fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[youjizz] move into own file

This commit is contained in:
Philipp Hagemeister 2013-06-23 22:14:22 +02:00
parent 1183b85f50
commit c3c77cec30
2 changed files with 46 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
youtube_dl/InfoExtractors.py
View File

@ -53,6 +53,7 @@ from .extractor.worldstarhiphop import WorldStarHipHopIE
from .extractor.xnxx import XNXXIE from .extractor.xnxx import XNXXIE
from .extractor.xvideos import XVideosIE from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youjizz import YouJizzIE
from .extractor.youku import YoukuIE from .extractor.youku import YoukuIE
from .extractor.youporn import YouPornIE from .extractor.youporn import YouPornIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
@ -81,46 +82,6 @@ from .extractor.zdf import ZDFIE
class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
# Get webpage content
webpage = self._download_webpage(url, video_id)
# 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
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}
return [info]
class EightTracksIE(InfoExtractor): class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks' IE_NAME = '8tracks'

45
youtube_dl/extractor/youjizz.py Normal file
View File

@ -0,0 +1,45 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
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)
# 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
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}
return [info]