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