from .common import InfoExtractor
from .youtube import YoutubeIE
-from ..compat import (
- compat_urlparse,
-)
from ..utils import (
clean_html,
ExtractorError,
_TEST = {
'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
- 'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
+ 'md5': '00a3a27ee20d44bcaa0933ccec4a2cf7',
'info_dict': {
'id': '25418',
'ext': 'mp4',
- 'title': 'MIT DNA Learning Center Set',
- 'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
+ 'title': 'MIT DNA and Protein Sets',
+ 'description': 'md5:46f5c69ce434f0a97e7c628cc142802d',
},
}
'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')
+ base_url = self._proto_relative_url(self._search_regex(
+ r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url'), 'http:')
formats_json = self._search_regex(
r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json)
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')
+ return self.url_result(embed_url)
class OCWMITIE(InfoExtractor):
'upload_date': '20121109',
'uploader_id': 'MIT',
'uploader': 'MIT OpenCourseWare',
- # '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'
}
},
{
'uploader_id': 'MIT',
'uploader': 'MIT OpenCourseWare',
'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
- # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
}
}
]
metadata = re.sub(r'[\'"]', '', 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)
metadata = re.sub(r'[\'"]', '', 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.')
video_id = YoutubeIE.extract_id(yt)
'title': title,
'description': description,
'url': yt,
- 'url_transparent'
- 'subtitles': subs,
'ie_key': 'Youtube',
}