTPError) or mimetype2ext(e.cause.response.headers.get('Content-Type')) != 'json': raise - err_json = self._parse_json(self._webpage_read_content(e.cause, None, item_id), item_id, fatal=False) + err_json = self._parse_json(self._webpage_read_content(e.cause.response, None, item_id), item_id, fatal=False) err_message = traverse_obj(err_json, ('errors', ..., 'detail'), get_all=False) if err_message: raise ExtractorError(f'Patreon said: {err_message}', expected=True) diff --git a/yt_dlp/extractor/peloton.py b/yt_dlp/extractor/peloton.py index 4835822cf..786429988 100644 --- a/yt_dlp/extractor/peloton.py +++ b/yt_dlp/extractor/peloton.py @@ -3,7 +3,7 @@ import urllib.parse from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, float_or_none, @@ -83,8 +83,8 @@ def _login(self, video_id): }).encode(), headers={'Content-Type': 'application/json', 'User-Agent': 'web'}) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - json_string = self._webpage_read_content(e.cause, None, video_id) + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + json_string = self._webpage_read_content(e.cause.response, None, video_id) res = self._parse_json(json_string, video_id) raise ExtractorError(res['message'], expected=res['message'] == 'Login failed') else: @@ -96,8 +96,8 @@ def _get_token(self, video_id): 'https://api.onepeloton.com/api/subscription/stream', video_id, note='Downloading token', data=json.dumps({}).encode(), headers={'Content-Type': 'application/json'}) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_string = self._webpage_read_content(e.cause, None, video_id) + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + json_string = self._webpage_read_content(e.cause.response, None, video_id) res = self._parse_json(json_string, video_id) raise ExtractorError(res['message'], expected=res['message'] == 'Stream limit reached') else: @@ -109,7 +109,7 @@ def _real_extract(self, url): try: self._start_session(video_id) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: self._login(video_id) self._start_session(video_id) else: diff --git a/yt_dlp/extractor/piapro.py b/yt_dlp/extractor/piapro.py index eb5923d11..5f39e0639 100644 --- a/yt_dlp/extractor/piapro.py +++ b/yt_dlp/extractor/piapro.py @@ -69,7 +69,7 @@ def _perform_login(self, username, password): if urlh is False: login_ok = False else: - parts = compat_urlparse.urlparse(urlh.geturl()) + parts = compat_urlparse.urlparse(urlh.url) if parts.path != '/': login_ok = False if not login_ok: diff --git a/yt_dlp/extractor/pladform.py b/yt_dlp/extractor/pladform.py index dcf18e1f3..00500686f 100644 --- a/yt_dlp/extractor/pladform.py +++ b/yt_dlp/extractor/pladform.py @@ -78,7 +78,7 @@ def fail(text): expected=True) if not video: - targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').geturl() + targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').url if targetUrl == url: raise ExtractorError('Can\'t parse page') return self.url_result(targetUrl) diff --git a/yt_dlp/extractor/platzi.py b/yt_dlp/extractor/platzi.py index b8a441494..166b98c4a 100644 --- a/yt_dlp/extractor/platzi.py +++ b/yt_dlp/extractor/platzi.py @@ -36,7 +36,7 @@ def _perform_login(self, username, password): headers={'Referer': self._LOGIN_URL}) # login succeeded - if 'platzi.com/login' not in urlh.geturl(): + if 'platzi.com/login' not in urlh.url: return login_error = self._webpage_read_content( diff --git a/yt_dlp/extractor/playplustv.py b/yt_dlp/extractor/playplustv.py index 316f220f7..a4439c8bc 100644 --- a/yt_dlp/extractor/playplustv.py +++ b/yt_dlp/extractor/playplustv.py @@ -1,13 +1,9 @@ import json from .common import InfoExtractor -from ..compat import compat_HTTPError -from ..utils import ( - clean_html, - ExtractorError, - int_or_none, - PUTRequest, -) +from ..networking import PUTRequest +from ..networking.exceptions import HTTPError +from ..utils import ExtractorError, clean_html, int_or_none class PlayPlusTVIE(InfoExtractor): @@ -47,9 +43,9 @@ def _perform_login(self, username, password): try: self._token = self._download_json(req, None)['token'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: raise ExtractorError(self._parse_json( - e.cause.read(), None)['errorMessage'], expected=True) + e.cause.response.read(), None)['errorMessage'], expected=True) raise self._profile = self._call_api('Profiles')['list'][0]['_id'] diff --git a/yt_dlp/extractor/pornhub.py b/yt_dlp/extractor/pornhub.py index 2f5a572a5..f08414030 100644 --- a/yt_dlp/extractor/pornhub.py +++ b/yt_dlp/extractor/pornhub.py @@ -3,11 +3,12 @@ import math import operator import re -import urllib.request from .common import InfoExtractor from .openload import PhantomJSwrapper -from ..compat import compat_HTTPError, compat_str +from ..compat import compat_str +from ..networking import Request +from ..networking.exceptions import HTTPError from ..utils import ( NO_DEFAULT, ExtractorError, @@ -46,8 +47,8 @@ def dl(*args, **kwargs): r'document\.cookie\s*=\s*["\']RNKEY=', r'document\.location\.reload\(true\)')): url_or_request = args[0] - url = (url_or_request.get_full_url() - if isinstance(url_or_request, urllib.request.Request) + url = (url_or_request.url + if isinstance(url_or_request, Request) else url_or_request) phantom = PhantomJSwrapper(self, required_version='2.0') phantom.get(url, html=webpage) @@ -602,7 +603,7 @@ def download_page(base_url, num, fallback=False): base_url, item_id, note, query={'page': num}) def is_404(e): - return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404 + return isinstance(e.cause, HTTPError) and e.cause.status == 404 base_url = url has_page = page is not None diff --git a/yt_dlp/extractor/puhutv.py b/yt_dlp/extractor/puhutv.py index 482e5705f..4b8e5e90d 100644 --- a/yt_dlp/extractor/puhutv.py +++ b/yt_dlp/extractor/puhutv.py @@ -1,8 +1,6 @@ from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -72,7 +70,7 @@ def _real_extract(self, url): display_id, 'Downloading video JSON', headers=self.geo_verification_headers()) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: self.raise_geo_restricted() raise diff --git a/yt_dlp/extractor/radiko.py b/yt_dlp/extractor/radiko.py index 7fdf78283..cef68eba0 100644 --- a/yt_dlp/extractor/radiko.py +++ b/yt_dlp/extractor/radiko.py @@ -41,7 +41,7 @@ def _auth_client(self): 'x-radiko-device': 'pc', 'x-radiko-user': 'dummy_user', }) - auth1_header = auth1_handle.info() + auth1_header = auth1_handle.headers auth_token = auth1_header['X-Radiko-AuthToken'] kl = int(auth1_header['X-Radiko-KeyLength']) diff --git a/yt_dlp/extractor/radiocanada.py b/yt_dlp/extractor/radiocanada.py index 72c21d502..1a5a6355a 100644 --- a/yt_dlp/extractor/radiocanada.py +++ b/yt_dlp/extractor/radiocanada.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -74,8 +74,8 @@ def _call_api(self, path, video_id=None, app_code=None, query=None): return self._download_json( 'https://services.radio-canada.ca/media/' + path, video_id, query=query) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422): - data = self._parse_json(e.cause.read().decode(), None) + if isinstance(e.cause, HTTPError) and e.cause.status in (401, 422): + data = self._parse_json(e.cause.response.read().decode(), None) error = data.get('error_description') or data['errorMessage']['text'] raise ExtractorError(error, expected=True) raise diff --git a/yt_dlp/extractor/rcs.py b/yt_dlp/extractor/rcs.py index 2440858ca..028d3d90b 100644 --- a/yt_dlp/extractor/rcs.py +++ b/yt_dlp/extractor/rcs.py @@ -1,9 +1,9 @@ import re from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( ExtractorError, - HEADRequest, base_url, clean_html, extract_attributes, diff --git a/yt_dlp/extractor/rcti.py b/yt_dlp/extractor/rcti.py index 27b4ad7bb..79d9c8e31 100644 --- a/yt_dlp/extractor/rcti.py +++ b/yt_dlp/extractor/rcti.py @@ -3,7 +3,7 @@ import time from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( dict_get, ExtractorError, @@ -186,7 +186,7 @@ def _real_extract(self, url): try: formats = self._extract_m3u8_formats(video_url, display_id, 'mp4', headers={'Referer': 'https://www.rctiplus.com/'}) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: self.raise_geo_restricted(countries=['ID'], metadata_available=True) else: raise e diff --git a/yt_dlp/extractor/recurbate.py b/yt_dlp/extractor/recurbate.py index 5534cf3c3..d7294cb14 100644 --- a/yt_dlp/extractor/recurbate.py +++ b/yt_dlp/extractor/recurbate.py @@ -1,6 +1,5 @@ -import urllib.error - from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ExtractorError, merge_dicts @@ -25,7 +24,7 @@ def _real_extract(self, url): try: webpage = self._download_webpage(url, video_id) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: self.raise_login_required(msg=SUBSCRIPTION_MISSING_MESSAGE, method='cookies') raise token = self._html_search_regex(r'data-token="([^"]+)"', webpage, 'token') diff --git a/yt_dlp/extractor/redbulltv.py b/yt_dlp/extractor/redbulltv.py index a01bc8434..d1de2490f 100644 --- a/yt_dlp/extractor/redbulltv.py +++ b/yt_dlp/extractor/redbulltv.