youtube-dl/youtube_dl/extractor/infoq.py

72 lines
2.6 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 12:14:19 -07:00
import base64
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
2013-06-23 12:14:19 -07:00
class InfoQIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
2014-04-19 16:01:37 -07:00
_TESTS = [{
2014-04-20 17:55:35 -07:00
'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
2014-04-20 17:55:35 -07:00
'info_dict': {
'id': '12-jan-pythonthings',
'ext': 'mp4',
'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
'title': 'A Few of My Favorite [Python] Things',
2013-06-27 11:27:08 -07:00
},
}, {
'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
'only_matching': True,
}]
2013-06-23 12:14:19 -07:00
def _real_extract(self, url):
video_id = self._match_id(url)
2014-02-02 03:03:36 -08:00
webpage = self._download_webpage(url, video_id)
2013-06-23 12:14:19 -07:00
2014-04-19 16:01:37 -07:00
video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
video_description = self._html_search_meta('description', webpage, 'description')
2013-06-23 12:14:19 -07:00
2014-04-19 16:10:30 -07:00
# The server URL is hardcoded
2014-04-19 16:01:37 -07:00
video_url = 'rtmpe://video.infoq.com/cfx/st/'
2014-04-19 16:10:30 -07:00
# Extract video URL
encoded_id = self._search_regex(
r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
2014-04-19 16:10:30 -07:00
playpath = 'mp4:' + real_id
2013-06-23 12:14:19 -07:00
2014-04-19 16:01:37 -07:00
video_filename = playpath.split('/')[-1]
2013-06-23 12:14:19 -07:00
video_id, extension = video_filename.split('.')
http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
formats = [{
'format_id': 'rtmp',
'url': video_url,
'ext': extension,
'play_path': playpath,
}, {
'format_id': 'http',
'url': http_video_url,
'http_headers': {
'Cookie': 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
policy, signature, key_pair_id),
},
}]
self._sort_formats(formats)
2014-04-20 17:55:35 -07:00
return {
2013-06-23 12:14:19 -07:00
'id': video_id,
'title': video_title,
'description': video_description,
'formats': formats,
2014-04-20 17:55:35 -07:00
}