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/extractor/xvideos.py | |
parent | 7beb36a52974a2cf7c8b00ba1da339f4f3de3abc (diff) |
Move XVideos IE into its own file (and simplify it a bit)
Diffstat (limited to 'youtube_dl/extractor/xvideos.py')
-rw-r--r-- | youtube_dl/extractor/xvideos.py | 43 |
1 files changed, 43 insertions, 0 deletions
diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py new file mode 100644 index 000000000..8b3cb3930 --- /dev/null +++ b/youtube_dl/extractor/xvideos.py @@ -0,0 +1,43 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, +) + + +class XVideosIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, 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] |