yt-dlp/youtube_dl/extractor/wimp.py

56 lines
1.7 KiB
Python
Raw Normal View History

2014-01-21 20:01:23 -05:00
from __future__ import unicode_literals
2013-06-26 06:25:53 -04:00
import re
2013-06-26 06:25:53 -04:00
from .common import InfoExtractor
from .youtube import YoutubeIE
2013-06-26 06:25:53 -04:00
class WimpIE(InfoExtractor):
2014-02-21 05:57:19 -05:00
_VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
_TESTS = [{
2014-02-21 05:57:19 -05:00
'url': 'http://www.wimp.com/maruexhausted/',
'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
2014-01-21 20:01:23 -05:00
'info_dict': {
2014-02-21 05:57:19 -05:00
'id': 'maruexhausted',
'ext': 'flv',
'title': 'Maru is exhausted.',
'description': 'md5:57e099e857c0a4ea312542b684a869b8',
2013-06-27 14:46:46 -04:00
}
}, {
# youtube video
'url': 'http://www.wimp.com/clowncar/',
'info_dict': {
'id': 'cG4CEr2aiSg',
'ext': 'mp4',
'title': 'Basset hound clown car...incredible!',
'description': 'md5:8d228485e0719898c017203f900b3a35',
'uploader': 'Gretchen Hoey',
'uploader_id': 'gretchenandjeff1',
'upload_date': '20140303',
},
'add_ie': ['Youtube'],
}]
2013-06-26 06:25:53 -04:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
2014-01-21 20:01:23 -05:00
video_url = self._search_regex(
2014-11-04 05:13:17 -05:00
r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL')
if YoutubeIE.suitable(video_url):
self.to_screen('Found YouTube video')
return {
'_type': 'url',
'url': video_url,
'ie_key': YoutubeIE.ie_key(),
}
2013-12-08 01:22:19 -05:00
return {
'id': video_id,
2014-01-21 20:01:23 -05:00
'url': video_url,
2013-12-08 01:22:19 -05:00
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
}