_ 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 .youtube import YoutubeIE
   8 from ..compat import (
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     clean_html,
  13     ExtractorError,
  14     get_element_by_id,
  15 )
  16
  17
  18 class TechTVMITIE(InfoExtractor):
  19     IE_NAME = 'techtv.mit.edu'
  20     _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
  21
  22     _TEST = {
  23         'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
  24         'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
  25         'info_dict': {
  26             'id': '25418',
  27             'ext': 'mp4',
  28             'title': 'MIT DNA Learning Center Set',
  29             'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
  30         },
  31     }
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('id')
  36         raw_page = self._download_webpage(
  37             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
  38         clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
  39
  40         base_url = self._search_regex(
  41             r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
  42         formats_json = self._search_regex(
  43             r'bitrates: (\[.+?\])', raw_page, 'video formats')
  44         formats_mit = json.loads(formats_json)
  45         formats = [
  46             {
  47                 'format_id': f['label'],
  48                 'url': base_url + f['url'].partition(':')[2],
  49                 'ext': f['url'].partition(':')[0],
  50                 'format': f['label'],
  51                 'width': f['width'],
  52                 'vbr': f['bitrate'],
  53             }
  54             for f in formats_mit
  55         ]
  56
  57         title = get_element_by_id('edit-title', clean_page)
  58         description = clean_html(get_element_by_id('edit-description', clean_page))
  59         thumbnail = self._search_regex(
  60             r'playlist:.*?url: \'(.+?)\'',
  61             raw_page, 'thumbnail', flags=re.DOTALL)
  62
  63         return {
  64             'id': video_id,
  65             'title': title,
  66             'formats': formats,
  67             'description': description,
  68             'thumbnail': thumbnail,
  69         }
  70
  71
  72 class MITIE(TechTVMITIE):
  73     IE_NAME = 'video.mit.edu'
  74     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
  75
  76     _TEST = {
  77         'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
  78         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
  79         'info_dict': {
  80             'id': '21783',
  81             'ext': 'mp4',
  82             'title': 'The Government is Profiling You',
  83             'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
  84         },
  85     }
  86
  87     def _real_extract(self, url):
  88         mobj = re.match(self._VALID_URL, url)
  89         page_title = mobj.group('title')
  90         webpage = self._download_webpage(url, page_title)
  91         embed_url = self._search_regex(
  92             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
  93         return self.url_result(embed_url, ie='TechTVMIT')
  94
  95
  96 class OCWMITIE(InfoExtractor):
  97     IE_NAME = 'ocw.mit.edu'
  98     _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
  99     _BASE_URL = 'http://ocw.mit.edu/'
 100
 101     _TESTS = [
 102         {
 103             'url': '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/',
 104             'info_dict': {
 105                 'id': 'EObHWIEKGjA',
 106                 'ext': 'mp4',
 107                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
 108                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
 109                 #'subtitles': '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'
 110             }
 111         },
 112         {
 113             'url': '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/',
 114             'info_dict': {
 115                 'id': '7K1sB05pE0A',
 116                 'ext': 'mp4',
 117                 'title': 'Session 1: Introduction to Derivatives',
 118                 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
 119                 #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
 120             }
 121         }
 122     ]
 123
 124     def _real_extract(self, url):
 125         mobj = re.match(self._VALID_URL, url)
 126         topic = mobj.group('topic')
 127
 128         webpage = self._download_webpage(url, topic)
 129         title = self._html_search_meta('WT.cg_s', webpage)
 130         description = self._html_search_meta('Description', webpage)
 131
 132         # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
 133         embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
 134         if embed_chapter_media:
 135             metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
 136             metadata = re.split(r', ?', metadata)
 137             yt = metadata[1]
 138             subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
 139         else:
 140             # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
 141             embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
 142             if embed_media:
 143                 metadata = re.sub(r'[\'"]', '', embed_media.group(1))
 144                 metadata = re.split(r', ?', metadata)
 145                 yt = metadata[1]
 146                 subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
 147             else:
 148                 raise ExtractorError('Unable to find embedded YouTube video.')
 149         video_id = YoutubeIE.extract_id(yt)
 150
 151         return {
 152             '_type': 'url_transparent',
 153             'id': video_id,
 154             'title': title,
 155             'description': description,
 156             'url': yt,
 157             'url_transparent'
 158             'subtitles': subs,
 159             'ie_key': 'Youtube',
 160         }