pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-14 22:37:59 +09:00
Code Issues Projects Releases Wiki Activity

Improve YouJizz

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-01-12 16:36:51 +01:00
parent 629fcdd135
commit db16276b7c
1 changed files with 6 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
youtube_dl/InfoExtractors.py
View File

@ -3896,9 +3896,6 @@ class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com.""" """Information extractor for youjizz.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
@ -3911,19 +3908,15 @@ class YouJizzIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# Get the video title # Get the video title
VIDEO_TITLE_RE = r'<title>(?P<title>.*)</title>' result = re.search(r'<title>(?P<title>.*)</title>', webpage)
result = re.search(VIDEO_TITLE_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title') raise ExtractorError(u'ERROR: unable to extract video title')
return
video_title = result.group('title').strip() video_title = result.group('title').strip()
# Get the embed page # Get the embed page
EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)' result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
result = re.search(EMBED_PAGE_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract embed page') raise ExtractorError(u'ERROR: unable to extract embed page')
return
embed_page_url = result.group(0).strip() embed_page_url = result.group(0).strip()
video_id = result.group('videoid') video_id = result.group('videoid')
@ -3931,22 +3924,16 @@ class YouJizzIE(InfoExtractor):
webpage = self._download_webpage(embed_page_url, video_id) webpage = self._download_webpage(embed_page_url, video_id)
# Get the video URL # Get the video URL
SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);' result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
result = re.search(SOURCE_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video url') raise ExtractorError(u'ERROR: unable to extract video url')
return
video_url = result.group('source') video_url = result.group('source')
info = {'id': video_id, info = {'id': video_id,
'url': video_url, 'url': video_url,
'uploader': None,
'upload_date': None,
'title': video_title, 'title': video_title,
'ext': 'flv', 'ext': 'flv',
'format': 'flv', 'format': 'flv',
'thumbnail': None,
'description': None,
'player_url': embed_page_url} 'player_url': embed_page_url}
return [info] return [info]