From 32d687f55e103963a2cb8d8f3f88bb31b9cb8fb6 Mon Sep 17 00:00:00 2001 From: zx8 Date: Sun, 22 Mar 2015 18:03:40 +0000 Subject: [PATCH 1/2] [safari] Add safaribooksonline extractor --- youtube_dl/extractor/__init__.py | 4 + youtube_dl/extractor/safari.py | 144 +++++++++++++++++++++++++++++++ 2 files changed, 148 insertions(+) create mode 100644 youtube_dl/extractor/safari.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d73826d44..3a0c42ded 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -420,6 +420,10 @@ ) from .rutv import RUTVIE from .sandia import SandiaIE +from .safari import ( + SafariIE, + SafariCourseIE, +) from .sapo import SapoIE from .savefrom import SaveFromIE from .sbs import SBSIE diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py new file mode 100644 index 000000000..3e494b960 --- /dev/null +++ b/youtube_dl/extractor/safari.py @@ -0,0 +1,144 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from .brightcove import BrightcoveIE + +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + ExtractorError, + smuggle_url, + std_headers, +) + + +class SafariBaseIE(InfoExtractor): + _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' + _SUCCESSFUL_LOGIN_REGEX = r']+>Sign Out' + _ACCOUNT_CREDENTIALS_HINT = ('Use --username and --password options to ' + 'supply credentials for safaribooksonline.com ') + _NETRC_MACHINE = 'safaribooksonline' + + LOGGED_IN = False + + def _real_initialize(self): + # We only need to log in once for courses or individual videos + if not SafariBaseIE.LOGGED_IN: + self._login() + SafariBaseIE.LOGGED_IN = True + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + raise ExtractorError( + self._ACCOUNT_CREDENTIALS_HINT, + expected=True) + + headers = std_headers + if 'Referer' not in headers: + headers['Referer'] = self._LOGIN_URL + + login_page = self._download_webpage( + self._LOGIN_URL, None, + 'Downloading login form') + + csrf = self._html_search_regex( + r"", + login_page, 'csrf token') + + login_form = { + 'csrfmiddlewaretoken': csrf, + 'email': username, + 'password1': password, + 'login': 'Sign In', + 'next': '', + } + + request = compat_urllib_request.Request( + self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers) + login_page = self._download_webpage( + request, None, 'Logging in as %s' % username) + + if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None: + raise ExtractorError('Login failed; make sure your credentials are correct and ' + 'try again.', expected=True) + + self.to_screen('Login successful') + + +class SafariIE(SafariBaseIE): + IE_NAME = 'safari' + IE_DESC = 'safaribooksonline.com online video' + _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/' + '(?P\d+)/(?Ppart\d+)\.html') + _TEST = { + 'url': ('https://www.safaribooksonline.com/library/view/' + 'hadoop-fundamentals-livelessons/9780133392838/part00.html'), + 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', + 'info_dict': { + 'id': '9780133392838', + 'ext': 'mp4', + 'title': 'Introduction', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + part = mobj.group('part') + + webpage = self._download_webpage(url, part) + bc_url = BrightcoveIE._extract_brightcove_url(webpage) + if not bc_url: + raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) + + return { + '_type': 'url', + 'url': smuggle_url(bc_url, {'Referer': url}), + 'ie_key': 'Brightcove' + } + + +class SafariCourseIE(SafariBaseIE): + IE_NAME = 'safari:course' + IE_DESC = 'safaribooksonline.com online courses' + + _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/' + '(?P[^/]+)/(?P\d+)/?$') + + _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_FORMAT = 'json' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + course_path = mobj.group('course_path') + course_id = mobj.group('id') + + webpage = self._download_webpage( + '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), + course_path, 'Downloading course JSON') + + course_json = json.loads(webpage) + + if 'chapters' not in course_json: + raise ExtractorError('No chapters found for course %s' % course_id, expected=True) + + num_parts = len(course_json['chapters']) + parts = ['%02d' % part for part in range(num_parts)] + + entries = [ + self.url_result( + 'https://www.safaribooksonline.com/library/view/%s/%s/part%s.html' % (course_path, + course_id, + part_id), + 'Safari') + for part_id in parts] + + course_title = course_json['title'] + + return self.playlist_result(entries, course_id, course_title) From 31c48098276100a3fa2529b1443687e56838f707 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 26 Mar 2015 23:57:46 +0600 Subject: [PATCH 2/2] [safari] Improve