]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/tenplay.py
[vk] Extend _VALID_URL to handle biqle.ru (Closes #6179)
[youtube-dl] / youtube_dl / extractor / tenplay.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     int_or_none,
7     float_or_none,
8 )
9
10
11 class TenPlayIE(InfoExtractor):
12     _VALID_URL = r'https?://(?:www\.)?ten(play)?\.com\.au/.+'
13     _TEST = {
14         'url': 'http://tenplay.com.au/ten-insider/extra/season-2013/tenplay-tv-your-way',
15         'info_dict': {
16             'id': '2695695426001',
17             'ext': 'flv',
18             'title': 'TENplay: TV your way',
19             'description': 'Welcome to a new TV experience. Enjoy a taste of the TENplay benefits.',
20             'timestamp': 1380150606.889,
21             'upload_date': '20130925',
22             'uploader': 'TENplay',
23         },
24         'params': {
25             'skip_download': True,  # Requires rtmpdump
26         }
27     }
28
29     _video_fields = [
30         "id", "name", "shortDescription", "longDescription", "creationDate",
31         "publishedDate", "lastModifiedDate", "customFields", "videoStillURL",
32         "thumbnailURL", "referenceId", "length", "playsTotal",
33         "playsTrailingWeek", "renditions", "captioning", "startDate", "endDate"]
34
35     def _real_extract(self, url):
36         webpage = self._download_webpage(url, url)
37         video_id = self._html_search_regex(
38             r'videoID: "(\d+?)"', webpage, 'video_id')
39         api_token = self._html_search_regex(
40             r'apiToken: "([a-zA-Z0-9-_\.]+?)"', webpage, 'api_token')
41         title = self._html_search_regex(
42             r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>',
43             webpage, 'title')
44
45         json = self._download_json('https://api.brightcove.com/services/library?command=find_video_by_id&video_id=%s&token=%s&video_fields=%s' % (video_id, api_token, ','.join(self._video_fields)), title)
46
47         formats = []
48         for rendition in json['renditions']:
49             url = rendition['remoteUrl'] or rendition['url']
50             protocol = 'rtmp' if url.startswith('rtmp') else 'http'
51             ext = 'flv' if protocol == 'rtmp' else rendition['videoContainer'].lower()
52
53             if protocol == 'rtmp':
54                 url = url.replace('&mp4:', '')
55
56                 tbr = int_or_none(rendition.get('encodingRate'), 1000)
57
58             formats.append({
59                 'format_id': '_'.join(
60                     ['rtmp', rendition['videoContainer'].lower(),
61                      rendition['videoCodec'].lower(), '%sk' % tbr]),
62                 'width': int_or_none(rendition['frameWidth']),
63                 'height': int_or_none(rendition['frameHeight']),
64                 'tbr': tbr,
65                 'filesize': int_or_none(rendition['size']),
66                 'protocol': protocol,
67                 'ext': ext,
68                 'vcodec': rendition['videoCodec'].lower(),
69                 'container': rendition['videoContainer'].lower(),
70                 'url': url,
71             })
72         self._sort_formats(formats)
73
74         return {
75             'id': video_id,
76             'display_id': json['referenceId'],
77             'title': json['name'],
78             'description': json['shortDescription'] or json['longDescription'],
79             'formats': formats,
80             'thumbnails': [{
81                 'url': json['videoStillURL']
82             }, {
83                 'url': json['thumbnailURL']
84             }],
85             'thumbnail': json['videoStillURL'],
86             'duration': float_or_none(json.get('length'), 1000),
87             'timestamp': float_or_none(json.get('creationDate'), 1000),
88             'uploader': json.get('customFields', {}).get('production_company_distributor') or 'TENplay',
89             'view_count': int_or_none(json.get('playsTotal')),
90         }