78787e8f1cbb067527bd56e3167a921a3541e6d9
[ytdl] / 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         video_id = self._match_id(url)
35         raw_page = self._download_webpage(
36             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
37         clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
38
39         base_url = self._search_regex(
40             r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
41         formats_json = self._search_regex(
42             r'bitrates: (\[.+?\])', raw_page, 'video formats')
43         formats_mit = json.loads(formats_json)
44         formats = [
45             {
46                 'format_id': f['label'],
47                 'url': base_url + f['url'].partition(':')[2],
48                 'ext': f['url'].partition(':')[0],
49                 'format': f['label'],
50                 'width': f['width'],
51                 'vbr': f['bitrate'],
52             }
53             for f in formats_mit
54         ]
55
56         title = get_element_by_id('edit-title', clean_page)
57         description = clean_html(get_element_by_id('edit-description', clean_page))
58         thumbnail = self._search_regex(
59             r'playlist:.*?url: \'(.+?)\'',
60             raw_page, 'thumbnail', flags=re.DOTALL)
61
62         return {
63             'id': video_id,
64             'title': title,
65             'formats': formats,
66             'description': description,
67             'thumbnail': thumbnail,
68         }
69
70
71 class MITIE(TechTVMITIE):
72     IE_NAME = 'video.mit.edu'
73     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
74
75     _TEST = {
76         'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
77         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
78         'info_dict': {
79             'id': '21783',
80             'ext': 'mp4',
81             'title': 'The Government is Profiling You',
82             'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
83         },
84     }
85
86     def _real_extract(self, url):
87         mobj = re.match(self._VALID_URL, url)
88         page_title = mobj.group('title')
89         webpage = self._download_webpage(url, page_title)
90         embed_url = self._search_regex(
91             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
92         return self.url_result(embed_url, ie='TechTVMIT')
93
94
95 class OCWMITIE(InfoExtractor):
96     IE_NAME = 'ocw.mit.edu'
97     _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
98     _BASE_URL = 'http://ocw.mit.edu/'
99
100     _TESTS = [
101         {
102             '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/',
103             'info_dict': {
104                 'id': 'EObHWIEKGjA',
105                 'ext': 'mp4',
106                 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
107                 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
108                 # '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'
109             }
110         },
111         {
112             '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/',
113             'info_dict': {
114                 'id': '7K1sB05pE0A',
115                 'ext': 'mp4',
116                 'title': 'Session 1: Introduction to Derivatives',
117                 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
118                 # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
119             }
120         }
121     ]
122
123     def _real_extract(self, url):
124         mobj = re.match(self._VALID_URL, url)
125         topic = mobj.group('topic')
126
127         webpage = self._download_webpage(url, topic)
128         title = self._html_search_meta('WT.cg_s', webpage)
129         description = self._html_search_meta('Description', webpage)
130
131         # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
132         embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
133         if embed_chapter_media:
134             metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
135             metadata = re.split(r', ?', metadata)
136             yt = metadata[1]
137             subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
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                 subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
146             else:
147                 raise ExtractorError('Unable to find embedded YouTube video.')
148         video_id = YoutubeIE.extract_id(yt)
149
150         return {
151             '_type': 'url_transparent',
152             'id': video_id,
153             'title': title,
154             'description': description,
155             'url': yt,
156             'url_transparent'
157             'subtitles': subs,
158             'ie_key': 'Youtube',
159         }