]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/svt.py
1c04dfb7bf757477d134cc7caa223ab47d0800ba
[youtubedl] / youtube_dl / extractor / svt.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 (
8 determine_ext,
9 dict_get,
10 int_or_none,
11 try_get,
12 )
13
14
15 class SVTBaseIE(InfoExtractor):
16 def _extract_video(self, video_info, video_id):
17 formats = []
18 for vr in video_info['videoReferences']:
19 player_type = vr.get('playerType')
20 vurl = vr['url']
21 ext = determine_ext(vurl)
22 if ext == 'm3u8':
23 formats.extend(self._extract_m3u8_formats(
24 vurl, video_id,
25 ext='mp4', entry_protocol='m3u8_native',
26 m3u8_id=player_type, fatal=False))
27 elif ext == 'f4m':
28 formats.extend(self._extract_f4m_formats(
29 vurl + '?hdcore=3.3.0', video_id,
30 f4m_id=player_type, fatal=False))
31 elif ext == 'mpd':
32 if player_type == 'dashhbbtv':
33 formats.extend(self._extract_mpd_formats(
34 vurl, video_id, mpd_id=player_type, fatal=False))
35 else:
36 formats.append({
37 'format_id': player_type,
38 'url': vurl,
39 })
40 if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
41 self.raise_geo_restricted('This video is only available in Sweden')
42 self._sort_formats(formats)
43
44 subtitles = {}
45 subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences'))
46 if isinstance(subtitle_references, list):
47 for sr in subtitle_references:
48 subtitle_url = sr.get('url')
49 subtitle_lang = sr.get('language', 'sv')
50 if subtitle_url:
51 if determine_ext(subtitle_url) == 'm3u8':
52 # TODO(yan12125): handle WebVTT in m3u8 manifests
53 continue
54
55 subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url})
56
57 title = video_info.get('title')
58
59 series = video_info.get('programTitle')
60 season_number = int_or_none(video_info.get('season'))
61 episode = video_info.get('episodeTitle')
62 episode_number = int_or_none(video_info.get('episodeNumber'))
63
64 duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
65 age_limit = None
66 adult = dict_get(
67 video_info, ('inappropriateForChildren', 'blockedForChildren'),
68 skip_false_values=False)
69 if adult is not None:
70 age_limit = 18 if adult else 0
71
72 return {
73 'id': video_id,
74 'title': title,
75 'formats': formats,
76 'subtitles': subtitles,
77 'duration': duration,
78 'age_limit': age_limit,
79 'series': series,
80 'season_number': season_number,
81 'episode': episode,
82 'episode_number': episode_number,
83 }
84
85
86 class SVTIE(SVTBaseIE):
87 _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
88 _TEST = {
89 'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
90 'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
91 'info_dict': {
92 'id': '2900353',
93 'ext': 'mp4',
94 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
95 'duration': 27,
96 'age_limit': 0,
97 },
98 }
99
100 @staticmethod
101 def _extract_url(webpage):
102 mobj = re.search(
103 r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
104 if mobj:
105 return mobj.group('url')
106
107 def _real_extract(self, url):
108 mobj = re.match(self._VALID_URL, url)
109 widget_id = mobj.group('widget_id')
110 article_id = mobj.group('id')
111
112 info = self._download_json(
113 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
114 article_id)
115
116 info_dict = self._extract_video(info['video'], article_id)
117 info_dict['title'] = info['context']['title']
118 return info_dict
119
120
121 class SVTPlayIE(SVTBaseIE):
122 IE_DESC = 'SVT Play and Öppet arkiv'
123 _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp)/(?P<id>[0-9]+)'
124 _TESTS = [{
125 'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
126 'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
127 'info_dict': {
128 'id': '5996901',
129 'ext': 'mp4',
130 'title': 'Flygplan till Haile Selassie',
131 'duration': 3527,
132 'thumbnail': 're:^https?://.*[\.-]jpg$',
133 'age_limit': 0,
134 'subtitles': {
135 'sv': [{
136 'ext': 'wsrt',
137 }]
138 },
139 },
140 }, {
141 # geo restricted to Sweden
142 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
143 'only_matching': True,
144 }, {
145 'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
146 'only_matching': True,
147 }]
148
149 def _real_extract(self, url):
150 video_id = self._match_id(url)
151
152 webpage = self._download_webpage(url, video_id)
153
154 data = self._parse_json(
155 self._search_regex(
156 r'root\["__svtplay"\]\s*=\s*([^;]+);',
157 webpage, 'embedded data', default='{}'),
158 video_id, fatal=False)
159
160 thumbnail = self._og_search_thumbnail(webpage)
161
162 if data:
163 video_info = try_get(
164 data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
165 dict)
166 if video_info:
167 info_dict = self._extract_video(video_info, video_id)
168 info_dict.update({
169 'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
170 'thumbnail': thumbnail,
171 })
172 return info_dict
173
174 video_id = self._search_regex(
175 r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
176 webpage, 'video id', default=None)
177
178 if video_id:
179 data = self._download_json(
180 'http://www.svt.se/videoplayer-api/video/%s' % video_id, video_id)
181 info_dict = self._extract_video(data, video_id)
182 if not info_dict.get('title'):
183 info_dict['title'] = re.sub(
184 r'\s*\|\s*.+?$', '',
185 info_dict.get('episode') or self._og_search_title(webpage))
186 return info_dict