[subtitles] Added tests to check correct behavior when no subtitles are
[youtube-dl] / youtube_dl / extractor / funnyordie.py
1 import re
2
3 from .common import InfoExtractor
4
5
6 class FunnyOrDieIE(InfoExtractor):
7     _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
8     _TEST = {
9         u'url': u'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
10         u'file': u'0732f586d7.mp4',
11         u'md5': u'f647e9e90064b53b6e046e75d0241fbd',
12         u'info_dict': {
13             u"description": u"Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.", 
14             u"title": u"Heart-Shaped Box: Literal Video Version"
15         }
16     }
17
18     def _real_extract(self, url):
19         mobj = re.match(self._VALID_URL, url)
20
21         video_id = mobj.group('id')
22         webpage = self._download_webpage(url, video_id)
23
24         video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
25             webpage, u'video URL', flags=re.DOTALL)
26
27         title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
28             r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
29
30         info = {
31             'id': video_id,
32             'url': video_url,
33             'ext': 'mp4',
34             'title': title,
35             'description': self._og_search_description(webpage),
36         }
37         return [info]