_ Git - youtube-dl/blob - youtube_dl/extractor/pyvideo.py

   1 import re
   2 import os
   3
   4 from .common import InfoExtractor
   5
   6
   7 class PyvideoIE(InfoExtractor):
   8     _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
   9     _TESTS = [{
  10         u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
  11         u'file': u'24_4WWkSmNo.mp4',
  12         u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
  13         u'info_dict': {
  14             u"title": u"Become a logging expert in 30 minutes",
  15             u"description": u"md5:9665350d466c67fb5b1598de379021f7",
  16             u"upload_date": u"20130320",
  17             u"uploader": u"NextDayVideo",
  18             u"uploader_id": u"NextDayVideo",
  19         },
  20         u'add_ie': ['Youtube'],
  21     },
  22     {
  23         u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
  24         u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
  25         u'info_dict': {
  26             u'id': u'2542',
  27             u'ext': u'm4v',
  28             u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
  29         },
  30     },
  31     ]
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('id')
  36         webpage = self._download_webpage(url, video_id)
  37         m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
  38
  39         if m_youtube is not None:
  40             return self.url_result(m_youtube.group(1), 'Youtube')
  41
  42         title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
  43             webpage, u'title', flags=re.DOTALL)
  44         video_url = self._search_regex([r'<source src="(.*?)"',
  45             r'<dt>Download</dt>.*?<a href="(.+?)"'],
  46             webpage, u'video url', flags=re.DOTALL)
  47         return {
  48             'id': video_id,
  49             'title': os.path.splitext(title)[0],
  50             'url': video_url,
  51         }