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( float_or_none, ExtractorError, @@ -68,9 +68,9 @@ def extract_info(self, video_id): headers={'Authorization': token} ) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + if isinstance(e.cause, HTTPError) and e.cause.status == 404: error_message = self._parse_json( - e.cause.read().decode(), video_id)['error'] + e.cause.response.read().decode(), video_id)['error'] raise ExtractorError('%s said: %s' % ( self.IE_NAME, error_message), expected=True) raise diff --git a/yt_dlp/extractor/redgifs.py b/yt_dlp/extractor/redgifs.py index 098fb8185..f9453202b 100644 --- a/yt_dlp/extractor/redgifs.py +++ b/yt_dlp/extractor/redgifs.py @@ -1,8 +1,8 @@ import functools -import urllib from .common import InfoExtractor from ..compat import compat_parse_qs +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -82,7 +82,7 @@ def _call_api(self, ep, video_id, *args, **kwargs): f'https://api.redgifs.com/v2/{ep}', video_id, headers=headers, *args, **kwargs) break except ExtractorError as e: - if first_attempt and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: + if first_attempt and isinstance(e.cause, HTTPError) and e.cause.status == 401: del self._API_HEADERS['authorization'] # refresh the token continue raise diff --git a/yt_dlp/extractor/regiotv.py b/yt_dlp/extractor/regiotv.py index 6114841fb..edb6ae5bc 100644 --- a/yt_dlp/extractor/regiotv.py +++ b/yt_dlp/extractor/regiotv.py @@ -1,10 +1,6 @@ from .common import InfoExtractor - -from ..utils import ( - sanitized_Request, - xpath_text, - xpath_with_ns, -) +from ..networking import Request +from ..utils import xpath_text, xpath_with_ns class RegioTVIE(InfoExtractor): @@ -33,7 +29,7 @@ def _real_extract(self, url): SOAP_TEMPLATE = '<{0} xmlns="http://v.telvi.de/">{1}' - request = sanitized_Request( + request = Request( 'http://v.telvi.de/', SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8')) video_data = self._download_xml(request, video_id, 'Downloading video XML') diff --git a/yt_dlp/extractor/rokfin.py b/yt_dlp/extractor/rokfin.py index 0e40eb32a..4a4d40bef 100644 --- a/yt_dlp/extractor/rokfin.py +++ b/yt_dlp/extractor/rokfin.py @@ -245,7 +245,7 @@ def _perform_login(self, username, password): f'{self._AUTH_BASE}/token', None, note='getting access credentials', errnote='error getting access credentials', data=urlencode_postdata({ - 'code': urllib.parse.parse_qs(urllib.parse.urldefrag(urlh.geturl()).fragment).get('code')[0], + 'code': urllib.parse.parse_qs(urllib.parse.urldefrag(urlh.url).fragment).get('code')[0], 'client_id': 'web', 'grant_type': 'authorization_code', 'redirect_uri': 'https://rokfin.com/silent-check-sso.html' @@ -269,7 +269,7 @@ def _download_json_using_access_token(self, url_or_request, video_id, headers={} json_string, urlh = self._download_webpage_handle( url_or_request, video_id, headers=headers, query=query, expected_status=401) - if not auth_token or urlh.code != 401 or refresh_token is None: + if not auth_token or urlh.status != 401 or refresh_token is None: return self._parse_json(json_string, video_id) self._access_mgmt_tokens = self._download_json( diff --git a/yt_dlp/extractor/roosterteeth.py b/yt_dlp/extractor/roosterteeth.py index 776fbfbc0..94e673b13 100644 --- a/yt_dlp/extractor/roosterteeth.py +++ b/yt_dlp/extractor/roosterteeth.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -35,8 +35,8 @@ def _perform_login(self, username, password): })) except ExtractorError as e: msg = 'Unable to login' - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - resp = self._parse_json(e.cause.read().decode(), None, fatal=False) + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + resp = self._parse_json(e.cause.response.read().decode(), None, fatal=False) if resp: error = resp.get('extra_info') or resp.get('error_description') or resp.get('error') if error: @@ -138,8 +138,8 @@ def _real_extract(self, url): m3u8_url = video_data['attributes']['url'] # XXX: additional URL at video_data['links']['download'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - if self._parse_json(e.cause.read().decode(), display_id).get('access') is False: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + if self._parse_json(e.cause.response.read().decode(), display_id).get('access') is False: self.raise_login_required( '%s is only available for FIRST members' % display_id) raise diff --git a/yt_dlp/extractor/rozhlas.py b/yt_dlp/extractor/rozhlas.py index 5f83d42e8..63134322d 100644 --- a/yt_dlp/extractor/rozhlas.py +++ b/yt_dlp/extractor/rozhlas.py @@ -1,7 +1,7 @@ import itertools -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, extract_attributes, @@ -81,7 +81,7 @@ def _extract_formats(self, entry, audio_id): 'vcodec': 'none', }) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 429: + if isinstance(e.cause, HTTPError) and e.cause.status == 429: retry.error = e.cause else: self.report_warning(e.msg) diff --git a/yt_dlp/extractor/rte.py b/yt_dlp/extractor/rte.py index aedaa5b55..7ba80d4ba 100644 --- a/yt_dlp/extractor/rte.py +++ b/yt_dlp/extractor/rte.py @@ -1,7 +1,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( float_or_none, parse_iso8601, @@ -31,8 +31,8 @@ def _real_extract(self, url): except ExtractorError as ee: if num < len(ENDPOINTS) or formats: continue - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: - error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False) + if isinstance(ee.cause, HTTPError) and ee.cause.status == 404: + error_info = self._parse_json(ee.cause.response.read().decode(), item_id, fatal=False) if error_info: raise ExtractorError( '%s said: %s' % (self.IE_NAME, error_info['message']), diff --git a/yt_dlp/extractor/rts.py b/yt_dlp/extractor/rts.py index 81c4d7cac..9f73d1811 100644 --- a/yt_dlp/extractor/rts.py +++ b/yt_dlp/extractor/rts.py @@ -136,8 +136,8 @@ def download_json(internal_id): if not entries: page, urlh = self._download_webpage_handle(url, display_id) - if re.match(self._VALID_URL, urlh.geturl()).group('id') != media_id: - return self.url_result(urlh.geturl(), 'RTS') + if re.match(self._VALID_URL, urlh.url).group('id') != media_id: + return self.url_result(urlh.url, 'RTS') # article with videos on rhs videos = re.findall( diff --git a/yt_dlp/extractor/rumble.py b/yt_dlp/extractor/rumble.py index 82f3f0f8c..f8bf4a182 100644 --- a/yt_dlp/extractor/rumble.py +++ b/yt_dlp/extractor/rumble.py @@ -2,7 +2,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, UnsupportedError, @@ -371,7 +371,7 @@ def entries(self, url, playlist_id): try: webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + if isinstance(e.cause, HTTPError) and e.cause.status == 404: break raise for video_url in re.findall(r'class=video-item--a\s?href=([^>]+\.html)', webpage): diff --git a/yt_dlp/extractor/safari.py b/yt_dlp/extractor/safari.py index 450a661e9..8d322d710 100644 --- a/yt_dlp/extractor/safari.py +++ b/yt_dlp/extractor/safari.py @@ -28,13 +28,13 @@ def _perform_login(self, username, password): 'Downloading login page') def is_logged(urlh): - return 'learning.oreilly.com/home/' in urlh.geturl() + return 'learning.oreilly.com/home/' in urlh.url if is_logged(urlh): self.LOGGED_IN = True return - redirect_url = urlh.geturl() + redirect_url = urlh.url parsed_url = compat_urlparse.urlparse(redirect_url) qs = compat_parse_qs(parsed_url.query) next_uri = compat_urlparse.urljoin( @@ -129,7 +129,7 @@ def _real_extract(self, url): webpage, urlh = self._download_webpage_handle(url, video_id) - mobj = re.match(self._VALID_URL, urlh.geturl()) + mobj = re.match(self._VALID_URL, urlh.url) reference_id = mobj.group('reference_id') if not reference_id: reference_id = self._search_regex( diff --git a/yt_dlp/extractor/sbs.py b/yt_dlp/extractor/sbs.py index 119106e8e..7a9115047 100644 --- a/yt_dlp/extractor/sbs.py +++ b/yt_dlp/extractor/sbs.py @@ -1,6 +1,6 @@ from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( - HEADRequest, float_or_none, int_or_none, parse_duration, diff --git a/yt_dlp/extractor/sevenplus.py b/yt_dlp/extractor/sevenplus.py index 222bf6ce7..6c688d150 100644 --- a/yt_dlp/extractor/sevenplus.py +++ b/yt_dlp/extractor/sevenplus.py @@ -2,10 +2,8 @@ import re from .brightcove import BrightcoveNewBaseIE -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, try_get, @@ -97,9 +95,9 @@ def _real_extract(self, url): 'videoType': 'vod', }, headers=headers)['media'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: raise ExtractorError(self._parse_json( - e.cause.read().decode(), episode_id)[0]['error_code'], expected=True) + e.cause.response.read().decode(), episode_id)[0]['error_code'], expected=True) raise for source in media.get('sources', {}): diff --git a/yt_dlp/extractor/shahid.py b/yt_dlp/extractor/shahid.py index 26a0bff40..d509e8879 100644 --- a/yt_dlp/extractor/shahid.py +++ b/yt_dlp/extractor/shahid.py @@ -3,7 +3,7 @@ import re from .aws import AWSIE -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, ExtractorError, @@ -22,7 +22,7 @@ class ShahidBaseIE(AWSIE): def _handle_error(self, e): fail_data = self._parse_json( - e.cause.read().decode('utf-8'), None, fatal=False) + e.cause.response.read().decode('utf-8'), None, fatal=False) if fail_data: faults = fail_data.get('faults', []) faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')]) @@ -40,7 +40,7 @@ def _call_api(self, path, video_id, request=None): 'secret_key': '4WUUJWuFvtTkXbhaWTDv7MhO+0LqoYDWfEnUXoWn', }, video_id, query) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): + if isinstance(e.cause, HTTPError): self._handle_error(e) raise @@ -88,7 +88,7 @@ def _perform_login(self, username, password): 'Content-Type': 'application/json; charset=UTF-8', })['user'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): + if isinstance(e.cause, HTTPError): self._handle_error(e) raise diff --git a/yt_dlp/extractor/sina.py b/yt_dlp/extractor/sina.py index aeba4e377..984281188 100644 --- a/yt_dlp/extractor/sina.py +++ b/yt_dlp/extractor/sina.py @@ -1,12 +1,12 @@ from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( - HEADRequest, ExtractorError, - int_or_none, - update_url_query, - qualities, - get_element_by_attribute, clean_html, + get_element_by_attribute, + int_or_none, + qualities, + update_url_query, ) @@ -60,7 +60,7 @@ def _real_extract(self, url): self.to_screen('Getting video id') request = HEADRequest(url) _, urlh = self._download_webpage_handle(request, 'NA', False) - return self._real_extract(urlh.geturl()) + return self._real_extract(urlh.url) else: pseudo_id = mobj.group('pseudo_id') webpage = self._download_webpage(url, pseudo_id) diff --git a/yt_dlp/extractor/sixplay.py