1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from .youtube
import YoutubeIE
15 class TechTVMITIE(InfoExtractor
):
16 IE_NAME
= 'techtv.mit.edu'
17 _VALID_URL
= r
'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
20 'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
21 'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
25 'title': 'MIT DNA Learning Center Set',
26 'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
30 def _real_extract(self
, url
):
31 mobj
= re
.match(self
._VALID
_URL
, url
)
32 video_id
= mobj
.group('id')
33 raw_page
= self
._download
_webpage
(
34 'http://techtv.mit.edu/videos/%s' % video_id
, video_id
)
35 clean_page
= re
.compile(r
'<!--.*?-->', re
.S
).sub('', raw_page
)
37 base_url
= self
._search
_regex
(
38 r
'ipadUrl: \'(.+?cloudfront
.net
/)', raw_page, 'base url
')
39 formats_json = self._search_regex(
40 r'bitrates
: (\
[.+?\
])', raw_page, 'video formats
')
41 formats_mit = json.loads(formats_json)
44 'format_id
': f['label
'],
45 'url
': base_url + f['url
'].partition(':')[2],
46 'ext
': f['url
'].partition(':')[0],
54 title = get_element_by_id('edit
-title
', clean_page)
55 description = clean_html(get_element_by_id('edit
-description
', clean_page))
56 thumbnail = self._search_regex(
57 r'playlist
:.*?url
: \'(.+?
)\'',
58 raw_page, 'thumbnail
', flags=re.DOTALL)
64 'description
': description,
65 'thumbnail
': thumbnail,
69 class MITIE(TechTVMITIE):
70 IE_NAME = 'video
.mit
.edu
'
71 _VALID_URL = r'https?
://video\
.mit\
.edu
/watch
/(?P
<title
>[^
/]+)'
74 'url
': 'http
://video
.mit
.edu
/watch
/the
-government
-is-profiling
-you
-13222/',
76 'md5
': '7db01d5ccc1895fc5010e9c9e13648da
',
80 'title
': 'The Government
is Profiling You
',
81 'description
': 'md5
:ad5795fe1e1623b73620dbfd47df9afd
',
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
')
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
/'
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
/',
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
'
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
/',
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
'
122 def _real_extract(self, url):
123 mobj = re.match(self._VALID_URL, url)
124 topic = mobj.group('topic
')
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)
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)
136 subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
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)
141 metadata = re.sub(r'[\'"]', '', embed_media.group(1))
142 metadata = re.split(r', ?
', metadata)
144 subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
146 raise ExtractorError('Unable to find embedded YouTube video
.')
147 video_id = YoutubeIE.extract_id(yt)
150 '_type
': 'url_transparent
',
153 'description
': description,