]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/svt.py
48bc4529e6ae8a265a672c066ac59b388ea3a5d5
[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 _GEO_COUNTRIES = ['SE']
17
18 def _extract_video(self, video_info, video_id):
19 formats = []
20 for vr in video_info['videoReferences']:
21 player_type = vr.get('playerType') or vr.get('format')
22 vurl = vr['url']
23 ext = determine_ext(vurl)
24 if ext == 'm3u8':
25 formats.extend(self._extract_m3u8_formats(
26 vurl, video_id,
27 ext='mp4', entry_protocol='m3u8_native',
28 m3u8_id=player_type, fatal=False))
29 elif ext == 'f4m':
30 formats.extend(self._extract_f4m_formats(
31 vurl + '?hdcore=3.3.0', video_id,
32 f4m_id=player_type, fatal=False))
33 elif ext == 'mpd':
34 if player_type == 'dashhbbtv':
35 formats.extend(self._extract_mpd_formats(
36 vurl, video_id, mpd_id=player_type, fatal=False))
37 else:
38 formats.append({
39 'format_id': player_type,
40 'url': vurl,
41 })
42 if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
43 self.raise_geo_restricted(
44 'This video is only available in Sweden',
45 countries=self._GEO_COUNTRIES)
46 self._sort_formats(formats)
47
48 subtitles = {}
49 subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences'))
50 if isinstance(subtitle_references, list):
51 for sr in subtitle_references:
52 subtitle_url = sr.get('url')
53 subtitle_lang = sr.get('language', 'sv')
54 if subtitle_url:
55 if determine_ext(subtitle_url) == 'm3u8':
56 # TODO(yan12125): handle WebVTT in m3u8 manifests
57 continue
58
59 subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url})
60
61 title = video_info.get('title')
62
63 series = video_info.get('programTitle')
64 season_number = int_or_none(video_info.get('season'))
65 episode = video_info.get('episodeTitle')
66 episode_number = int_or_none(video_info.get('episodeNumber'))
67
68 duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
69 age_limit = None
70 adult = dict_get(
71 video_info, ('inappropriateForChildren', 'blockedForChildren'),
72 skip_false_values=False)
73 if adult is not None:
74 age_limit = 18 if adult else 0
75
76 return {
77 'id': video_id,
78 'title': title,
79 'formats': formats,
80 'subtitles': subtitles,
81 'duration': duration,
82 'age_limit': age_limit,
83 'series': series,
84 'season_number': season_number,
85 'episode': episode,
86 'episode_number': episode_number,
87 }
88
89
90 class SVTIE(SVTBaseIE):
91 _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
92 _TEST = {
93 'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
94 'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
95 'info_dict': {
96 'id': '2900353',
97 'ext': 'mp4',
98 'title': 'Stjärnorna skojar till det - under SVT-intervjun',
99 'duration': 27,
100 'age_limit': 0,
101 },
102 }
103
104 @staticmethod
105 def _extract_url(webpage):
106 mobj = re.search(
107 r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
108 if mobj:
109 return mobj.group('url')
110
111 def _real_extract(self, url):
112 mobj = re.match(self._VALID_URL, url)
113 widget_id = mobj.group('widget_id')
114 article_id = mobj.group('id')
115
116 info = self._download_json(
117 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
118 article_id)
119
120 info_dict = self._extract_video(info['video'], article_id)
121 info_dict['title'] = info['context']['title']
122 return info_dict
123
124
125 class SVTPlayIE(SVTBaseIE):
126 IE_DESC = 'SVT Play and Öppet arkiv'
127 _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp)/(?P<id>[0-9]+)'
128 _TESTS = [{
129 'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
130 'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
131 'info_dict': {
132 'id': '5996901',
133 'ext': 'mp4',
134 'title': 'Flygplan till Haile Selassie',
135 'duration': 3527,
136 'thumbnail': r're:^https?://.*[\.-]jpg$',
137 'age_limit': 0,
138 'subtitles': {
139 'sv': [{
140 'ext': 'wsrt',
141 }]
142 },
143 },
144 }, {
145 # geo restricted to Sweden
146 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
147 'only_matching': True,
148 }, {
149 'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
150 'only_matching': True,
151 }]
152
153 def _real_extract(self, url):
154 video_id = self._match_id(url)
155
156 webpage = self._download_webpage(url, video_id)
157
158 data = self._parse_json(
159 self._search_regex(
160 r'root\["__svtplay"\]\s*=\s*([^;]+);',
161 webpage, 'embedded data', default='{}'),
162 video_id, fatal=False)
163
164 thumbnail = self._og_search_thumbnail(webpage)
165
166 if data:
167 video_info = try_get(
168 data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
169 dict)
170 if video_info:
171 info_dict = self._extract_video(video_info, video_id)
172 info_dict.update({
173 'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
174 'thumbnail': thumbnail,
175 })
176 return info_dict
177
178 video_id = self._search_regex(
179 r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
180 webpage, 'video id', default=None)
181
182 if video_id:
183 data = self._download_json(
184 'https://api.svt.se/videoplayer-api/video/%s' % video_id,
185 video_id, headers=self.geo_verification_headers())
186 info_dict = self._extract_video(data, video_id)
187 if not info_dict.get('title'):
188 info_dict['title'] = re.sub(
189 r'\s*\|\s*.+?$', '',
190 info_dict.get('episode') or self._og_search_title(webpage))
191 return info_dict