b/yt_dlp/extractor/sixplay.py index a6fb6c1f5..ef93b9276 100644 --- a/yt_dlp/extractor/sixplay.py +++ b/yt_dlp/extractor/sixplay.py @@ -79,7 +79,7 @@ def _real_extract(self, url): headers=self.geo_verification_headers()) if not urlh: continue - asset_url = urlh.geturl() + asset_url = urlh.url asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/') for i in range(3, 0, -1): asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i) diff --git a/yt_dlp/extractor/slideslive.py b/yt_dlp/extractor/slideslive.py index 3d36edbbc..25f867a60 100644 --- a/yt_dlp/extractor/slideslive.py +++ b/yt_dlp/extractor/slideslive.py @@ -426,7 +426,7 @@ def _real_extract(self, url): video_id, headers=traverse_obj(parse_qs(url), { 'Referer': ('embed_parent_url', -1), 'Origin': ('embed_container_origin', -1)})) - redirect_url = urlh.geturl() + redirect_url = urlh.url if 'domain_not_allowed' in redirect_url: domain = traverse_obj(parse_qs(redirect_url), ('allowed_domains[]', ...), get_all=False) if not domain: diff --git a/yt_dlp/extractor/sonyliv.py b/yt_dlp/extractor/sonyliv.py index 5ebe20df7..437957259 100644 --- a/yt_dlp/extractor/sonyliv.py +++ b/yt_dlp/extractor/sonyliv.py @@ -6,7 +6,7 @@ import uuid from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -123,12 +123,12 @@ def _call_api(self, version, path, video_id): 'https://apiv2.sonyliv.com/AGL/%s/A/ENG/WEB/%s' % (version, path), video_id, headers=self._HEADERS)['resultObj'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 406 and self._parse_json( - e.cause.read().decode(), video_id)['message'] == 'Please subscribe to watch this content': + if isinstance(e.cause, HTTPError) and e.cause.status == 406 and self._parse_json( + e.cause.response.read().decode(), video_id)['message'] == 'Please subscribe to watch this content': self.raise_login_required(self._LOGIN_HINT, method=None) - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: message = self._parse_json( - e.cause.read().decode(), video_id)['message'] + e.cause.response.read().decode(), video_id)['message'] if message == 'Geoblocked Country': self.raise_geo_restricted(countries=self._GEO_COUNTRIES) raise ExtractorError(message) diff --git a/yt_dlp/extractor/soundcloud.py b/yt_dlp/extractor/soundcloud.py index 979f23f44..a7c2afd49 100644 --- a/yt_dlp/extractor/soundcloud.py +++ b/yt_dlp/extractor/soundcloud.py @@ -7,15 +7,13 @@ InfoExtractor, SearchInfoExtractor ) -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_str +from ..networking import HEADRequest, Request +from ..networking.exceptions import HTTPError from ..utils import ( error_to_compat_str, ExtractorError, float_or_none, - HEADRequest, int_or_none, KNOWN_EXTENSIONS, mimetype2ext, @@ -26,7 +24,6 @@ update_url_query, url_or_none, urlhandle_detect_ext, - sanitized_Request, ) @@ -103,7 +100,7 @@ def _download_json(self, *args, **kwargs): try: return super()._download_json(*args, **kwargs) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): + if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403): self._store_client_id(None) self._update_client_id() continue @@ -123,7 +120,7 @@ def _perform_login(self, username, password): self._access_token = password query = self._API_AUTH_QUERY_TEMPLATE % self._CLIENT_ID payload = {'session': {'access_token': self._access_token}} - token_verification = sanitized_Request(self._API_VERIFY_AUTH_TOKEN % query, json.dumps(payload).encode('utf-8')) + token_verification = Request(self._API_VERIFY_AUTH_TOKEN % query, json.dumps(payload).encode('utf-8')) response = self._download_json(token_verification, None, note='Verifying login token...', fatal=False) if response is not False: self._HEADERS = {'Authorization': 'OAuth ' + self._access_token} @@ -212,7 +209,7 @@ def _extract_info_dict(self, info, full_title=None, secret_token=None, extract_f urlh = self._request_webpage( HEADRequest(redirect_url), track_id, fatal=False) if urlh: - format_url = urlh.geturl() + format_url = urlh.url format_urls.add(format_url) formats.append({ 'format_id': 'download', @@ -669,7 +666,7 @@ def _entries(self, url, playlist_id): except ExtractorError as e: # Downloading page may result in intermittent 502 HTTP error # See https://github.com/yt-dlp/yt-dlp/issues/872 - if not isinstance(e.cause, compat_HTTPError) or e.cause.code != 502: + if not isinstance(e.cause, HTTPError) or e.cause.status != 502: raise retry.error = e continue diff --git a/yt_dlp/extractor/teachable.py b/yt_dlp/extractor/teachable.py index c212a4926..01906bda9 100644 --- a/yt_dlp/extractor/teachable.py +++ b/yt_dlp/extractor/teachable.py @@ -56,7 +56,7 @@ def is_logged(webpage): self._logged_in = True return - login_url = urlh.geturl() + login_url = urlh.url login_form = self._hidden_inputs(login_page) diff --git a/yt_dlp/extractor/telemundo.py b/yt_dlp/extractor/telemundo.py index 88f29cb83..54e74a6c0 100644 --- a/yt_dlp/extractor/telemundo.py +++ b/yt_dlp/extractor/telemundo.py @@ -1,9 +1,6 @@ from .common import InfoExtractor -from ..utils import ( - try_get, - unified_timestamp, - HEADRequest, -) +from ..networking import HEADRequest +from ..utils import try_get, unified_timestamp class TelemundoIE(InfoExtractor): @@ -38,7 +35,7 @@ def _real_extract(self, url): m3u8_url = self._request_webpage(HEADRequest( redirect_url + '?format=redirect&manifest=m3u&format=redirect&Tracking=true&Embedded=true&formats=MPEG4'), - video_id, 'Processing m3u8').geturl() + video_id, 'Processing m3u8').url formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') date = unified_timestamp(try_get( metadata, lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['datePublished'].split(' ', 1)[1])) diff --git a/yt_dlp/extractor/tennistv.py b/yt_dlp/extractor/tennistv.py index bc64226bf..c1b4a3312 100644 --- a/yt_dlp/extractor/tennistv.py +++ b/yt_dlp/extractor/tennistv.py @@ -86,7 +86,7 @@ def _perform_login(self, username, password): }) self.get_token(None, { - 'code': urllib.parse.parse_qs(handle.geturl())['code'][-1], + 'code': urllib.parse.parse_qs(handle.url)['code'][-1], 'grant_type': 'authorization_code', 'client_id': 'tennis-tv-web', 'redirect_uri': 'https://www.tennistv.com/resources/v1.1.10/html/silent-check-sso.html' diff --git a/yt_dlp/extractor/tenplay.py b/yt_dlp/extractor/tenplay.py index 633032e31..c7097cf02 100644 --- a/yt_dlp/extractor/tenplay.py +++ b/yt_dlp/extractor/tenplay.py @@ -2,11 +2,8 @@ import base64 from .common import InfoExtractor -from ..utils import ( - HEADRequest, - int_or_none, - urlencode_postdata, -) +from ..networking import HEADRequest +from ..utils import int_or_none, urlencode_postdata class TenPlayIE(InfoExtractor): @@ -94,7 +91,7 @@ def _real_extract(self, url): data.get('playbackApiEndpoint'), content_id, 'Downloading video JSON', headers=headers).get('source') m3u8_url = self._request_webpage(HEADRequest( - _video_url), content_id).geturl() + _video_url), content_id).url if '10play-not-in-oz' in m3u8_url: self.raise_geo_restricted(countries=['AU']) formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4') diff --git a/yt_dlp/extractor/tfo.py b/yt_dlp/extractor/tfo.py index a24789cb3..d417f50e1 100644 --- a/yt_dlp/extractor/tfo.py +++ b/yt_dlp/extractor/tfo.py @@ -1,12 +1,8 @@ import json from .common import InfoExtractor -from ..utils import ( - HEADRequest, - ExtractorError, - int_or_none, - clean_html, -) +from ..networking import HEADRequest +from ..utils import ExtractorError, clean_html, int_or_none class TFOIE(InfoExtractor): diff --git a/yt_dlp/extractor/theplatform.py b/yt_dlp/extractor/theplatform.py index e659b8ee1..537f6f6cd 100644 --- a/yt_dlp/extractor/theplatform.py +++ b/yt_dlp/extractor/theplatform.py @@ -7,13 +7,13 @@ from .once import OnceIE from .adobepass import AdobePassIE +from ..networking import Request from ..utils import ( determine_ext, ExtractorError, float_or_none, int_or_none, parse_qs, - sanitized_Request, unsmuggle_url, update_url_query, xpath_with_ns, @@ -270,7 +270,7 @@ def _real_extract(self, url): source_url = smuggled_data.get('source_url') if source_url: headers['Referer'] = source_url - request = sanitized_Request(url, headers=headers) + request = Request(url, headers=headers) webpage = self._download_webpage(request, video_id) smil_url = self._search_regex( r']+href=(["\'])(?P.+?)\1[^>]+type=["\']application/smil\+xml', diff --git a/yt_dlp/extractor/thisoldhouse.py b/yt_dlp/extractor/thisoldhouse.py index 55b6413ae..cc7beeea5 100644 --- a/yt_dlp/extractor/thisoldhouse.py +++ b/yt_dlp/extractor/thisoldhouse.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..utils import HEADRequest +from ..networking import HEADRequest class ThisOldHouseIE(InfoExtractor): @@ -50,6 +50,6 @@ def _real_extract(self, url): r']+src=[\'"]((?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})[^\'"]*)[\'"]', webpage, 'video url') if 'subscription_required=true' in video_url or 'c-entry-group-labels__image' in webpage: - return self.url_result(self._request_webpage(HEADRequest(video_url), display_id).geturl(), 'Zype', display_id) + return self.url_result(self._request_webpage(HEADRequest(video_url), display_id).url, 'Zype', display_id) video_id = self._search_regex(r'(?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})', video_url, 'video id') return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id) diff --git a/yt_dlp/extractor/threeqsdn.py b/yt_dlp/extractor/threeqsdn.py index b1041902b..7841f8da6 100644 --- a/yt_dlp/extractor/threeqsdn.py +++ b/yt_dlp/extractor/threeqsdn.