diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:11:47 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:11:47 +0200 |
commit | cbf46c737c3f4156dee019b70521dcd3194877ac (patch) | |
tree | 59298f69374e85ad1173971ab5893efda6904bba /youtube_dl/InfoExtractors.py | |
parent | 7beb36a52974a2cf7c8b00ba1da339f4f3de3abc (diff) |
Move XVideos IE into its own file (and simplify it a bit)
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
-rwxr-xr-x | youtube_dl/InfoExtractors.py | 44 |
1 files changed, 1 insertions, 43 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 789fd147c..8fcd19ca2 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -37,54 +37,12 @@ from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.vimeo import VimeoIE +from .extractor.xvideos import XVideosIE from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.zdf import ZDFIE -class XVideosIE(InfoExtractor): - """Information extractor for xvideos.com""" - - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' - IE_NAME = u'xvideos' - - 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(1) - - webpage = self._download_webpage(url, video_id) - - self.report_extraction(video_id) - - # Extract video URL - video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', - webpage, u'video URL')) - - # Extract title - video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID', - webpage, u'title') - - # Extract video thumbnail - video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', - webpage, u'thumbnail', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'thumbnail': video_thumbnail, - 'description': None, - } - - return [info] - - - class InfoQIE(InfoExtractor): """Information extractor for infoq.com""" |