]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/infoq.py
debian/control: Update list of extractors.
[youtubedl] / youtube_dl / extractor / infoq.py
1 import base64
2 import re
3
4 from .common import InfoExtractor
5 from ..utils import (
6 compat_urllib_parse,
7
8 ExtractorError,
9 )
10
11
12 class InfoQIE(InfoExtractor):
13 _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
14 _TEST = {
15 u"name": u"InfoQ",
16 u"url": u"http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
17 u"file": u"12-jan-pythonthings.mp4",
18 u"info_dict": {
19 u"description": u"Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
20 u"title": u"A Few of My Favorite [Python] Things"
21 },
22 u"params": {
23 u"skip_download": True
24 }
25 }
26
27 def _real_extract(self, url):
28 mobj = re.match(self._VALID_URL, url)
29
30 webpage = self._download_webpage(url, video_id=url)
31 self.report_extraction(url)
32
33 # Extract video URL
34 mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
35 if mobj is None:
36 raise ExtractorError(u'Unable to extract video url')
37 real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
38 video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
39
40 # Extract title
41 video_title = self._search_regex(r'contentTitle = "(.*?)";',
42 webpage, u'title')
43
44 # Extract description
45 video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
46 webpage, u'description', fatal=False)
47
48 video_filename = video_url.split('/')[-1]
49 video_id, extension = video_filename.split('.')
50
51 info = {
52 'id': video_id,
53 'url': video_url,
54 'uploader': None,
55 'upload_date': None,
56 'title': video_title,
57 'ext': extension, # Extension is always(?) mp4, but seems to be flv
58 'thumbnail': None,
59 'description': video_description,
60 }
61
62 return [info]