diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-12-13 12:24:42 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-12-13 12:35:45 +0100 |
commit | 1cc79574fc5df21bf35dccf61eac0e9e75ed8d20 (patch) | |
tree | 5cc2bd2a2faba0ac5e8371892e3ef09ab5338080 /youtube_dl/extractor/xvideos.py | |
parent | 20e35880bf7413c5085c1ade96af0fc6e56d84d1 (diff) |
Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
Diffstat (limited to 'youtube_dl/extractor/xvideos.py')
-rw-r--r-- | youtube_dl/extractor/xvideos.py | 22 |
1 files changed, 6 insertions, 16 deletions
diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 7e0044824..2a45dc574 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,15 +3,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, - ExtractorError, +) +from ..utils import ( clean_html, + ExtractorError, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)' _TEST = { 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', @@ -24,37 +26,25 @@ class XVideosIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) if mobj: raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) - # Extract video URL video_url = compat_urllib_parse.unquote( self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) - - # Extract title video_title = self._html_search_regex( r'<title>(.*?)\s+-\s+XVID', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'url_bigthumb=(.+?)&', webpage, '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, 'age_limit': 18, } |