diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-04-01 22:03:35 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-04-01 22:03:35 +0600 |
commit | 7cf02b661953b6c4a9d16f838c622831e55cb389 (patch) | |
tree | 419ec7dc719a81d1ba5b74ba615e87cf8148b851 | |
parent | 60e1fe00799357145e1d43efc1a1548a8d9abb11 (diff) | |
parent | 55cde6ef3c046dfd5f6ef84b908d38ee4375cf08 (diff) |
Merge branch 'mtp1376-varzesh3'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/varzesh3.py | 45 |
2 files changed, 46 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9fddb8e32..f3ebe4ee2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -556,6 +556,7 @@ from .ultimedia import UltimediaIE from .unistra import UnistraIE from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE +from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE diff --git a/youtube_dl/extractor/varzesh3.py b/youtube_dl/extractor/varzesh3.py new file mode 100644 index 000000000..9369abaf8 --- /dev/null +++ b/youtube_dl/extractor/varzesh3.py @@ -0,0 +1,45 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class Varzesh3IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P<id>[^/]+)/?' + _TEST = { + 'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/', + 'md5': '2a933874cb7dce4366075281eb49e855', + 'info_dict': { + 'id': '76337', + 'ext': 'mp4', + 'title': '۵ واکنش برتر دروازهبانان؛هفته ۲۶ بوندسلیگا', + 'description': 'فصل ۲۰۱۵-۲۰۱۴', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r'<source[^>]+src="([^"]+)"', webpage, 'video url') + + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'(?s)<div class="matn">(.+?)</div>', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + + video_id = self._search_regex( + r"<link[^>]+rel='(?:canonical|shortlink)'[^>]+href='/\?p=([^']+)'", + webpage, display_id, default=display_id) + + return { + 'url': video_url, + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } |