]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/infoq.py
f25f43664e262b25473557c5f11dae91e697e3f6
[youtubedl] / youtube_dl / extractor / infoq.py
1 from __future__ import unicode_literals
2
3 import base64
4
5 from .common import InfoExtractor
6 from ..compat import (
7 compat_urllib_parse,
8 )
9
10
11 class InfoQIE(InfoExtractor):
12 _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
13
14 _TEST = {
15 'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
16 'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
17 'info_dict': {
18 'id': '12-jan-pythonthings',
19 'ext': 'mp4',
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',
22 },
23 }
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27 webpage = self._download_webpage(url, video_id)
28
29 video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
30 video_description = self._html_search_meta('description', webpage, 'description')
31
32 # The server URL is hardcoded
33 video_url = 'rtmpe://video.infoq.com/cfx/st/'
34
35 # Extract video URL
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
40
41 video_filename = playpath.split('/')[-1]
42 video_id, extension = video_filename.split('.')
43
44 http_base = self._search_regex(
45 r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
46 'HTTP base URL')
47
48 formats = [{
49 'format_id': 'rtmp',
50 'url': video_url,
51 'ext': extension,
52 'play_path': playpath,
53 }, {
54 'format_id': 'http',
55 'url': http_base + real_id,
56 }]
57 self._sort_formats(formats)
58
59 return {
60 'id': video_id,
61 'title': video_title,
62 'description': video_description,
63 'formats': formats,
64 }