diff options
author | Haricharan Padmanaban <hari.jan20@gmail.com> | 2014-09-14 23:14:00 -0500 |
---|---|---|
committer | Haricharan Padmanaban <hari.jan20@gmail.com> | 2014-09-14 23:14:00 -0500 |
commit | 98703c7fbfcf06348220aa63f9422cdd792cfe1a (patch) | |
tree | 7da50de9653ffba31071a6c71878ae1082d7343c /youtube_dl/extractor/einthusan.py | |
parent | 9a66c1079cdf6d6688aafe0dcc7c1285f04a302c (diff) |
Einthusan Add new extractor
Diffstat (limited to 'youtube_dl/extractor/einthusan.py')
-rw-r--r-- | youtube_dl/extractor/einthusan.py | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py new file mode 100644 index 000000000..712368faf --- /dev/null +++ b/youtube_dl/extractor/einthusan.py @@ -0,0 +1,54 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class EinthusanIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?einthusan\.com/movies/watch.php\?(.*)?id=(?P<id>[0-9]+).*?' + _TESTS = [ + { + 'url': 'http://www.einthusan.com/movies/watch.php?hindimoviesonline=Ek+Villain&lang=hindi&id=2447', + 'md5': 'af244f4458cd667205e513d75da5b8b1', + 'info_dict': { + 'id': '2447', + 'ext': 'mp4', + 'title': 'Ek Villain', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + { + 'url': 'http://www.einthusan.com/movies/watch.php?id=1671', + 'md5': 'ef63c7a803e22315880ed182c10d1c5c', + 'info_dict': { + 'id': '1671', + 'ext': 'mp4', + 'title': 'Soodhu Kavvuum', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'''<h1><a class="movie-title".*?>(.*?)</a></h1>''', webpage, 'title') + + video_url = self._html_search_regex( + r'''(?s)jwplayer\("mediaplayer"\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video url') + + thumb_rel_url = self._html_search_regex( + r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', webpage, "thumbnail url") + thumb_abs_url = re.sub('\.\.', 'http://www.einthusan.com', thumb_rel_url) + + return { + 'id': video_id, + 'ext': 'mp4', + 'title': video_title, + 'url': video_url, + 'thumbnail': thumb_abs_url, + } |