]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtv.py
New upstream version 2019.01.16
[youtubedl] / youtube_dl / extractor / drtv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6 ExtractorError,
7 int_or_none,
8 float_or_none,
9 mimetype2ext,
10 parse_iso8601,
11 remove_end,
12 update_url_query,
13 )
14
15
16 class DRTVIE(InfoExtractor):
17 _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
18 _GEO_BYPASS = False
19 _GEO_COUNTRIES = ['DK']
20 IE_NAME = 'drtv'
21 _TESTS = [{
22 'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
23 'md5': '7ae17b4e18eb5d29212f424a7511c184',
24 'info_dict': {
25 'id': 'klassen-darlig-taber-10',
26 'ext': 'mp4',
27 'title': 'Klassen - Dårlig taber (10)',
28 'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
29 'timestamp': 1471991907,
30 'upload_date': '20160823',
31 'duration': 606.84,
32 },
33 }, {
34 # embed
35 'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
36 'info_dict': {
37 'id': 'christiania-pusher-street-ryddes-drdkrjpo',
38 'ext': 'mp4',
39 'title': 'LIVE Christianias rydning af Pusher Street er i gang',
40 'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
41 'timestamp': 1472800279,
42 'upload_date': '20160902',
43 'duration': 131.4,
44 },
45 'params': {
46 'skip_download': True,
47 },
48 }, {
49 # with SignLanguage formats
50 'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
51 'info_dict': {
52 'id': 'historien-om-danmark-stenalder',
53 'ext': 'mp4',
54 'title': 'Historien om Danmark: Stenalder (1)',
55 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
56 'timestamp': 1490401996,
57 'upload_date': '20170325',
58 'duration': 3502.04,
59 'formats': 'mincount:20',
60 },
61 'params': {
62 'skip_download': True,
63 },
64 }]
65
66 def _real_extract(self, url):
67 video_id = self._match_id(url)
68
69 webpage = self._download_webpage(url, video_id)
70
71 if '>Programmet er ikke længere tilgængeligt' in webpage:
72 raise ExtractorError(
73 'Video %s is not available' % video_id, expected=True)
74
75 video_id = self._search_regex(
76 (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
77 r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
78 webpage, 'video id')
79
80 programcard = self._download_json(
81 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
82 video_id, 'Downloading video JSON')
83 data = programcard['Data'][0]
84
85 title = remove_end(self._og_search_title(
86 webpage, default=None), ' | TV | DR') or data['Title']
87 description = self._og_search_description(
88 webpage, default=None) or data.get('Description')
89
90 timestamp = parse_iso8601(data.get('CreatedTime'))
91
92 thumbnail = None
93 duration = None
94
95 restricted_to_denmark = False
96
97 formats = []
98 subtitles = {}
99
100 for asset in data['Assets']:
101 kind = asset.get('Kind')
102 if kind == 'Image':
103 thumbnail = asset.get('Uri')
104 elif kind in ('VideoResource', 'AudioResource'):
105 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
106 restricted_to_denmark = asset.get('RestrictedToDenmark')
107 asset_target = asset.get('Target')
108 for link in asset.get('Links', []):
109 uri = link.get('Uri')
110 if not uri:
111 continue
112 target = link.get('Target')
113 format_id = target or ''
114 preference = None
115 if asset_target in ('SpokenSubtitles', 'SignLanguage'):
116 preference = -1
117 format_id += '-%s' % asset_target
118 if target == 'HDS':
119 f4m_formats = self._extract_f4m_formats(
120 uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
121 video_id, preference, f4m_id=format_id, fatal=False)
122 if kind == 'AudioResource':
123 for f in f4m_formats:
124 f['vcodec'] = 'none'
125 formats.extend(f4m_formats)
126 elif target == 'HLS':
127 formats.extend(self._extract_m3u8_formats(
128 uri, video_id, 'mp4', entry_protocol='m3u8_native',
129 preference=preference, m3u8_id=format_id,
130 fatal=False))
131 else:
132 bitrate = link.get('Bitrate')
133 if bitrate:
134 format_id += '-%s' % bitrate
135 formats.append({
136 'url': uri,
137 'format_id': format_id,
138 'tbr': int_or_none(bitrate),
139 'ext': link.get('FileFormat'),
140 'vcodec': 'none' if kind == 'AudioResource' else None,
141 'preference': preference,
142 })
143 subtitles_list = asset.get('SubtitlesList')
144 if isinstance(subtitles_list, list):
145 LANGS = {
146 'Danish': 'da',
147 }
148 for subs in subtitles_list:
149 if not subs.get('Uri'):
150 continue
151 lang = subs.get('Language') or 'da'
152 subtitles.setdefault(LANGS.get(lang, lang), []).append({
153 'url': subs['Uri'],
154 'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
155 })
156
157 if not formats and restricted_to_denmark:
158 self.raise_geo_restricted(
159 'Unfortunately, DR is not allowed to show this program outside Denmark.',
160 countries=self._GEO_COUNTRIES)
161
162 self._sort_formats(formats)
163
164 return {
165 'id': video_id,
166 'title': title,
167 'description': description,
168 'thumbnail': thumbnail,
169 'timestamp': timestamp,
170 'duration': duration,
171 'formats': formats,
172 'subtitles': subtitles,
173 }
174
175
176 class DRTVLiveIE(InfoExtractor):
177 IE_NAME = 'drtv:live'
178 _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
179 _GEO_COUNTRIES = ['DK']
180 _TEST = {
181 'url': 'https://www.dr.dk/tv/live/dr1',
182 'info_dict': {
183 'id': 'dr1',
184 'ext': 'mp4',
185 'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
186 },
187 'params': {
188 # m3u8 download
189 'skip_download': True,
190 },
191 }
192
193 def _real_extract(self, url):
194 channel_id = self._match_id(url)
195 channel_data = self._download_json(
196 'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
197 channel_id)
198 title = self._live_title(channel_data['Title'])
199
200 formats = []
201 for streaming_server in channel_data.get('StreamingServers', []):
202 server = streaming_server.get('Server')
203 if not server:
204 continue
205 link_type = streaming_server.get('LinkType')
206 for quality in streaming_server.get('Qualities', []):
207 for stream in quality.get('Streams', []):
208 stream_path = stream.get('Stream')
209 if not stream_path:
210 continue
211 stream_url = update_url_query(
212 '%s/%s' % (server, stream_path), {'b': ''})
213 if link_type == 'HLS':
214 formats.extend(self._extract_m3u8_formats(
215 stream_url, channel_id, 'mp4',
216 m3u8_id=link_type, fatal=False, live=True))
217 elif link_type == 'HDS':
218 formats.extend(self._extract_f4m_formats(update_url_query(
219 '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
220 channel_id, f4m_id=link_type, fatal=False))
221 self._sort_formats(formats)
222
223 return {
224 'id': channel_id,
225 'title': title,
226 'thumbnail': channel_data.get('PrimaryImageUri'),
227 'formats': formats,
228 'is_live': True,
229 }