]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ctvnews.py
debian/copyright: use spaces rather than tabs to start continuation lines.
[youtubedl] / youtube_dl / extractor / ctvnews.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import orderedSet
8
9
10 class CTVNewsIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
12 _TESTS = [{
13 'url': 'http://www.ctvnews.ca/video?clipId=901995',
14 'md5': '9b8624ba66351a23e0b6e1391971f9af',
15 'info_dict': {
16 'id': '901995',
17 'ext': 'flv',
18 'title': 'Extended: \'That person cannot be me\' Johnson says',
19 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
20 'timestamp': 1467286284,
21 'upload_date': '20160630',
22 }
23 }, {
24 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
25 'info_dict':
26 {
27 'id': '1.2966224',
28 },
29 'playlist_mincount': 19,
30 }, {
31 'url': 'http://www.ctvnews.ca/video?binId=1.2876780',
32 'info_dict':
33 {
34 'id': '1.2876780',
35 },
36 'playlist_mincount': 100,
37 }, {
38 'url': 'http://www.ctvnews.ca/1.810401',
39 'only_matching': True,
40 }, {
41 'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231',
42 'only_matching': True,
43 }, {
44 'url': 'http://vancouverisland.ctvnews.ca/video?clipId=761241',
45 'only_matching': True,
46 }]
47
48 def _real_extract(self, url):
49 page_id = self._match_id(url)
50
51 def ninecninemedia_url_result(clip_id):
52 return {
53 '_type': 'url_transparent',
54 'id': clip_id,
55 'url': '9c9media:ctvnews_web:%s' % clip_id,
56 'ie_key': 'NineCNineMedia',
57 }
58
59 if page_id.isdigit():
60 return ninecninemedia_url_result(page_id)
61 else:
62 webpage = self._download_webpage('http://www.ctvnews.ca/%s' % page_id, page_id, query={
63 'ot': 'example.AjaxPageLayout.ot',
64 'maxItemsPerPage': 1000000,
65 })
66 entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
67 re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
68 return self.playlist_result(entries, page_id)