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -90,7 +90,7 @@ def _real_extract(self, url): config = self._download_json( url.replace('://playout.3qsdn.com/', '://playout.3qsdn.com/config/'), video_id) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: self.raise_geo_restricted() raise diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py index 2f491c317..48de61f93 100644 --- a/yt_dlp/extractor/tiktok.py +++ b/yt_dlp/extractor/tiktok.py @@ -7,9 +7,9 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_unquote, compat_urllib_parse_urlparse +from ..networking import HEADRequest from ..utils import ( ExtractorError, - HEADRequest, LazyList, UnsupportedError, UserNotLive, @@ -1084,7 +1084,7 @@ class TikTokVMIE(InfoExtractor): def _real_extract(self, url): new_url = self._request_webpage( - HEADRequest(url), self._match_id(url), headers={'User-Agent': 'facebookexternalhit/1.1'}).geturl() + HEADRequest(url), self._match_id(url), headers={'User-Agent': 'facebookexternalhit/1.1'}).url if self.suitable(new_url): # Prevent infinite loop in case redirect fails raise UnsupportedError(new_url) return self.url_result(new_url) diff --git a/yt_dlp/extractor/toutv.py b/yt_dlp/extractor/toutv.py index f60c199f0..ced1224fa 100644 --- a/yt_dlp/extractor/toutv.py +++ b/yt_dlp/extractor/toutv.py @@ -1,7 +1,7 @@ import json from .radiocanada import RadioCanadaIE -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -52,8 +52,8 @@ def _perform_login(self, username, password): 'Content-Type': 'application/json;charset=utf-8', })['access_token'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read().decode(), None)['Message'] + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read().decode(), None)['Message'] raise ExtractorError(error, expected=True) raise self._claims = self._call_api('validation/v2/getClaims')['claims'] diff --git a/yt_dlp/extractor/triller.py b/yt_dlp/extractor/triller.py index 6a4dadb9b..c5d01c827 100644 --- a/yt_dlp/extractor/triller.py +++ b/yt_dlp/extractor/triller.py @@ -3,9 +3,9 @@ import re from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( ExtractorError, - HEADRequest, UnsupportedError, determine_ext, int_or_none, @@ -327,7 +327,7 @@ class TrillerShortIE(InfoExtractor): }] def _real_extract(self, url): - real_url = self._request_webpage(HEADRequest(url), self._match_id(url)).geturl() + real_url = self._request_webpage(HEADRequest(url), self._match_id(url)).url if self.suitable(real_url): # Prevent infinite loop in case redirect fails raise UnsupportedError(real_url) return self.url_result(real_url) diff --git a/yt_dlp/extractor/trueid.py b/yt_dlp/extractor/trueid.py index 696343627..86f0990e8 100644 --- a/yt_dlp/extractor/trueid.py +++ b/yt_dlp/extractor/trueid.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -88,9 +88,9 @@ def _real_extract(self, url): stream_data = self._download_json( f'https://{domain}/cmsPostProxy/contents/video/{video_id}/streamer?os=android', video_id, data=b'')['data'] except ExtractorError as e: - if not isinstance(e.cause, compat_HTTPError): + if not isinstance(e.cause, HTTPError): raise e - errmsg = self._parse_json(e.cause.read().decode(), video_id)['meta']['message'] + errmsg = self._parse_json(e.cause.response.read().decode(), video_id)['meta']['message'] if 'country' in errmsg: self.raise_geo_restricted( errmsg, [initial_data['display_country']] if initial_data.get('display_country') else None, True) diff --git a/yt_dlp/extractor/tubetugraz.py b/yt_dlp/extractor/tubetugraz.py index 2199fea19..a351e4e55 100644 --- a/yt_dlp/extractor/tubetugraz.py +++ b/yt_dlp/extractor/tubetugraz.py @@ -22,7 +22,7 @@ def _perform_login(self, username, password): return content, urlh = self._download_webpage_handle( - urlh.geturl(), None, fatal=False, headers={'referer': urlh.geturl()}, + urlh.url, None, fatal=False, headers={'referer': urlh.url}, note='logging in', errnote='unable to log in', data=urlencode_postdata({ 'lang': 'de', @@ -30,7 +30,7 @@ def _perform_login(self, username, password): 'j_username': username, 'j_password': password })) - if not urlh or urlh.geturl() == 'https://tube.tugraz.at/paella/ui/index.html': + if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html': return if not self._html_search_regex( @@ -40,14 +40,14 @@ def _perform_login(self, username, password): return content, urlh = self._download_webpage_handle( - urlh.geturl(), None, fatal=False, headers={'referer': urlh.geturl()}, + urlh.url, None, fatal=False, headers={'referer': urlh.url}, note='logging in with TFA', errnote='unable to log in with TFA', data=urlencode_postdata({ 'lang': 'de', '_eventId_proceed': '', 'j_tokenNumber': self._get_tfa_info(), })) - if not urlh or urlh.geturl() == 'https://tube.tugraz.at/paella/ui/index.html': + if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html': return self.report_warning('unable to login: incorrect TFA code') diff --git a/yt_dlp/extractor/tubitv.py b/yt_dlp/extractor/tubitv.py index de8b5da69..bd46bc363 100644 --- a/yt_dlp/extractor/tubitv.py +++ b/yt_dlp/extractor/tubitv.py @@ -1,13 +1,13 @@ import re from .common import InfoExtractor +from ..networking import Request from ..utils import ( ExtractorError, int_or_none, js_to_json, - sanitized_Request, - urlencode_postdata, traverse_obj, + urlencode_postdata, ) @@ -72,8 +72,8 @@ def _perform_login(self, username, password): 'password': password, } payload = urlencode_postdata(form_data) - request = sanitized_Request(self._LOGIN_URL, payload) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request = Request(self._LOGIN_URL, payload) + request.headers['Content-Type'] = 'application/x-www-form-urlencoded' login_page = self._download_webpage( request, None, False, 'Wrong login info') if not re.search(r'id="tubi-logout"', login_page): diff --git a/yt_dlp/extractor/tumblr.py b/yt_dlp/extractor/tumblr.py index 88d4ae32d..a26bdcaae 100644 --- a/yt_dlp/extractor/tumblr.py +++ b/yt_dlp/extractor/tumblr.py @@ -274,7 +274,7 @@ def _real_extract(self, url): url = f'http://{blog}.tumblr.com/post/{video_id}/' webpage, urlh = self._download_webpage_handle(url, video_id) - redirect_url = urlh.geturl() + redirect_url = urlh.url api_only = bool(self._search_regex( r'(tumblr.com|^)/(safe-mode|login_required|blog/view)', diff --git a/yt_dlp/extractor/tunein.py b/yt_dlp/extractor/tunein.py index e02121bd8..fd2fe132c 100644 --- a/yt_dlp/extractor/tunein.py +++ b/yt_dlp/extractor/tunein.py @@ -225,10 +225,10 @@ def _real_extract(self, url): urlh = self._request_webpage( url, redirect_id, note='Downloading redirect page') - url = urlh.geturl() + url = urlh.url url_parsed = urllib.parse.urlparse(url) if url_parsed.port == 443: - url = url_parsed._replace(netloc=url_parsed.hostname).geturl() + url = url_parsed._replace(netloc=url_parsed.hostname).url self.to_screen('Following redirect: %s' % url) return self.url_result(url) diff --git a/yt_dlp/extractor/tv2.py b/yt_dlp/extractor/tv2.py index c51e63371..f6b452dc8 100644 --- a/yt_dlp/extractor/tv2.py +++ b/yt_dlp/extractor/tv2.py @@ -1,7 +1,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -57,8 +57,8 @@ def _real_extract(self, url): headers={'content-type': 'application/json'}, data='{"device":{"id":"1-1-1","name":"Nettleser (HTML)"}}'.encode())['playback'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read().decode(), video_id)['error'] + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read().decode(), video_id)['error'] error_code = error.get('code') if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION': self.raise_geo_restricted(countries=self._GEO_COUNTRIES) @@ -211,8 +211,8 @@ def _real_extract(self, url): api_base + '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol, video_id, 'Downloading play JSON')['playback'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - error = self._parse_json(e.cause.read().decode(), video_id)['error'] + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + error = self._parse_json(e.cause.response.read().decode(), video_id)['error'] error_code = error.get('code') if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION': self.raise_geo_restricted(countries=self._GEO_COUNTRIES) diff --git a/yt_dlp/extractor/tvp.py b/yt_dlp/extractor/tvp.py index c686044fa..2aa0dd870 100644 --- a/yt_dlp/extractor/tvp.py +++ b/yt_dlp/extractor/tvp.py @@ -488,9 +488,9 @@ def _call_api(self, resource, video_id, query={}, **kwargs): f'{self._API_BASE_URL}/{resource}', video_id, query={'lang': 'pl', 'platform': 'BROWSER', **query}, expected_status=lambda x: is_valid(x) or 400 <= x < 500, **kwargs) - if is_valid(urlh.getcode()): + if is_valid(urlh.status): return document - raise ExtractorError(f'Woronicza said: {document.get("code")} (HTTP {urlh.getcode()})') + raise ExtractorError(f'Woronicza said: {document.get("code")} (HTTP {urlh.status})') def _parse_video(self, video, with_url=True): info_dict = traverse_obj(video, { diff --git a/yt_dlp/extractor/tvplay.py b/yt_dlp/extractor/tvplay.py index e056f9872..48a6efe1c 100644 --- a/yt_dlp/extractor/tvplay.py +++ b/yt_dlp/extractor/tvplay.py @@ -1,10 +1,8 @@ import re from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urlparse, -) +from ..compat import compat_urlparse +from ..networking.exceptions import HTTPError from ..utils import ( determine_ext, ExtractorError, @@ -129,8 +127,8 @@ def _real_extract(self, url): 'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON') except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - msg = self._parse_json(e.cause.read().decode('utf-8'), video_id) + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + msg = self._parse_json(e.cause.response.read().decode('utf-8'), video_id) raise ExtractorError(msg['msg'], expected=True) raise diff --git a/yt_dlp/extractor/tvplayer.py b/yt_dlp/extractor/tvplayer.py index b05355f87..228c2366e 100644 --- a/yt_dlp/extractor/tvplayer.py +++ b/yt_dlp/extractor/tvplayer.py @@ -1,8 +1,6 @@ from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( extract_attributes, try_get, @@ -64,9 +62,9 @@ def _real_extract(self, url): 'validate': validate, }))['tvplayer']['response'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): + if isinstance(e.cause, HTTPError): response = self._parse_json( - e.cause.read().decode(), resource_id)['tvplayer']['response'] + e.cause.response.read().decode(), resource_id)['tvplayer']['response'] raise ExtractorError( '%s said: %s' % (self.IE_NAME, response['error']), expected=True) raise diff --git a/yt_dlp/extractor/twitcasting.py b/yt_dlp/extractor/twitcasting.py index 2548dae04..dff353a4f 100644 --- a/yt_dlp/extractor/twitcasting.py +++ b/yt_dlp/extractor/twitcasting.py @@ -107,9 +107,9 @@ def _real_extract(self, url): url, video_id, data=request_data, headers={'Origin': 'https://twitcasting.tv'}, note='Trying video password') - if urlh.geturl() != url and request_data: + if urlh.url != url and request_data: webpage = self._download_webpage( - urlh.geturl(), video_id, data=request_data, + urlh.url, video_id, data=request_data, headers={'Origin': 'https://twitcasting.tv'}, note='Retrying authentication') # has to check here as the first request can contain password input form even if the password is correct diff --git a/yt_dlp/extractor/twitch.py b/yt_dlp/extractor/twitch.py index c8ee52014..3297ef091 100644 --- a/yt_dlp/extractor/twitch.py +++ b/yt_dlp/extractor/twitch.py @@ -71,7 +71,7 @@ def login_step(page, urlh, note, data): form = self._hidden_inputs(page) form.update(data) - page_url = urlh.geturl() + page_url = urlh.url post_url = self._search_regex( r']+action=(["\'])(?P.