[streamcz] Update extractor
[youtube-dl] / youtube_dl / extractor / streamcz.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 import re
5 import json
6
7 from .common import InfoExtractor
8 from ..compat import (
9     compat_str,
10 )
11 from ..utils import (
12     int_or_none,
13 )
14
15
16 class StreamCZIE(InfoExtractor):
17     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)'
18
19     _TESTS = [{
20         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
21         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
22         'info_dict': {
23             'id': '765767',
24             'ext': 'mp4',
25             'title': 'Peklo na talíři: Éčka pro děti',
26             'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE',
27             'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
28             'duration': 256,
29         },
30     }, {
31         'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
32         'md5': 'e54a254fb8b871968fd8403255f28589',
33         'info_dict': {
34             'id': '10002447',
35             'ext': 'mp4',
36             'title': 'Kancelář Blaník: Tři roky pro Mazánka',
37             'description': 'md5:3862a00ba7bf0b3e44806b544032c859',
38             'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000',
39             'duration': 368,
40         },
41     }]
42
43     def _real_extract(self, url):
44         video_id = self._match_id(url)
45         data = self._download_json(
46             'http://www.stream.cz/API/episode/%s' % video_id, video_id)
47
48         formats = []
49         for quality, video in enumerate(data['video_qualities']):
50             for f in video['formats']:
51                 typ = f['type'].partition('/')[2]
52                 qlabel = video.get('quality_label')
53                 formats.append({
54                     'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ,
55                     'format_id': '%s-%s' % (typ, f['quality']),
56                     'url': f['source'],
57                     'height': int_or_none(f['quality'].rstrip('p')),
58                     'quality': quality,
59                 })
60         self._sort_formats(formats)
61
62         image = data.get('image')
63         if image:
64             thumbnail = self._proto_relative_url(
65                 image.replace('{width}', '1240').replace('{height}', '697'),
66                 scheme='http:',
67             )
68         else:
69             thumbnail = None
70
71         stream = data.get('_embedded', {}).get('stream:show', {}).get('name')
72         if stream:
73             title = '%s: %s' % (stream, data['name'])
74         else:
75             title = data['name']
76
77         return {
78             'id': video_id,
79             'title': title,
80             'thumbnail': thumbnail,
81             'formats': formats,
82             'description': data.get('web_site_text'),
83             'duration': int_or_none(data.get('duration')),
84             'view_count': int_or_none(data.get('views')),
85         }