and simplify --- youtube_dl/extractor/safari.py | 101 +++++++++++++++++++-------------- 1 file changed, 57 insertions(+), 44 deletions(-) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 3e494b960..10251f29e 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from .brightcove import BrightcoveIE @@ -20,16 +19,18 @@ class SafariBaseIE(InfoExtractor): _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' - _SUCCESSFUL_LOGIN_REGEX = r']+>Sign Out' - _ACCOUNT_CREDENTIALS_HINT = ('Use --username and --password options to ' - 'supply credentials for safaribooksonline.com ') - _NETRC_MACHINE = 'safaribooksonline' + _SUCCESSFUL_LOGIN_REGEX = r']*>Sign Out' + _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com' + _NETRC_MACHINE = 'safari' + + _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_FORMAT = 'json' LOGGED_IN = False def _real_initialize(self): # We only need to log in once for courses or individual videos - if not SafariBaseIE.LOGGED_IN: + if not self.LOGGED_IN: self._login() SafariBaseIE.LOGGED_IN = True @@ -49,7 +50,7 @@ def _login(self): 'Downloading login form') csrf = self._html_search_regex( - r"", + r"name='csrfmiddlewaretoken'\s+value='([^']+)'", login_page, 'csrf token') login_form = { @@ -66,8 +67,9 @@ def _login(self): request, None, 'Logging in as %s' % username) if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None: - raise ExtractorError('Login failed; make sure your credentials are correct and ' - 'try again.', expected=True) + raise ExtractorError( + 'Login failed; make sure your credentials are correct and try again.', + expected=True) self.to_screen('Login successful') @@ -75,69 +77,80 @@ def _login(self): class SafariIE(SafariBaseIE): IE_NAME = 'safari' IE_DESC = 'safaribooksonline.com online video' - _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/' - '(?P\d+)/(?Ppart\d+)\.html') - _TEST = { - 'url': ('https://www.safaribooksonline.com/library/view/' - 'hadoop-fundamentals-livelessons/9780133392838/part00.html'), + _VALID_URL = r'''(?x)https?:// + (?:www\.)?safaribooksonline\.com/ + (?: + library/view/[^/]+| + api/v1/book + )/ + (?P\d+)/ + (?:chapter(?:-content)?/)? + (?Ppart\d+)\.html + ''' + + _TESTS = [{ + 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', 'info_dict': { - 'id': '9780133392838', + 'id': '2842601850001', 'ext': 'mp4', 'title': 'Introduction', - } - } + }, + 'skip': 'Requires safaribooksonline account credentials', + }, { + 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + course_id = mobj.group('course_id') part = mobj.group('part') - webpage = self._download_webpage(url, part) + webpage = self._download_webpage( + '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part), + part) + bc_url = BrightcoveIE._extract_brightcove_url(webpage) if not bc_url: raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) - return { - '_type': 'url', - 'url': smuggle_url(bc_url, {'Referer': url}), - 'ie_key': 'Brightcove' - } + return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove') class SafariCourseIE(SafariBaseIE): IE_NAME = 'safari:course' IE_DESC = 'safaribooksonline.com online courses' - _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/' - '(?P[^/]+)/(?P\d+)/?$') + _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P\d+)/?(?:[#?]|$)' - _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' - _API_FORMAT = 'json' + _TESTS = [{ + 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/', + 'info_dict': { + 'id': '9780133392838', + 'title': 'Hadoop Fundamentals LiveLessons', + }, + 'playlist_count': 22, + 'skip': 'Requires safaribooksonline account credentials', + }, { + 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_path = mobj.group('course_path') - course_id = mobj.group('id') + course_id = self._match_id(url) - webpage = self._download_webpage( + course_json = self._download_json( '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), - course_path, 'Downloading course JSON') - - course_json = json.loads(webpage) + course_id, 'Downloading course JSON') if 'chapters' not in course_json: - raise ExtractorError('No chapters found for course %s' % course_id, expected=True) - - num_parts = len(course_json['chapters']) - parts = ['%02d' % part for part in range(num_parts)] + raise ExtractorError( + 'No chapters found for course %s' % course_id, expected=True) entries = [ - self.url_result( - 'https://www.safaribooksonline.com/library/view/%s/%s/part%s.html' % (course_path, - course_id, - part_id), - 'Safari') - for part_id in parts] + self.url_result(chapter, 'Safari') + for chapter in course_json['chapters']] course_title = course_json['title']