+?)\1', page, 'post url', default=self._LOGIN_POST_URL, group='url') diff --git a/yt_dlp/extractor/twitter.py b/yt_dlp/extractor/twitter.py index fc157ac22..4015277a8 100644 --- a/yt_dlp/extractor/twitter.py +++ b/yt_dlp/extractor/twitter.py @@ -1596,7 +1596,7 @@ def _real_extract(self, url): if eid: id = eid url = self._BASE_URL + id - new_url = self._request_webpage(url, id, headers={'User-Agent': 'curl'}).geturl() + new_url = self._request_webpage(url, id, headers={'User-Agent': 'curl'}).url __UNSAFE_LINK = "https://twitter.com/safety/unsafe_link_warning?unsafe_link=" if new_url.startswith(__UNSAFE_LINK): new_url = new_url.replace(__UNSAFE_LINK, "") diff --git a/yt_dlp/extractor/udemy.py b/yt_dlp/extractor/udemy.py index 329e5da2d..5c296051a 100644 --- a/yt_dlp/extractor/udemy.py +++ b/yt_dlp/extractor/udemy.py @@ -1,8 +1,9 @@ import re -import urllib.request from .common import InfoExtractor -from ..compat import compat_HTTPError, compat_str, compat_urlparse +from ..compat import compat_str, compat_urlparse +from ..networking import Request +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, @@ -10,7 +11,6 @@ float_or_none, int_or_none, js_to_json, - sanitized_Request, smuggle_url, try_get, unescapeHTML, @@ -153,11 +153,10 @@ def _download_json(self, url_or_request, *args, **kwargs): headers['X-Udemy-Bearer-Token'] = cookie.value headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value - if isinstance(url_or_request, urllib.request.Request): - for header, value in headers.items(): - url_or_request.add_header(header, value) + if isinstance(url_or_request, Request): + url_or_request.headers.update(headers) else: - url_or_request = sanitized_Request(url_or_request, headers=headers) + url_or_request = Request(url_or_request, headers=headers) response = super(UdemyIE, self)._download_json(url_or_request, *args, **kwargs) self._handle_error(response) @@ -212,7 +211,7 @@ def _real_extract(self, url): lecture = self._download_lecture(course_id, lecture_id) except ExtractorError as e: # Error could possibly mean we are not enrolled in the course - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: webpage = webpage or self._download_webpage(url, lecture_id) self._enroll_course(url, webpage, course_id) lecture = self._download_lecture(course_id, lecture_id) diff --git a/yt_dlp/extractor/vevo.py b/yt_dlp/extractor/vevo.py index da4ce49ca..aa40227a7 100644 --- a/yt_dlp/extractor/vevo.py +++ b/yt_dlp/extractor/vevo.py @@ -2,10 +2,8 @@ import json from .common import InfoExtractor -from ..compat import ( - compat_str, - compat_HTTPError, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -184,8 +182,8 @@ def _call_api(self, path, *args, **kwargs): try: data = self._download_json(self._api_url_template % path, *args, **kwargs) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): - errors = self._parse_json(e.cause.read().decode(), None)['errors'] + if isinstance(e.cause, HTTPError): + errors = self._parse_json(e.cause.response.read().decode(), None)['errors'] error_message = ', '.join([error['message'] for error in errors]) raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) raise diff --git a/yt_dlp/extractor/vice.py b/yt_dlp/extractor/vice.py index d1a3b48aa..8a7126853 100644 --- a/yt_dlp/extractor/vice.py +++ b/yt_dlp/extractor/vice.py @@ -7,10 +7,8 @@ from .adobepass import AdobePassIE from .common import InfoExtractor from .youtube import YoutubeIE -from ..compat import ( - compat_HTTPError, - compat_str, -) +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, ExtractorError, @@ -140,8 +138,8 @@ def _real_extract(self, url): 'https://vms.vice.com/%s/video/preplay/%s' % (locale, video_id), video_id, query=query) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401): - error = json.loads(e.cause.read().decode()) + if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401): + error = json.loads(e.cause.response.read().decode()) error_message = error.get('error_description') or error['details'] raise ExtractorError('%s said: %s' % ( self.IE_NAME, error_message), expected=True) diff --git a/yt_dlp/extractor/videocampus_sachsen.py b/yt_dlp/extractor/videocampus_sachsen.py index 982ab3dd0..37bc7d718 100644 --- a/yt_dlp/extractor/videocampus_sachsen.py +++ b/yt_dlp/extractor/videocampus_sachsen.py @@ -2,7 +2,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ExtractorError, OnDemandPagedList, urlencode_postdata @@ -169,7 +169,7 @@ def _real_extract(self, url): f'https://{host}/media/hlsMedium/key/{video_id}/format/auto/ext/mp4/learning/0/path/m3u8', video_id, 'mp4', m3u8_id='hls', fatal=True) except ExtractorError as e: - if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (404, 500): + if not isinstance(e.cause, HTTPError) or e.cause.status not in (404, 500): raise formats.append({'url': f'https://{host}/getMedium/{video_id}.mp4'}) diff --git a/yt_dlp/extractor/vidio.py b/yt_dlp/extractor/vidio.py index 23e1aaf20..770aa284d 100644 --- a/yt_dlp/extractor/vidio.py +++ b/yt_dlp/extractor/vidio.py @@ -39,7 +39,7 @@ def is_logged_in(): login_post, login_post_urlh = self._download_webpage_handle( self._LOGIN_URL, None, 'Logging in', data=urlencode_postdata(login_form), expected_status=[302, 401]) - if login_post_urlh.getcode() == 401: + if login_post_urlh.status == 401: if get_element_by_class('onboarding-content-register-popup__title', login_post): raise ExtractorError( 'Unable to log in: The provided email has not registered yet.', expected=True) diff --git a/yt_dlp/extractor/vidlii.py b/yt_dlp/extractor/vidlii.py index cde4274d9..44353b7fc 100644 --- a/yt_dlp/extractor/vidlii.py +++ b/yt_dlp/extractor/vidlii.py @@ -1,8 +1,8 @@ import re from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( - HEADRequest, format_field, float_or_none, get_element_by_id, diff --git a/yt_dlp/extractor/viewlift.py b/yt_dlp/extractor/viewlift.py index 381260114..8f686f05d 100644 --- a/yt_dlp/extractor/viewlift.py +++ b/yt_dlp/extractor/viewlift.py @@ -1,7 +1,7 @@ import json from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -46,8 +46,8 @@ def _call_api(self, site, path, video_id, url, query): return self._download_json( self._API_BASE + path, video_id, headers={'Authorization': self._TOKENS.get(site)}, query=query) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - webpage = e.cause.read().decode() + if isinstance(e.cause, HTTPError) and e.cause.status == 403: + webpage = e.cause.response.read().decode() try: error_message = traverse_obj(json.loads(webpage), 'errorMessage', 'message') except json.JSONDecodeError: diff --git a/yt_dlp/extractor/viidea.py b/yt_dlp/extractor/viidea.py index 4cdf2677b..649ffe395 100644 --- a/yt_dlp/extractor/viidea.py +++ b/yt_dlp/extractor/viidea.py @@ -2,10 +2,10 @@ from .common import InfoExtractor from ..compat import ( - compat_HTTPError, compat_str, compat_urlparse, ) +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, js_to_json, @@ -133,9 +133,9 @@ def _real_extract(self, url): '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id), lecture_id)['lecture'][0] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if isinstance(e.cause, HTTPError) and e.cause.status == 403: msg = self._parse_json( - e.cause.read().decode('utf-8'), lecture_id) + e.cause.response.read().decode('utf-8'), lecture_id) raise ExtractorError(msg['detail'], expected=True) raise diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index d81d9c551..e72fa50fa 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -2,20 +2,16 @@ import functools import re import itertools -import urllib.error from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urlparse, -) +from ..compat import compat_str, compat_urlparse +from ..networking import HEADRequest, Request +from ..networking.exceptions import HTTPError from ..utils import ( clean_html, determine_ext, ExtractorError, get_element_by_class, - HEADRequest, js_to_json, int_or_none, merge_dicts, @@ -23,7 +19,6 @@ parse_filesize, parse_iso8601, parse_qs, - sanitized_Request, smuggle_url, str_or_none, try_get, @@ -72,7 +67,7 @@ def _perform_login(self, username, password): 'Referer': self._LOGIN_URL, }) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418: + if isinstance(e.cause, HTTPError) and e.cause.status == 418: raise ExtractorError( 'Unable to log in: bad username or password', expected=True) @@ -809,7 +804,7 @@ def _try_album_password(self, url): 