1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 19:52:11 +00:00
youtube-dl/youtube_dl/extractor/wimp.py
2015-12-07 22:18:00 +06:00

54 lines
1.7 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
from .youtube import YoutubeIE
class WimpIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.wimp.com/maruexhausted/',
'md5': 'ee21217ffd66d058e8b16be340b74883',
'info_dict': {
'id': 'maruexhausted',
'ext': 'mp4',
'title': 'Maru is exhausted.',
'description': 'md5:57e099e857c0a4ea312542b684a869b8',
}
}, {
'url': 'http://www.wimp.com/clowncar/',
'md5': '4e2986c793694b55b37cf92521d12bb4',
'info_dict': {
'id': 'clowncar',
'ext': 'mp4',
'title': 'It\'s like a clown car.',
'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
youtube_id = self._search_regex(
r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
webpage, 'video URL', default=None)
if youtube_id:
return {
'_type': 'url',
'url': youtube_id,
'ie_key': YoutubeIE.ie_key(),
}
video_url = self._search_regex(
r'<video[^>]+>\s*<source[^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'video URL', group='url')
return {
'id': video_id,
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
}