]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/watchbox.py
New upstream version 2018.04.25
[youtubedl] / youtube_dl / extractor / watchbox.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_str
8 from ..utils import (
9 int_or_none,
10 js_to_json,
11 strip_or_none,
12 try_get,
13 unified_timestamp,
14 )
15
16
17 class WatchBoxIE(InfoExtractor):
18 _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
19 _TESTS = [{
20 # film
21 'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
22 'info_dict': {
23 'id': '341368',
24 'ext': 'mp4',
25 'title': 'Free Jimmy',
26 'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
27 'thumbnail': r're:^https?://.*\.jpg$',
28 'duration': 4890,
29 'age_limit': 16,
30 'release_year': 2009,
31 },
32 'params': {
33 'format': 'bestvideo',
34 'skip_download': True,
35 },
36 'expected_warnings': ['Failed to download m3u8 information'],
37 }, {
38 # episode
39 'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
40 'info_dict': {
41 'id': '328286',
42 'ext': 'mp4',
43 'title': 'S01 E01 - Date in der Hölle',
44 'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
45 'thumbnail': r're:^https?://.*\.jpg$',
46 'duration': 1291,
47 'age_limit': 12,
48 'release_year': 2010,
49 'series': 'Ugly Americans',
50 'season_number': 1,
51 'episode': 'Date in der Hölle',
52 'episode_number': 1,
53 },
54 'params': {
55 'format': 'bestvideo',
56 'skip_download': True,
57 },
58 'expected_warnings': ['Failed to download m3u8 information'],
59 }, {
60 'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
61 'only_matching': True,
62 }]
63
64 def _real_extract(self, url):
65 mobj = re.match(self._VALID_URL, url)
66 kind, video_id = mobj.group('kind', 'id')
67
68 webpage = self._download_webpage(url, video_id)
69
70 source = self._parse_json(
71 self._search_regex(
72 r'(?s)source\s*:\s*({.+?})\s*,\s*\n', webpage, 'source',
73 default='{}'),
74 video_id, transform_source=js_to_json, fatal=False) or {}
75
76 video_id = compat_str(source.get('videoId') or video_id)
77
78 devapi = self._download_json(
79 'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
80 'format': 'json',
81 'apikey': 'hbbtv',
82 }, fatal=False)
83
84 item = try_get(devapi, lambda x: x['items'][0], dict) or {}
85
86 title = item.get('title') or try_get(
87 item, lambda x: x['movie']['headline_movie'],
88 compat_str) or source['title']
89
90 formats = []
91 hls_url = item.get('media_videourl_hls') or source.get('hls')
92 if hls_url:
93 formats.extend(self._extract_m3u8_formats(
94 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
95 m3u8_id='hls', fatal=False))
96 dash_url = item.get('media_videourl_wv') or source.get('dash')
97 if dash_url:
98 formats.extend(self._extract_mpd_formats(
99 dash_url, video_id, mpd_id='dash', fatal=False))
100 mp4_url = item.get('media_videourl')
101 if mp4_url:
102 formats.append({
103 'url': mp4_url,
104 'format_id': 'mp4',
105 'width': int_or_none(item.get('width')),
106 'height': int_or_none(item.get('height')),
107 'tbr': int_or_none(item.get('bitrate')),
108 })
109 self._sort_formats(formats)
110
111 description = strip_or_none(item.get('descr'))
112 thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
113 duration = int_or_none(item.get('media_length') or source.get('length'))
114 timestamp = unified_timestamp(item.get('pubDate'))
115 view_count = int_or_none(item.get('media_views'))
116 age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
117 release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
118
119 info = {
120 'id': video_id,
121 'title': title,
122 'description': description,
123 'thumbnail': thumbnail,
124 'duration': duration,
125 'timestamp': timestamp,
126 'view_count': view_count,
127 'age_limit': age_limit,
128 'release_year': release_year,
129 'formats': formats,
130 }
131
132 if kind.lower() == 'serien':
133 series = try_get(
134 item, lambda x: x['special']['title'],
135 compat_str) or source.get('format')
136 season_number = int_or_none(self._search_regex(
137 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
138 default=None) or self._search_regex(
139 r'/staffel-(\d+)/', url, 'season number', default=None))
140 episode = source.get('title')
141 episode_number = int_or_none(self._search_regex(
142 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
143 default=None))
144 info.update({
145 'series': series,
146 'season_number': season_number,
147 'episode': episode,
148 'episode_number': episode_number,
149 })
150
151 return info