'X-Requested-With': 'XMLHttpRequest', }) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: raise ExtractorError('Wrong password', expected=True) raise @@ -832,10 +827,10 @@ def _real_extract(self, url): # Retrieve video webpage to extract further information webpage, urlh = self._download_webpage_handle( url, video_id, headers=headers) - redirect_url = urlh.geturl() + redirect_url = urlh.url except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - errmsg = ee.cause.read() + if isinstance(ee.cause, HTTPError) and ee.cause.status == 403: + errmsg = ee.cause.response.read() if b'Because of its privacy settings, this video cannot be played here' in errmsg: raise ExtractorError( 'Cannot download embed-only video without embedding ' @@ -1154,7 +1149,7 @@ def _fetch_page(self, album_id, authorization, hashed_pass, page): 'Authorization': 'jwt ' + authorization, })['data'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: return for video in videos: link = video.get('link') @@ -1196,7 +1191,7 @@ def _real_extract(self, url): 'X-Requested-With': 'XMLHttpRequest', })['hashed_pass'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: raise ExtractorError('Wrong password', expected=True) raise entries = OnDemandPagedList(functools.partial( @@ -1309,10 +1304,10 @@ class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete I def _page_url(self, base_url, pagenum): url = '%s/page:%d/' % (base_url, pagenum) - request = sanitized_Request(url) + request = Request(url) # Set the header to get a partial html page with the ids, # the normal page doesn't contain them. - request.add_header('X-Requested-With', 'XMLHttpRequest') + request.headers['X-Requested-With'] = 'XMLHttpRequest' return request def _real_extract(self, url): @@ -1432,7 +1427,7 @@ def _real_extract(self, url): **self._hidden_inputs(password_form), }), note='Logging in with video password') except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 418: + if isinstance(e.cause, HTTPError) and e.cause.status == 418: raise ExtractorError('Wrong video password', expected=True) raise diff --git a/yt_dlp/extractor/vk.py b/yt_dlp/extractor/vk.py index 575369028..6b7379d46 100644 --- a/yt_dlp/extractor/vk.py +++ b/yt_dlp/extractor/vk.py @@ -36,7 +36,7 @@ class VKBaseIE(InfoExtractor): def _download_webpage_handle(self, url_or_request, video_id, *args, fatal=True, **kwargs): response = super()._download_webpage_handle(url_or_request, video_id, *args, fatal=fatal, **kwargs) - challenge_url, cookie = response[1].geturl() if response else '', None + challenge_url, cookie = response[1].url if response else '', None if challenge_url.startswith('https://vk.com/429.html?'): cookie = self._get_cookies(challenge_url).get('hash429') if not cookie: diff --git a/yt_dlp/extractor/vocaroo.py b/yt_dlp/extractor/vocaroo.py index 704e25c22..d98fbfd2d 100644 --- a/yt_dlp/extractor/vocaroo.py +++ b/yt_dlp/extractor/vocaroo.py @@ -1,8 +1,6 @@ from .common import InfoExtractor -from ..utils import ( - HEADRequest, - float_or_none, -) +from ..networking import HEADRequest +from ..utils import float_or_none class VocarooIE(InfoExtractor): diff --git a/yt_dlp/extractor/vodlocker.py b/yt_dlp/extractor/vodlocker.py index 1c7236ed3..b215d6c9d 100644 --- a/yt_dlp/extractor/vodlocker.py +++ b/yt_dlp/extractor/vodlocker.py @@ -1,10 +1,6 @@ from .common import InfoExtractor -from ..utils import ( - ExtractorError, - NO_DEFAULT, - sanitized_Request, - urlencode_postdata, -) +from ..networking import Request +from ..utils import NO_DEFAULT, ExtractorError, urlencode_postdata class VodlockerIE(InfoExtractor): @@ -37,8 +33,8 @@ def _real_extract(self, url): if fields['op'] == 'download1': self._sleep(3, video_id) # they do detect when requests happen too fast! post = urlencode_postdata(fields) - req = sanitized_Request(url, post) - req.add_header('Content-type', 'application/x-www-form-urlencoded') + req = Request(url, post) + req.headers['Content-type'] = 'application/x-www-form-urlencoded' webpage = self._download_webpage( req, video_id, 'Downloading video page') diff --git a/yt_dlp/extractor/voot.py b/yt_dlp/extractor/voot.py index dd41647aa..b19a27934 100644 --- a/yt_dlp/extractor/voot.py +++ b/yt_dlp/extractor/voot.py @@ -1,10 +1,10 @@ import json import time -import urllib.error import uuid from .common import InfoExtractor from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, float_or_none, @@ -140,7 +140,7 @@ def _real_extract(self, url): 'voottoken': self._TOKEN, })['m3u8'] except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: self._check_token_expiry() raise diff --git a/yt_dlp/extractor/vrt.py b/yt_dlp/extractor/vrt.py index 005835712..497233d95 100644 --- a/yt_dlp/extractor/vrt.py +++ b/yt_dlp/extractor/vrt.py @@ -1,10 +1,10 @@ import functools import json import time -import urllib.error import urllib.parse from .gigya import GigyaBaseIE +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, clean_html, @@ -263,7 +263,7 @@ def _perform_login(self, username, password): '_csrf': self._get_cookies('https://login.vrt.be').get('OIDCXSRF').value, })) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: retry.error = e continue raise diff --git a/yt_dlp/extractor/vrv.py b/yt_dlp/extractor/vrv.py index ad9dc568a..523c442e6 100644 --- a/yt_dlp/extractor/vrv.py +++ b/yt_dlp/extractor/vrv.py @@ -8,7 +8,8 @@ import urllib.parse from .common import InfoExtractor -from ..compat import compat_HTTPError, compat_urllib_parse_urlencode +from ..compat import compat_urllib_parse_urlencode +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, float_or_none, @@ -54,8 +55,8 @@ def _call_api(self, path, video_id, note, data=None): '?'.join([base_url, encoded_query]), video_id, note='Downloading %s JSON metadata' % note, headers=headers, data=data) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: - raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True) + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + raise ExtractorError(json.loads(e.cause.response.read().decode())['message'], expected=True) raise def _call_cms(self, path, video_id, note): diff --git a/yt_dlp/extractor/weibo.py b/yt_dlp/extractor/weibo.py index 81a23b9df..bc9a71abe 100644 --- a/yt_dlp/extractor/weibo.py +++ b/yt_dlp/extractor/weibo.py @@ -31,7 +31,7 @@ def _real_extract(self, url): # to get Referer url for genvisitor webpage, urlh = self._download_webpage_handle(url, video_id) - visitor_url = urlh.geturl() + visitor_url = urlh.url if 'passport.weibo.com' in visitor_url: # first visit diff --git a/yt_dlp/extractor/weverse.py b/yt_dlp/extractor/weverse.py index 8f2a7ee06..9a08b8e43 100644 --- a/yt_dlp/extractor/weverse.py +++ b/yt_dlp/extractor/weverse.py @@ -5,13 +5,13 @@ import json import re import time -import urllib.error import urllib.parse import uuid from .common import InfoExtractor from .naver import NaverBaseIE from .youtube import YoutubeIE +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, UserNotLive, @@ -59,7 +59,7 @@ def _perform_login(self, username, password): 'password': password, }, separators=(',', ':')).encode(), headers=headers, note='Logging in') except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: raise ExtractorError('Invalid password provided', expected=True) raise @@ -97,10 +97,10 @@ def _call_api(self, ep, video_id, data=None, note='Downloading API JSON'): 'wmd': wmd, }) except ExtractorError as e: - if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: self.raise_login_required( 'Session token has expired. Log in again or refresh cookies in browser') - elif isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: + elif isinstance(e.cause, HTTPError) and e.cause.status == 403: raise ExtractorError('Your account does not have access to this content', expected=True) raise diff --git a/yt_dlp/extractor/wistia.py b/yt_dlp/extractor/wistia.py index 884fa4b5f..bce5e8326 100644 --- a/yt_dlp/extractor/wistia.py +++ b/yt_dlp/extractor/wistia.py @@ -1,12 +1,12 @@ import re -import urllib.error import urllib.parse from base64 import b64decode from .common import InfoExtractor +from ..networking import HEADRequest +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, - HEADRequest, determine_ext, float_or_none, int_or_none, @@ -365,7 +365,7 @@ def _real_extract(self, url): try: data = self._download_embed_config('channel', channel_id, url) - except (ExtractorError, urllib.error.HTTPError): + except (ExtractorError, HTTPError): # Some channels give a 403 from the JSON API self.report_warning('Failed to download channel data from API, falling back to webpage.') webpage = self._download_webpage(f'https://fast.wistia.net/embed/channel/{channel_id}', channel_id) diff --git a/yt_dlp/extractor/wykop.py b/yt_dlp/extractor/wykop.py index 0fa6d524d..1d29cc89b 100644 --- a/yt_dlp/extractor/wykop.py +++ b/yt_dlp/extractor/wykop.py @@ -1,7 +1,7 @@ import json -import urllib.error from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, format_field, @@ -43,7 +43,7 @@ def _call_api(self, path, video_id, note='Downloading JSON metadata'): try: return self._do_call_api(path, video_id, note, headers={'Authorization': f'Bearer {token}'}) except ExtractorError as e: - if not retrying and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 403: + if not retrying and isinstance(e.cause, HTTPError) and e.cause.status == 403: token = self._get_token(True) continue raise diff --git a/yt_dlp/extractor/xhamster.py b/yt_dlp/extractor/xhamster.py index 7af6c8f03..37224799b 100644 --- a/yt_dlp/extractor/xhamster.py +++ b/yt_dlp/extractor/xhamster.py @@ -183,7 +183,7 @@ def get_height(s): 'height': get_height(quality), 'filesize': format_sizes.get(quality), 'http_headers': { - 'Referer': urlh.geturl(), + 'Referer': urlh.url, }, }) xplayer_sources = try_get( diff --git a/yt_dlp/extractor/xtube.py