1 from __future__ import unicode_literals
5 from .common import InfoExtractor
11 class InfoQIE(InfoExtractor):
12 _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
15 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
16 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
18 'id': '12-jan-pythonthings',
20 'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
21 'title': 'A Few of My Favorite [Python] Things',
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27 webpage = self._download_webpage(url, video_id)
29 video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
30 video_description = self._html_search_meta('description', webpage, 'description')
32 # The server URL is hardcoded
33 video_url = 'rtmpe://video.infoq.com/cfx/st/'
36 encoded_id = self._search_regex(
37 r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
38 real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
39 playpath = 'mp4:' + real_id
41 video_filename = playpath.split('/')[-1]
42 video_id, extension = video_filename.split('.')
44 http_base = self._search_regex(
45 r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
52 'play_path': playpath,
55 'url': http_base + real_id,
57 self._sort_formats(formats)
62 'description': video_description,