mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 20:33:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

[einthusan] Add description and beautify

Browse source
This commit is contained in:
Philipp Hagemeister 2014-09-15 23:33:47 +02:00
parent 5419033935
commit e2037b3f7d
1 changed files with 15 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
youtube_dl/extractor/einthusan.py
View file

@ -7,7 +7,7 @@
class EinthusanIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?einthusan\.com/movies/watch.php\?(.*)?id=(?P<id>[0-9]+).*?'
_VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)'
_TESTS = [
{
'url': 'http://www.einthusan.com/movies/watch.php?id=2447',
@ -17,6 +17,7 @@ class EinthusanIE(InfoExtractor):
'ext': 'mp4',
'title': 'Ek Villain',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'md5:9d29fc91a7abadd4591fb862fa560d93',
}
},
{
@ -27,6 +28,7 @@ class EinthusanIE(InfoExtractor):
'ext': 'mp4',
'title': 'Soodhu Kavvuum',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'md5:05d8a0c0281a4240d86d76e14f2f4d51',
}
},
]
@ -36,19 +38,24 @@ def _real_extract(self, 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_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')
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)
description = self._html_search_meta('description', webpage)
thumbnail = self._html_search_regex(
r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''',
webpage, "thumbnail url", fatal=False)
if thumbnail is not None:
thumbnail = thumbnail.replace('..', 'http://www.einthusan.com')
return {
'id': video_id,
'ext': 'mp4',
'title': video_title,
'url': video_url,
'thumbnail': thumb_abs_url,
'thumbnail': thumbnail,
'description': description,
}