b/yt_dlp/extractor/xtube.py index ce4480c7d..db8292589 100644 --- a/yt_dlp/extractor/xtube.py +++ b/yt_dlp/extractor/xtube.py @@ -2,12 +2,12 @@ import re from .common import InfoExtractor +from ..networking import Request from ..utils import ( int_or_none, js_to_json, orderedSet, parse_duration, - sanitized_Request, str_to_int, url_or_none, ) @@ -186,7 +186,7 @@ def _real_extract(self, url): entries = [] for pagenum in itertools.count(1): - request = sanitized_Request( + request = Request( 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum), headers={ 'Cookie': 'popunder=4', diff --git a/yt_dlp/extractor/yesjapan.py b/yt_dlp/extractor/yesjapan.py index b45fa8f14..94e41660d 100644 --- a/yt_dlp/extractor/yesjapan.py +++ b/yt_dlp/extractor/yesjapan.py @@ -1,9 +1,6 @@ from .common import InfoExtractor -from ..utils import ( - HEADRequest, - get_element_by_attribute, - parse_iso8601, -) +from ..networking import HEADRequest +from ..utils import get_element_by_attribute, parse_iso8601 class YesJapanIE(InfoExtractor): @@ -42,7 +39,7 @@ def _real_extract(self, url): req = self._request_webpage( redirect_req, video_id, note='Resolving final URL', errnote='Could not resolve final URL', fatal=False) if req: - video_url = req.geturl() + video_url = req.url formats = [{ 'format_id': 'sd', diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 826bbb20e..2b3776aa1 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -15,13 +15,13 @@ import threading import time import traceback -import urllib.error import urllib.parse from .common import InfoExtractor, SearchInfoExtractor from .openload import PhantomJSwrapper from ..compat import functools from ..jsinterp import JSInterpreter +from ..networking.exceptions import HTTPError, network_exceptions from ..utils import ( NO_DEFAULT, ExtractorError, @@ -41,7 +41,6 @@ join_nonempty, js_to_json, mimetype2ext, - network_exceptions, orderedSet, parse_codecs, parse_count, @@ -959,15 +958,15 @@ def _extract_response(self, item_id, query, note='Downloading API JSON', headers except ExtractorError as e: if not isinstance(e.cause, network_exceptions): return self._error_or_warning(e, fatal=fatal) - elif not isinstance(e.cause, urllib.error.HTTPError): + elif not isinstance(e.cause, HTTPError): retry.error = e continue - first_bytes = e.cause.read(512) + first_bytes = e.cause.response.read(512) if not is_html(first_bytes): yt_error = try_get( self._parse_json( - self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), + self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), lambda x: x['error']['message'], str) if yt_error: self._report_alerts([('ERROR', yt_error)], fatal=False) @@ -975,7 +974,7 @@ def _extract_response(self, item_id, query, note='Downloading API JSON', headers # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289 # We also want to catch all other network exceptions since errors in later pages can be troublesome # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 - if e.cause.code not in (403, 429): + if e.cause.status not in (403, 429): retry.error = e continue return self._error_or_warning(e, fatal=fatal) @@ -2837,7 +2836,7 @@ def _extract_sequence_from_mpd(refresh_sequence, immediate): # Obtain from MPD's maximum seq value old_mpd_url = mpd_url last_error = ctx.pop('last_error', None) - expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403 + expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) or (mpd_url, stream_number, False)) if not refresh_sequence: @@ -5263,7 +5262,7 @@ def _extract_webpage(self, url, item_id, fatal=True): data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {} except ExtractorError as e: if isinstance(e.cause, network_exceptions): - if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429): + if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429): retry.error = e continue self._error_or_warning(e, fatal=fatal) diff --git a/yt_dlp/extractor/zaiko.py b/yt_dlp/extractor/zaiko.py index 84cee4445..0ccacbb6a 100644 --- a/yt_dlp/extractor/zaiko.py +++ b/yt_dlp/extractor/zaiko.py @@ -16,7 +16,7 @@ class ZaikoBaseIE(InfoExtractor): def _download_real_webpage(self, url, video_id): webpage, urlh = self._download_webpage_handle(url, video_id) - final_url = urlh.geturl() + final_url = urlh.url if 'zaiko.io/login' in final_url: self.raise_login_required() elif '/_buy/' in final_url: diff --git a/yt_dlp/extractor/zattoo.py b/yt_dlp/extractor/zattoo.py index 22620c0a3..6bd9ea064 100644 --- a/yt_dlp/extractor/zattoo.py +++ b/yt_dlp/extractor/zattoo.py @@ -2,7 +2,8 @@ from uuid import uuid4 from .common import InfoExtractor -from ..compat import compat_HTTPError, compat_str +from ..compat import compat_str +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, int_or_none, @@ -36,7 +37,7 @@ def _perform_login(self, username, password): 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', }) except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + if isinstance(e.cause, HTTPError) and e.cause.status == 400: raise ExtractorError( 'Unable to login: incorrect username and/or password', expected=True) diff --git a/yt_dlp/extractor/zype.py b/yt_dlp/extractor/zype.py index 8cf994505..2f3b4c47f 100644 --- a/yt_dlp/extractor/zype.py +++ b/yt_dlp/extractor/zype.py @@ -1,7 +1,7 @@ import re from .common import InfoExtractor -from ..compat import compat_HTTPError +from ..networking.exceptions import HTTPError from ..utils import ( dict_get, ExtractorError, @@ -37,9 +37,9 @@ def _real_extract(self, url): response = self._download_json(re.sub( r'\.(?:js|html)\?', '.json?', url), video_id)['response'] except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 403): + if isinstance(e.cause, HTTPError) and e.cause.status in (400, 401, 403): raise ExtractorError(self._parse_json( - e.cause.read().decode(), video_id)['message'], expected=True) + e.cause.response.read().decode(), video_id)['message'], expected=True) raise body = response['body'] diff --git a/yt_dlp/networking/common.py b/yt_dlp/networking/common.py index e4b362827..458eca39f 100644 --- a/yt_dlp/networking/common.py +++ b/yt_dlp/networking/common.py @@ -24,6 +24,7 @@ from ..utils import ( bug_reports_message, classproperty, + deprecation_warning, error_to_str, escape_url, update_url_query, @@ -507,16 +508,21 @@ def get_header(self, name, default=None): # The following methods are for compatability reasons and are deprecated @property def code(self): + deprecation_warning('Response.code is deprecated, use Response.status', stacklevel=2) return self.status def getcode(self): + deprecation_warning('Response.getcode() is deprecated, use Response.status', stacklevel=2) return self.status def geturl(self): + deprecation_warning('Response.geturl() is deprecated, use Response.url', stacklevel=2) return self.url def info(self): + deprecation_warning('Response.info() is deprecated, use Response.headers', stacklevel=2) return self.headers def getheader(self, name, default=None): + deprecation_warning('Response.getheader() is deprecated, use Response.get_header', stacklevel=2) return self.get_header(name, default) diff --git a/yt_dlp/networking/exceptions.py b/yt_dlp/networking/exceptions.py index 6fe8afb92..10afc9ccb 100644 --- a/yt_dlp/networking/exceptions.py +++ b/yt_dlp/networking/exceptions.py @@ -3,7 +3,7 @@ import typing import urllib.error -from ..utils import YoutubeDLError +from ..utils import YoutubeDLError, deprecation_warning if typing.TYPE_CHECKING: from .common import RequestHandler, Response @@ -137,6 +137,7 @@ def reason(self, value): @property def headers(self): + deprecation_warning('HTTPError.headers is deprecated, use HTTPError.response.headers instead') return self._http_error.response.headers @headers.setter @@ -144,16 +145,20 @@ def headers(self, value): return def info(self): + deprecation_warning('HTTPError.info() is deprecated, use HTTPError.response.headers instead') return self.response.headers def getcode(self): + deprecation_warning('HTTPError.getcode is deprecated, use HTTPError.status instead') return self.status def geturl(self): + deprecation_warning('HTTPError.geturl is deprecated, use HTTPError.response.url instead') return self.response.url @property def code(self): + deprecation_warning('HTTPError.code is deprecated, use HTTPError.status instead') return self.status @code.setter @@ -162,6 +167,7 @@ def code(self, value): @property def url(self): + deprecation_warning('HTTPError.url is deprecated, use HTTPError.response.url instead') return self.response.url @url.setter @@ -170,6 +176,7 @@ def url(self, value): @property def hdrs(self): + deprecation_warning('HTTPError.hdrs is deprecated, use HTTPError.response.headers instead') return self.response.headers @hdrs.setter @@ -178,6 +185,7 @@ def hdrs(self, value): @property def filename(self): + deprecation_warning('HTTPError.filename is deprecated, use HTTPError.response.url instead') return self.response.url @filename.setter @@ -185,6 +193,18 @@ def filename(self, value): return def __getattr__(self, name): + # File operations are passed through the response. + # Warn for some commonly used ones + passthrough_warnings = { + 'read': 'response.read()', + # technically possibly due to passthrough, but we should discourage this + 'get_header': 'response.get_header()', + 'readable': 'response.readable()', + 'closed': 'response.closed', + 'tell': 'response.tell()', + } + if name in passthrough_warnings: + deprecation_warning(f'HTTPError.{name} is deprecated, use HTTPError.{passthrough_warnings[name]} instead') return super().