]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/adobetv.py
[qqmusic] Add support for playlists
[youtube-dl] / youtube_dl / extractor / adobetv.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5     parse_duration,
6     unified_strdate,
7     str_to_int,
8 )
9
10
11 class AdobeTVIE(InfoExtractor):
12     _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
13
14     _TEST = {
15         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
16         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
17         'info_dict': {
18             'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
19             'ext': 'mp4',
20             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
21             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
22             'thumbnail': 're:https?://.*\.jpg$',
23             'upload_date': '20110914',
24             'duration': 60,
25             'view_count': int,
26         },
27     }
28
29     def _real_extract(self, url):
30         video_id = self._match_id(url)
31         webpage = self._download_webpage(url, video_id)
32
33         player = self._parse_json(
34             self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
35             video_id)
36
37         title = player.get('title') or self._search_regex(
38             r'data-title="([^"]+)"', webpage, 'title')
39         description = self._og_search_description(webpage)
40         thumbnail = self._og_search_thumbnail(webpage)
41
42         upload_date = unified_strdate(
43             self._html_search_meta('datepublished', webpage, 'upload date'))
44
45         duration = parse_duration(
46             self._html_search_meta('duration', webpage, 'duration') or
47             self._search_regex(
48                 r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
49                 webpage, 'duration', fatal=False))
50
51         view_count = str_to_int(self._search_regex(
52             r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
53             webpage, 'view count'))
54
55         formats = [{
56             'url': source['src'],
57             'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
58             'tbr': source.get('bitrate'),
59         } for source in player['sources']]
60         self._sort_formats(formats)
61
62         return {
63             'id': video_id,
64             'title': title,
65             'description': description,
66             'thumbnail': thumbnail,
67             'upload_date': upload_date,
68             'duration': duration,
69             'view_count': view_count,
70             'formats': formats,
71         }