youtube_dl/extractor/mit.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_str,
   7     clean_html,
   8     get_element_by_id,
   9 )
  10
  11
  12 class TechTVMITIE(InfoExtractor):
  13     IE_NAME = u'techtv.mit.edu'
  14     _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
  15
  16     _TEST = {
  17         u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
  18         u'file': u'25418.mp4',
  19         u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
  20         u'info_dict': {
  21             u'title': u'MIT DNA Learning Center Set',
  22             u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         raw_page = self._download_webpage(
  30             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
  31         clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
  32
  33         base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
  34             raw_page, u'base url')
  35         formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
  36             u'video formats')
  37         formats_mit = json.loads(formats_json)
  38         formats = [
  39             {
  40                 'format_id': f['label'],
  41                 'url': base_url + f['url'].partition(':')[2],
  42                 'ext': f['url'].partition(':')[0],
  43                 'format': f['label'],
  44                 'width': f['width'],
  45                 'vbr': f['bitrate'],
  46             }
  47             for f in formats_mit
  48         ]
  49
  50         title = get_element_by_id('edit-title', clean_page)
  51         description = clean_html(get_element_by_id('edit-description', clean_page))
  52         thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
  53             raw_page, u'thumbnail', flags=re.DOTALL)
  54
  55         return {'id': video_id,
  56                 'title': title,
  57                 'formats': formats,
  58                 'description': description,
  59                 'thumbnail': thumbnail,
  60                 }
  61
  62
  63 class MITIE(TechTVMITIE):
  64     IE_NAME = u'video.mit.edu'
  65     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
  66
  67     _TEST = {
  68         u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
  69         u'file': u'21783.mp4',
  70         u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
  71         u'info_dict': {
  72             u'title': u'The Government is Profiling You',
  73             u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
  74         },
  75     }
  76
  77     def _real_extract(self, url):
  78         mobj = re.match(self._VALID_URL, url)
  79         page_title = mobj.group('title')
  80         webpage = self._download_webpage(url, page_title)
  81         self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
  82         embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
  83             u'embed url')
  84         return self.url_result(embed_url, ie='TechTVMIT')