[piapro] Add extractor (#2801)

Based on https://github.com/ytdl-org/youtube-dl/pull/25922
Closes #2710, https://github.com/ytdl-org/youtube-dl/issues/5856

Authored by: pycabbage, Lesmiscore
This commit is contained in:
Lesmiscore (Naoya Ozaki) 2022-02-18 02:15:29 +09:00 committed by GitHub
parent ae419aa94f
commit 6bb608d055
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 101 additions and 0 deletions

View file

@ -1162,6 +1162,7 @@
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .piapro import PiaproIE
from .picarto import (
PicartoIE,
PicartoVodIE,

100
yt_dlp/extractor/piapro.py Normal file
View file

@ -0,0 +1,100 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
parse_duration,
parse_filesize,
str_to_int,
unified_timestamp,
urlencode_postdata,
)
class PiaproIE(InfoExtractor):
_NETRC_MACHINE = 'piapro'
_VALID_URL = r'https?://piapro\.jp/t/(?P<id>\w+)/?'
_TESTS = [{
'url': 'https://piapro.jp/t/NXYR',
'md5': 'a9d52f27d13bafab7ee34116a7dcfa77',
'info_dict': {
'id': 'NXYR',
'ext': 'mp3',
'uploader': 'wowaka',
'uploader_id': 'wowaka',
'title': '裏表ラバーズ',
'thumbnail': r're:^https?://.*\.jpg$',
}
}]
def _real_initialize(self):
self._login_status = self._login()
def _login(self):
username, password = self._get_login_info()
if not username:
return False
login_ok = True
login_form_strs = {
'_username': username,
'_password': password,
'_remember_me': 'on',
'login': 'ログイン'
}
self._request_webpage('https://piapro.jp/login/', None)
urlh = self._request_webpage(
'https://piapro.jp/login/exe', None,
note='Logging in', errnote='Unable to log in',
data=urlencode_postdata(login_form_strs))
if urlh is False:
login_ok = False
else:
parts = compat_urlparse.urlparse(urlh.geturl())
if parts.path != '/':
login_ok = False
if not login_ok:
self.report_warning(
'unable to log in: bad username or password')
return login_ok
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
category_id = self._search_regex(r'categoryId=(.+)">', webpage, 'category ID')
if category_id not in ('1', '2', '21', '22', '23', '24', '25'):
raise ExtractorError('The URL does not contain audio.', expected=True)
str_duration, str_filesize = self._search_regex(
r'サイズ:</span>(.+?)/\(([0-9,]+?[KMG]?B)', webpage, 'duration and size',
group=(1, 2), default=(None, None))
str_viewcount = self._search_regex(r'閲覧数:</span>([0-9,]+)\s+', webpage, 'view count', fatal=False)
uploader_id, uploader = self._search_regex(
r'<a\s+class="cd_user-name"\s+href="/(.*)">([^<]+)さん<', webpage, 'uploader',
group=(1, 2), default=(None, None))
content_id = self._search_regex(r'contentId\:\'(.+)\'', webpage, 'content ID')
create_date = self._search_regex(r'createDate\:\'(.+)\'', webpage, 'timestamp')
player_webpage = self._download_webpage(
f'https://piapro.jp/html5_player_popup/?id={content_id}&cdate={create_date}',
video_id, note='Downloading player webpage')
return {
'id': video_id,
'title': self._html_search_regex(r'<h1\s+class="cd_works-title">(.+?)</h1>', webpage, 'title', fatal=False),
'description': self._html_search_regex(r'<p\s+class="cd_dtl_cap">(.+?)</p>\s*<div', webpage, 'description', fatal=False),
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': unified_timestamp(create_date, False),
'duration': parse_duration(str_duration),
'view_count': str_to_int(str_viewcount),
'thumbnail': self._html_search_meta('twitter:image', webpage),
'filesize_approx': parse_filesize(str_filesize.replace(',', '')),
'url': self._search_regex(r'mp3:\s*\'(.*?)\'\}', player_webpage, 'url'),
'ext': 'mp3',
'vcodec': 'none',
}