2 from __future__ import unicode_literals
6 from .common import InfoExtractor
19 class DVTVIE(InfoExtractor):
21 IE_DESC = 'http://video.aktualne.cz/'
23 _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
26 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
27 'md5': '67cb83e4a955d36e1b5d31993134a0c2',
29 'id': 'dc0768de855511e49e4b0025900fea04',
31 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
33 'upload_date': '20141217',
34 'timestamp': 1418792400,
37 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
39 'title': r're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci',
40 'id': '973eb3bc854e11e498be002590604f2e',
43 'md5': 'da7ca6be4935532241fa9520b3ad91e4',
45 'id': 'b0b40906854d11e4bdad0025900fea04',
47 'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne',
48 'description': 'md5:0916925dea8e30fe84222582280b47a0',
49 'timestamp': 1418760010,
50 'upload_date': '20141216',
53 'md5': '5f7652a08b05009c1292317b449ffea2',
55 'id': '420ad9ec854a11e4bdad0025900fea04',
57 'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka',
58 'description': 'md5:ff2f9f6de73c73d7cef4f756c1c1af42',
59 'timestamp': 1418760010,
60 'upload_date': '20141216',
63 'md5': '498eb9dfa97169f409126c617e2a3d64',
65 'id': '95d35580846a11e4b6d20025900fea04',
67 'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?',
68 'description': 'md5:889fe610a70fee5511dc3326a089188e',
69 'timestamp': 1418760010,
70 'upload_date': '20141216',
73 'md5': 'b8dc6b744844032dab6ba3781a7274b9',
75 'id': '6fe14d66853511e4833a0025900fea04',
77 'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády',
78 'description': 'md5:544f86de6d20c4815bea11bf2ac3004f',
79 'timestamp': 1418760010,
80 'upload_date': '20141216',
84 'url': 'https://video.aktualne.cz/dvtv/zeman-si-jen-leci-mindraky-sobotku-nenavidi-a-babis-se-mu-te/r~960cdb3a365a11e7a83b0025900fea04/',
85 'md5': 'f8efe9656017da948369aa099788c8ea',
87 'id': '3c496fec365911e7a6500025900fea04',
89 'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
91 'upload_date': '20170511',
92 'timestamp': 1494514200,
95 'skip_download': True,
98 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
99 'only_matching': True,
101 # Test live stream video (liveStarter) parsing
102 'url': 'https://video.aktualne.cz/dvtv/zive-mistryne-sveta-eva-samkova-po-navratu-ze-sampionatu/r~182654c2288811e990fd0cc47ab5f122/',
103 'md5': '2e552e483f2414851ca50467054f9d5d',
105 'id': '8d116360288011e98c840cc47ab5f122',
107 'title': 'Živě: Mistryně světa Eva Samková po návratu ze šampionátu',
108 'upload_date': '20190204',
109 'timestamp': 1549289591,
112 # Video content is no longer available
113 'skip_download': True,
117 def _parse_video_metadata(self, js, video_id, timestamp):
119 data = self._parse_json(js, video_id, transform_source=js_to_json)
121 live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict)
123 data.update(live_starter)
125 title = unescapeHTML(data['title'])
129 for tracks in data.get('tracks', {}).values():
131 video_url = video.get('src')
134 video_type = video.get('type')
135 ext = determine_ext(video_url, mimetype2ext(video_type))
136 if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8':
137 formats.extend(self._extract_m3u8_formats(
138 video_url, video_id, 'mp4', entry_protocol='m3u8_native',
139 m3u8_id='hls', fatal=False))
140 elif video_type == 'application/dash+xml' or ext == 'mpd':
141 formats.extend(self._extract_mpd_formats(
142 video_url, video_id, mpd_id='dash', fatal=False))
144 label = video.get('label')
145 height = self._search_regex(
146 r'^(\d+)[pP]', label or '', 'height', default=None)
148 for f in (ext, label):
153 'format_id': '-'.join(format_id),
154 'height': int_or_none(height),
156 self._sort_formats(formats)
159 'id': data.get('mediaid') or video_id,
161 'description': data.get('description'),
162 'thumbnail': data.get('image'),
163 'duration': int_or_none(data.get('duration')),
164 'timestamp': int_or_none(timestamp),
168 def _real_extract(self, url):
169 video_id = self._match_id(url)
171 webpage = self._download_webpage(url, video_id)
173 timestamp = parse_iso8601(self._html_search_meta(
174 'article:published_time', webpage, 'published time', default=None))
178 r"(?s)playlist\.push\(({.+?})\);",
185 'title': self._og_search_title(webpage),
186 'entries': [self._parse_video_metadata(i, video_id, timestamp) for i in items]
190 item = self._search_regex(
191 r'(?s)BBXPlayer.setup\((.+?)\);',
192 webpage, 'video', default=None)
195 # remove function calls (ex. htmldeentitize)
196 # TODO this should be fixed in a general way in the js_to_json
197 item = re.sub(r'\w+?\((.+)\)', r'\1', item)
200 return self._parse_video_metadata(item, video_id, timestamp)
202 raise ExtractorError('Could not find neither video nor playlist')