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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urlparse,
   9     clean_html,
  10     get_element_by_id,
  11 )
  12
  13
  14 class TechTVMITIE(InfoExtractor):
  15     IE_NAME = 'techtv.mit.edu'
  16     _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
  17
  18     _TEST = {
  19         'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
  20         'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
  21         'info_dict': {
  22             'id': '25418',
  23             'ext': 'mp4',
  24             'title': 'MIT DNA Learning Center Set',
  25             'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         raw_page = self._download_webpage(
  33             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
  34         clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
  35
  36         base_url = self._search_regex(
  37             r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
  38         formats_json = self._search_regex(
  39             r'bitrates: (\[.+?\])', raw_page, 'video formats')
  40         formats_mit = json.loads(formats_json)
  41         formats = [
  42             {
  43                 'format_id': f['label'],
  44                 'url': base_url + f['url'].partition(':')[2],
  45                 'ext': f['url'].partition(':')[0],
  46                 'format': f['label'],
  47                 'width': f['width'],
  48                 'vbr': f['bitrate'],
  49             }
  50             for f in formats_mit
  51         ]
  52
  53         title = get_element_by_id('edit-title', clean_page)
  54         description = clean_html(get_element_by_id('edit-description', clean_page))
  55         thumbnail = self._search_regex(
  56             r'playlist:.*?url: \'(.+?)\'',
  57             raw_page, 'thumbnail', flags=re.DOTALL)
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'formats': formats,
  63             'description': description,
  64             'thumbnail': thumbnail,
  65         }
  66
  67
  68 class MITIE(TechTVMITIE):
  69     IE_NAME = 'video.mit.edu'
  70     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
  71
  72     _TEST = {
  73         'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
  74         'file': '.mp4',
  75         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
  76         'info_dict': {
  77             'id': '21783',
  78             'ext': 'mp4',
  79             'title': 'The Government is Profiling You',
  80             'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
  81         },
  82     }
  83
  84     def _real_extract(self, url):
  85         mobj = re.match(self._VALID_URL, url)
  86         page_title = mobj.group('title')
  87         webpage = self._download_webpage(url, page_title)
  88         embed_url = self._search_regex(
  89             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
  90         return self.url_result(embed_url, ie='TechTVMIT')
  91
  92 class OCWMITIE(InfoExtractor):
  93     IE_NAME = u'ocw.mit.edu'
  94     _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
  95     _BASE_URL = u'http://ocw.mit.edu/'
  96
  97     _TESTS = [
  98         {
  99             u'url': u'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
 100             u'md5': u'348bef727b573c0bd9ad8a7c08c89ebd',
 101             u'info_dict': {
 102                 u'title': u'7. Discrete Random Variables III',
 103                 u'description': u'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
 104                 u'subtitles': u'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
 105             }
 106         },
 107         {
 108             u'url': u'http://ocw.mit.edu/courses/mathematics/18-01sc-single-variable-calculus-fall-2010/1.-differentiation/part-a-definition-and-basic-rules/session-1-introduction-to-derivatives/',
 109             u'md5': u'f4a434f08f15e581eb67cec0b57bcf6f',
 110             u'info_dict': {
 111                 u'title': u'Lec 1 _ MIT 18.01 Single Variable Calculus, Fall 2007',
 112                 u'subtitles': u'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
 113             }
 114         }
 115     ]
 116
 117     def _real_extract(self, url):
 118         webpage = self._download_webpage(url, self.IE_NAME)
 119         title = self._html_search_meta(u'WT.cg_s', webpage)
 120         description = self._html_search_meta(u'Description', webpage)
 121
 122         # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
 123         embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
 124         if embed_chapter_media:
 125             metadata = re.sub(r'[\'"]', u'', embed_chapter_media.group(1))
 126             metadata = re.split(r', ?', metadata)
 127             yt = metadata[1]
 128             subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
 129         else:
 130             # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
 131             embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
 132             if embed_media:
 133                 metadata = re.sub(r'[\'"]', u'', embed_media.group(1))
 134                 metadata = re.split(r', ?', metadata)
 135                 yt = metadata[1]
 136                 subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
 137             else:
 138                 raise ExtractorError('Unable to find embedded YouTube video.')
 139
 140         data = self.url_result(yt, 'Youtube')
 141         data['subtitles'] = subs
 142
 143         return data