1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
|
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
clean_html,
get_element_by_id,
)
class TechTVMITIE(InfoExtractor):
IE_NAME = 'techtv.mit.edu'
_VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
_TEST = {
'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
'info_dict': {
'id': '25418',
'ext': 'mp4',
'title': 'MIT DNA Learning Center Set',
'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
raw_page = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
base_url = self._search_regex(
r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
formats_json = self._search_regex(
r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json)
formats = [
{
'format_id': f['label'],
'url': base_url + f['url'].partition(':')[2],
'ext': f['url'].partition(':')[0],
'format': f['label'],
'width': f['width'],
'vbr': f['bitrate'],
}
for f in formats_mit
]
title = get_element_by_id('edit-title', clean_page)
description = clean_html(get_element_by_id('edit-description', clean_page))
thumbnail = self._search_regex(
r'playlist:.*?url: \'(.+?)\'',
raw_page, 'thumbnail', flags=re.DOTALL)
return {
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
}
class MITIE(TechTVMITIE):
IE_NAME = 'video.mit.edu'
_VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
_TEST = {
'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
'file': '.mp4',
'md5': '7db01d5ccc1895fc5010e9c9e13648da',
'info_dict': {
'id': '21783',
'ext': 'mp4',
'title': 'The Government is Profiling You',
'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
embed_url = self._search_regex(
r'<iframe .*?src="(.+?)"', webpage, 'embed url')
return self.url_result(embed_url, ie='TechTVMIT')
class OCWMITIE(InfoExtractor):
IE_NAME = u'ocw.mit.edu'
_VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
_BASE_URL = u'http://ocw.mit.edu/'
_TESTS = [
{
u'url': u'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/',
u'md5': u'348bef727b573c0bd9ad8a7c08c89ebd',
u'info_dict': {
u'title': u'7. Discrete Random Variables III',
u'description': u'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
u'subtitles': u'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'
}
},
{
u'url': u'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/',
u'md5': u'f4a434f08f15e581eb67cec0b57bcf6f',
u'info_dict': {
u'title': u'Lec 1 _ MIT 18.01 Single Variable Calculus, Fall 2007',
u'subtitles': u'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
}
}
]
def _real_extract(self, url):
webpage = self._download_webpage(url, self.IE_NAME)
title = self._html_search_meta(u'WT.cg_s', webpage)
description = self._html_search_meta(u'Description', webpage)
# search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
if embed_chapter_media:
metadata = re.sub(r'[\'"]', u'', embed_chapter_media.group(1))
metadata = re.split(r', ?', metadata)
yt = metadata[1]
subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
else:
# search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
if embed_media:
metadata = re.sub(r'[\'"]', u'', embed_media.group(1))
metadata = re.split(r', ?', metadata)
yt = metadata[1]
subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
else:
raise ExtractorError('Unable to find embedded YouTube video.')
data = self.url_result(yt, 'Youtube')
data['subtitles'] = subs
return data
|
