diff options
author | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
---|---|---|
committer | Jesús <heckyel@hyperbola.info> | 2021-06-09 17:54:27 -0500 |
commit | 27fe903c511691c078942bef5ee9a05a43b15c8f (patch) | |
tree | 50f30ab2ec749b965869518c0a28651f8677f0d3 /hypervideo_dl/extractor/extremetube.py | |
download | hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.lz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.tar.xz hypervideo-27fe903c511691c078942bef5ee9a05a43b15c8f.zip |
initial
Diffstat (limited to 'hypervideo_dl/extractor/extremetube.py')
-rw-r--r-- | hypervideo_dl/extractor/extremetube.py | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/hypervideo_dl/extractor/extremetube.py b/hypervideo_dl/extractor/extremetube.py new file mode 100644 index 0000000..acd4090 --- /dev/null +++ b/hypervideo_dl/extractor/extremetube.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +from ..utils import str_to_int +from .keezmovies import KeezMoviesIE + + +class ExtremeTubeIE(KeezMoviesIE): + _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)' + _TESTS = [{ + 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', + 'md5': '92feaafa4b58e82f261e5419f39c60cb', + 'info_dict': { + 'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431', + 'ext': 'mp4', + 'title': 'Music Video 14 british euro brit european cumshots swallow', + 'uploader': 'anonim', + 'view_count': int, + 'age_limit': 18, + } + }, { + 'url': 'http://www.extremetube.com/gay/video/abcde-1234', + 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick', + 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/652431', + 'only_matching': True, + }] + + def _real_extract(self, url): + webpage, info = self._extract_info(url) + + if not info['title']: + info['title'] = self._search_regex( + r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title') + + uploader = self._html_search_regex( + r'Uploaded by:\s*</[^>]+>\s*<a[^>]+>(.+?)</a>', + webpage, 'uploader', fatal=False) + view_count = str_to_int(self._search_regex( + r'Views:\s*</[^>]+>\s*<[^>]+>([\d,\.]+)</', + webpage, 'view count', fatal=False)) + + info.update({ + 'uploader': uploader, + 'view_count': view_count, + }) + + return info |