mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-12 14:26:49 +01:00
[youjizz] move into own file
This commit is contained in:
parent
1183b85f50
commit
c3c77cec30
@ -53,6 +53,7 @@
|
||||
from .extractor.xnxx import XNXXIE
|
||||
from .extractor.xvideos import XVideosIE
|
||||
from .extractor.yahoo import YahooIE, YahooSearchIE
|
||||
from .extractor.youjizz import YouJizzIE
|
||||
from .extractor.youku import YoukuIE
|
||||
from .extractor.youporn import YouPornIE
|
||||
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
|
||||
@ -81,46 +82,6 @@
|
||||
|
||||
|
||||
|
||||
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):
|
||||
IE_NAME = '8tracks'
|
||||
|
45
youtube_dl/extractor/youjizz.py
Normal file
45
youtube_dl/extractor/youjizz.py
Normal 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]
|
Loading…
Reference in New Issue
Block a user