diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-10-27 00:33:35 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-10-27 00:33:35 +0100 |
| commit | 249efaf44bbdedf24f7da7c9d27afc397251d106 (patch) | |
| tree | 0ed3ce08c8cbc35a84f9364501e0546c43c12798 /youtube_dl/extractor/pornhub.py | |
| parent | 8d32abff9e3d56bf74eb6eec8284623a94f4551f (diff) | |
[pornhub] Modernize and fix test definition
Diffstat (limited to 'youtube_dl/extractor/pornhub.py')
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 13 |
1 files changed, 6 insertions, 7 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 4118ee956..618e8f5dd 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,13 +16,14 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))' + _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)' _TEST = { 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', - 'file': '648719015.mp4', 'md5': '882f488fa1f0026f023f33576004a2ed', 'info_dict': { - "uploader": "BABES-COM", + 'id': '648719015', + 'ext': 'mp4', + "uploader": "Babes", "title": "Seductive Indian beauty strips down and fingers her pink pussy", "age_limit": 18 } @@ -35,9 +36,7 @@ class PornHubIE(InfoExtractor): return count def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -45,7 +44,7 @@ class PornHubIE(InfoExtractor): video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: |