__getattr__(name) def __str__(self): diff --git a/yt_dlp/postprocessor/common.py b/yt_dlp/postprocessor/common.py index 08b0fe1ff..8cef86c43 100644 --- a/yt_dlp/postprocessor/common.py +++ b/yt_dlp/postprocessor/common.py @@ -1,16 +1,15 @@ import functools import json import os -import urllib.error +from ..networking import Request +from ..networking.exceptions import HTTPError, network_exceptions from ..utils import ( PostProcessingError, RetryManager, _configuration_args, deprecation_warning, encodeFilename, - network_exceptions, - sanitized_Request, ) @@ -203,13 +202,13 @@ def _download_json(self, url, *, expected_http_errors=(404,)): self.write_debug(f'{self.PP_NAME} query: {url}') for retry in RetryManager(self.get_param('extractor_retries', 3), self._retry_download): try: - rsp = self._downloader.urlopen(sanitized_Request(url)) + rsp = self._downloader.urlopen(Request(url)) except network_exceptions as e: - if isinstance(e, urllib.error.HTTPError) and e.code in expected_http_errors: + if isinstance(e, HTTPError) and e.status in expected_http_errors: return None retry.error = PostProcessingError(f'Unable to communicate with {self.PP_NAME} API: {e}') continue - return json.loads(rsp.read().decode(rsp.info().get_param('charset') or 'utf-8')) + return json.loads(rsp.read().decode(rsp.headers.get_param('charset') or 'utf-8')) class AudioConversionError(PostProcessingError): # Deprecated diff --git a/yt_dlp/update.py b/yt_dlp/update.py index 4790075eb..d708b09e3 100644 --- a/yt_dlp/update.py +++ b/yt_dlp/update.py @@ -7,19 +7,18 @@ import re import subprocess import sys -import urllib.error from zipimport import zipimporter from .compat import functools # isort: split from .compat import compat_realpath, compat_shlex_quote +from .networking import Request +from .networking.exceptions import HTTPError, network_exceptions from .utils import ( Popen, cached_method, deprecation_warning, - network_exceptions, remove_end, remove_start, - sanitized_Request, shell_quote, system_identifier, version_tuple, @@ -190,7 +189,7 @@ def _tag(self): def _get_version_info(self, tag): url = f'{API_BASE_URL}/{self._target_repo}/releases/{tag}' self.ydl.write_debug(f'Fetching release info: {url}') - return json.loads(self.ydl.urlopen(sanitized_Request(url, headers={ + return json.loads(self.ydl.urlopen(Request(url, headers={ 'Accept': 'application/vnd.github+json', 'User-Agent': 'yt-dlp', 'X-GitHub-Api-Version': '2022-11-28', @@ -315,7 +314,7 @@ def update(self): try: newcontent = self._download(self.release_name, self._tag) except network_exceptions as e: - if isinstance(e, urllib.error.HTTPError) and e.code == 404: + if isinstance(e, HTTPError) and e.status == 404: return self._report_error( f'The requested tag {self._label(self.target_channel, self.target_tag)} does not exist', True) return self._report_network_error(f'fetch updates: {e}') diff --git a/yt_dlp/utils/_deprecated.py b/yt_dlp/utils/_deprecated.py index e55d42354..a8ae8ecb5 100644 --- a/yt_dlp/utils/_deprecated.py +++ b/yt_dlp/utils/_deprecated.py @@ -10,16 +10,6 @@ from ._utils import preferredencoding -from ..networking._urllib import HTTPHandler - -# isort: split -from .networking import random_user_agent, std_headers # noqa: F401 -from ..networking._urllib import PUTRequest # noqa: F401 -from ..networking._urllib import SUPPORTED_ENCODINGS, HEADRequest # noqa: F401 -from ..networking._urllib import ProxyHandler as PerRequestProxyHandler # noqa: F401 -from ..networking._urllib import RedirectHandler as YoutubeDLRedirectHandler # noqa: F401 -from ..networking._urllib import make_socks_conn_class, update_Request # noqa: F401 -from ..networking.exceptions import network_exceptions # noqa: F401 def encodeFilename(s, for_subprocess=False): @@ -47,12 +37,3 @@ def decodeOption(optval): def error_to_compat_str(err): return str(err) - - -class YoutubeDLHandler(HTTPHandler): - def __init__(self, params, *args, **kwargs): - self._params = params - super().__init__(*args, **kwargs) - - -YoutubeDLHTTPSHandler = YoutubeDLHandler diff --git a/yt_dlp/utils/_legacy.py b/yt_dlp/utils/_legacy.py index 96ac468b1..077000971 100644 --- a/yt_dlp/utils/_legacy.py +++ b/yt_dlp/utils/_legacy.py @@ -1,17 +1,30 @@ """No longer used and new code should not use. Exists only for API compat.""" - import platform import struct import sys +import urllib.error import urllib.parse +import urllib.request import zlib from ._utils import Popen, decode_base_n, preferredencoding from .traversal import traverse_obj from ..dependencies import certifi, websockets +from ..networking._helper import make_ssl_context +from ..networking._urllib import HTTPHandler # isort: split +from .networking import random_user_agent, std_headers # noqa: F401 from ..cookies import YoutubeDLCookieJar # noqa: F401 +from ..networking._urllib import PUTRequest # noqa: F401 +from ..networking._urllib import SUPPORTED_ENCODINGS, HEADRequest # noqa: F401 +from ..networking._urllib import ProxyHandler as PerRequestProxyHandler # noqa: F401 +from ..networking._urllib import RedirectHandler as YoutubeDLRedirectHandler # noqa: F401 +from ..networking._urllib import ( # noqa: F401 + make_socks_conn_class, + update_Request, +) +from ..networking.exceptions import HTTPError, network_exceptions # noqa: F401 has_certifi = bool(certifi) has_websockets = bool(websockets) @@ -176,5 +189,52 @@ def handle_youtubedl_headers(headers): return filtered_headers +def request_to_url(req): + if isinstance(req, urllib.request.Request): + return req.get_full_url() + else: + return req + + +def sanitized_Request(url, *args, **kwargs): + from ..utils import escape_url, extract_basic_auth, sanitize_url + url, auth_header = extract_basic_auth(escape_url(sanitize_url(url))) + if auth_header is not None: + headers = args[1] if len(args) >= 2 else kwargs.setdefault('headers', {}) + headers['Authorization'] = auth_header + return urllib.request.Request(url, *args, **kwargs) + + +class YoutubeDLHandler(HTTPHandler): + def __init__(self, params, *args, **kwargs): + self._params = params + super().__init__(*args, **kwargs) + + +YoutubeDLHTTPSHandler = YoutubeDLHandler + + +class YoutubeDLCookieProcessor(urllib.request.HTTPCookieProcessor): + def __init__(self, cookiejar=None): + urllib.request.HTTPCookieProcessor.__init__(self, cookiejar) + + def http_response(self, request, response): + return urllib.request.HTTPCookieProcessor.http_response(self, request, response) + + https_request = urllib.request.HTTPCookieProcessor.http_request + https_response = http_response + + +def make_HTTPS_handler(params, **kwargs): + return YoutubeDLHTTPSHandler(params, context=make_ssl_context( + verify=not params.get('nocheckcertificate'), + client_certificate=params.get('client_certificate'), + client_certificate_key=params.get('client_certificate_key'), + client_certificate_password=params.get('client_certificate_password'), + legacy_support=params.get('legacyserverconnect'), + use_certifi='no-certifi' not in params.get('compat_opts', []), + ), **kwargs) + + def process_communicate_or_kill(p, *args, **kwargs): return Popen.communicate_or_kill(p, *args, **kwargs) diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index d0e328716..2e619f9ea 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -62,11 +62,6 @@ compiled_regex_type = type(re.compile('')) -USER_AGENTS = { - 'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27', -} - - class NO_DEFAULT: pass @@ -727,14 +722,6 @@ def extract_basic_auth(url): return url, f'Basic {auth_payload.decode()}' -def sanitized_Request(url, *args, **kwargs): - url, auth_header = extract_basic_auth(escape_url(sanitize_url(url))) - if auth_header is not None: - headers = args[1] if len(args) >= 2 else kwargs.setdefault('headers', {}) - headers['Authorization'] = auth_header - return urllib.request.Request(url, *args, **kwargs) - - def expand_path(s): """Expand shell variables and ~""" return os.path.expandvars(compat_expanduser(s)) @@ -894,19 +881,6 @@ def formatSeconds(secs, delim=':', msec=False): return '%s.%03d' % (ret, time.milliseconds) if msec else ret -def make_HTTPS_handler(params, **kwargs): - from ._deprecated import YoutubeDLHTTPSHandler - from ..networking._helper import make_ssl_context - return YoutubeDLHTTPSHandler(params, context=make_ssl_context( - verify=not params.get('nocheckcertificate'), - client_certificate=params.get('client_certificate'), - client_certificate_key=params.get('client_certificate_key'), - client_certificate_password=params.get('client_certificate_password'), - legacy_support=params.get('legacyserverconnect'), - use_certifi='no-certifi' not in params.get('compat_opts', []), - ), **kwargs) - - def bug_reports_message(before=';'): from ..update import REPOSITORY @@ -1143,17 +1117,6 @@ def is_path_like(f): return isinstance(f, (str, bytes, os.PathLike)) -class YoutubeDLCookieProcessor(urllib.request.HTTPCookieProcessor): - def __init__(self, cookiejar=None): - urllib.request.HTTPCookieProcessor.__init__(self, cookiejar) - - def http_response(self, request, response): - return urllib.request.HTTPCookieProcessor.http_response(self, request, response) - - https_request = urllib.request.HTTPCookieProcessor.http_request - https_response = http_response - - def extract_timezone(date_str): m = re.search( r'''(?x) @@ -1455,6 +1418,7 @@ def write_string(s, out=None, encoding=None): out.flush() +# TODO: Use global logger def deprecation_warning(msg, *, printer=None, stacklevel=0, **kwargs): from .. import _IN_CLI if _IN_CLI: @@ -2005,13 +1969,6 @@ def url_or_none(url): return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None -def request_to_url(req): - if isinstance(req, urllib.request.Request): - return req.get_full_url() - else: - return req - - def strftime_or_none(timestamp, date_format='%Y%m%d', default=None): datetime_object = None try: @@ -5525,7 +5482,7 @@ def info(self, message): def warning(self, message, *, once=False): if self._ydl: - self._ydl.report_warning(message, only_once=once) + self._ydl.report_warning(message, once) def error(self, message, *, is_error=True): if self._ydl: