]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mit.py
Initiate new release.
[youtubedl] / 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': '00a3a27ee20d44bcaa0933ccec4a2cf7',
22 'info_dict': {
23 'id': '25418',
24 'ext': 'mp4',
25 'title': 'MIT DNA and Protein Sets',
26 'description': 'md5:46f5c69ce434f0a97e7c628cc142802d',
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._proto_relative_url(self._search_regex(
37 r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url'), 'http:')
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 OCWMITIE(InfoExtractor):
69 IE_NAME = 'ocw.mit.edu'
70 _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
71 _BASE_URL = 'http://ocw.mit.edu/'
72
73 _TESTS = [
74 {
75 '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/',
76 'info_dict': {
77 'id': 'EObHWIEKGjA',
78 'ext': 'webm',
79 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
80 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
81 'upload_date': '20121109',
82 'uploader_id': 'MIT',
83 'uploader': 'MIT OpenCourseWare',
84 }
85 },
86 {
87 '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/',
88 'info_dict': {
89 'id': '7K1sB05pE0A',
90 'ext': 'mp4',
91 'title': 'Session 1: Introduction to Derivatives',
92 'upload_date': '20090818',
93 'uploader_id': 'MIT',
94 'uploader': 'MIT OpenCourseWare',
95 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
96 }
97 }
98 ]
99
100 def _real_extract(self, url):
101 mobj = re.match(self._VALID_URL, url)
102 topic = mobj.group('topic')
103
104 webpage = self._download_webpage(url, topic)
105 title = self._html_search_meta('WT.cg_s', webpage)
106 description = self._html_search_meta('Description', webpage)
107
108 # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
109 embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
110 if embed_chapter_media:
111 metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
112 metadata = re.split(r', ?', metadata)
113 yt = metadata[1]
114 else:
115 # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
116 embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
117 if embed_media:
118 metadata = re.sub(r'[\'"]', '', embed_media.group(1))
119 metadata = re.split(r', ?', metadata)
120 yt = metadata[1]
121 else:
122 raise ExtractorError('Unable to find embedded YouTube video.')
123 video_id = YoutubeIE.extract_id(yt)
124
125 return {
126 '_type': 'url_transparent',
127 'id': video_id,
128 'title': title,
129 'description': description,
130 'url': yt,
131 'ie_key': 'Youtube',
132 }