diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 22:01:57 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 22:01:57 +0200 |
commit | 570fa151fcd1f56cba8aaeff9f77d1e50e508e1b (patch) | |
tree | fe20738655f0aca19d2c76ee995477dfe29f53bd | |
parent | 9c286cfa004d18da196a6961ffda30bb9bf57515 (diff) |
Move XNXX into its own file
-rw-r--r-- | youtube_dl/extractor/xnxx.py | 45 |
1 files changed, 45 insertions, 0 deletions
diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py new file mode 100644 index 000000000..68acb8409 --- /dev/null +++ b/youtube_dl/extractor/xnxx.py @@ -0,0 +1,45 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + + ExtractorError, +) + + +class XNXXIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' + VIDEO_URL_RE = r'flv_url=(.*?)&' + VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' + VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' + + 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) + + # Get webpage content + webpage = self._download_webpage(url, video_id) + + video_url = self._search_regex(self.VIDEO_URL_RE, + webpage, u'video URL') + video_url = compat_urllib_parse.unquote(video_url) + + video_title = self._html_search_regex(self.VIDEO_TITLE_RE, + webpage, u'title') + + video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE, + webpage, u'thumbnail', fatal=False) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + }] |