Raphaël G. Git Repositories - youtubedl/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 ..utils import (
   9     clean_html,
  10     ExtractorError,
  11     get_element_by_id,
  12 )
  13
  14
  15 class TechTVMITIE(InfoExtractor):
  16     IE_NAME = 'techtv.mit.edu'
  17     _VALID_URL = r'https?://techtv\.mit\.edu/(?:videos|embeds)/(?P<id>\d+)'
  18
  19     _TEST = {
  20         'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
  21         'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
  22         'info_dict': {
  23             'id': '25418',
  24             'ext': 'mp4',
  25             'title': 'MIT DNA Learning Center Set',
  26             'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
  27         },
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  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         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
  75         'info_dict': {
  76             'id': '21783',
  77             'ext': 'mp4',
  78             'title': 'The Government is Profiling You',
  79             'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
  80         },
  81     }
  82
  83     def _real_extract(self, url):
  84         mobj = re.match(self._VALID_URL, url)
  85         page_title = mobj.group('title')
  86         webpage = self._download_webpage(url, page_title)
  87         embed_url = self._search_regex(
  88             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
  89         return self.url_result(embed_url, ie='TechTVMIT')
  90
  91
  92 class OCWMITIE(InfoExtractor):
  93     IE_NAME = 'ocw.mit.edu'
  94     _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
  95     _BASE_URL = 'http://ocw.mit.edu/'
  96
  97     _TESTS = [
  98         {
  99             '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/',
 100             'info_dict': {
 101                 'id': 'EObHWIEKGjA',
 102                 'ext': 'mp4',
 103                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
 104                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
 105                 'upload_date': '20121109',
 106                 'uploader_id': 'MIT',
 107                 'uploader': 'MIT OpenCourseWare',
 108             }
 109         },
 110         {
 111             '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/',
 112             'info_dict': {
 113                 'id': '7K1sB05pE0A',
 114                 'ext': 'mp4',
 115                 'title': 'Session 1: Introduction to Derivatives',
 116                 'upload_date': '20090818',
 117                 'uploader_id': 'MIT',
 118                 'uploader': 'MIT OpenCourseWare',
 119                 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
 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         else:
 139             # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
 140             embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
 141             if embed_media:
 142                 metadata = re.sub(r'[\'"]', '', embed_media.group(1))
 143                 metadata = re.split(r', ?', metadata)
 144                 yt = metadata[1]
 145             else:
 146                 raise ExtractorError('Unable to find embedded YouTube video.')
 147         video_id = YoutubeIE.extract_id(yt)
 148
 149         return {
 150             '_type': 'url_transparent',
 151             'id': video_id,
 152             'title': title,
 153             'description': description,
 154             'url': yt,
 155             'ie_key': 'Youtube',
 156         }