1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-23 03:12:58 +08:00
youtube-dl/youtube_dl/extractor/youjizz.py

70 lines
2.5 KiB
Python

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_TEST = {
u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
u'file': u'2189178.flv',
u'md5': u'07e15fa469ba384c7693fd246905547c',
u'info_dict': {
u"title": u"Zeichentrick 1",
u"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
# Get the video title
video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
webpage, u'title').strip()
# Get the embed page
result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
if result is None:
raise ExtractorError(u'ERROR: unable to extract embed page')
embed_page_url = result.group(0).strip()
video_id = result.group('videoid')
webpage = self._download_webpage(embed_page_url, video_id)
# Get the video URL
m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
if m_playlist is not None:
playlist_url = m_playlist.group('playlist')
playlist_page = self._download_webpage(playlist_url, video_id,
u'Downloading playlist page')
m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
if len(m_levels) == 0:
raise ExtractorError(u'Unable to extract video url')
videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
(_, video_url) = sorted(videos)[0]
video_url = video_url.replace('%252F', '%2F')
else:
video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
webpage, u'video URL')
info = {'id': video_id,
'url': video_url,
'title': video_title,
'ext': 'flv',
'format': 'flv',
'player_url': embed_page_url,
'age_limit': age_limit}
return [info]