diff options
author | Unknown <blackjack4494@web.de> | 2020-09-02 20:25:25 +0200 |
---|---|---|
committer | Unknown <blackjack4494@web.de> | 2020-09-02 20:25:25 +0200 |
commit | cefecac12cd3c70f9c7a30992c60b05c2eb5d34e (patch) | |
tree | f7b8e3f8ca2f6e402c83a501f72c09854ae04887 /youtube_dlc/extractor/lenta.py | |
parent | 9688f237163b6aa546fde00bb3fd1e3445dd4c31 (diff) | |
download | hypervideo-pre-cefecac12cd3c70f9c7a30992c60b05c2eb5d34e.tar.lz hypervideo-pre-cefecac12cd3c70f9c7a30992c60b05c2eb5d34e.tar.xz hypervideo-pre-cefecac12cd3c70f9c7a30992c60b05c2eb5d34e.zip |
[skip travis] renaming
to avoid using same folder when using pip install for example
Diffstat (limited to 'youtube_dlc/extractor/lenta.py')
-rw-r--r-- | youtube_dlc/extractor/lenta.py | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/youtube_dlc/extractor/lenta.py b/youtube_dlc/extractor/lenta.py new file mode 100644 index 000000000..2ebd4e577 --- /dev/null +++ b/youtube_dlc/extractor/lenta.py @@ -0,0 +1,53 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class LentaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/', + 'info_dict': { + 'id': '964400', + 'ext': 'mp4', + 'title': 'Надежду Савченко задержали', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 61, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + }, { + # EaglePlatform iframe embed + 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + 'info_dict': { + 'id': '227304', + 'ext': 'mp4', + 'title': 'Навальный вышел на свободу', + 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 87, + 'view_count': int, + 'age_limit': 0, + }, + 'params': { + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'vid\s*:\s*["\']?(\d+)', webpage, 'eagleplatform id', + default=None) + if video_id: + return self.url_result( + 'eagleplatform:lentaru.media.eagleplatform.com:%s' % video_id, + ie='EaglePlatform', video_id=video_id) + + return self.url_result(url, ie='Generic') |