]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dvtv.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
17 class DVTVIE(InfoExtractor
):
19 IE_DESC
= 'http://video.aktualne.cz/'
21 _VALID_URL
= r
'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
24 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
25 'md5': '67cb83e4a955d36e1b5d31993134a0c2',
27 'id': 'dc0768de855511e49e4b0025900fea04',
29 'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
33 'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
35 'title': r
're:^DVTV 16\. 12\. 2014: útok Talibanu, boj o kliniku, uprchlíci',
36 'id': '973eb3bc854e11e498be002590604f2e',
39 'md5': 'da7ca6be4935532241fa9520b3ad91e4',
41 'id': 'b0b40906854d11e4bdad0025900fea04',
43 'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne',
44 'description': 'md5:0916925dea8e30fe84222582280b47a0',
45 'timestamp': 1418760010,
46 'upload_date': '20141216',
49 'md5': '5f7652a08b05009c1292317b449ffea2',
51 'id': '420ad9ec854a11e4bdad0025900fea04',
53 'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka',
54 'description': 'md5:ff2f9f6de73c73d7cef4f756c1c1af42',
55 'timestamp': 1418760010,
56 'upload_date': '20141216',
59 'md5': '498eb9dfa97169f409126c617e2a3d64',
61 'id': '95d35580846a11e4b6d20025900fea04',
63 'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?',
64 'description': 'md5:889fe610a70fee5511dc3326a089188e',
65 'timestamp': 1418760010,
66 'upload_date': '20141216',
69 'md5': 'b8dc6b744844032dab6ba3781a7274b9',
71 'id': '6fe14d66853511e4833a0025900fea04',
73 'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády',
74 'description': 'md5:544f86de6d20c4815bea11bf2ac3004f',
75 'timestamp': 1418760010,
76 'upload_date': '20141216',
80 'url': 'https://video.aktualne.cz/dvtv/zeman-si-jen-leci-mindraky-sobotku-nenavidi-a-babis-se-mu-te/r~960cdb3a365a11e7a83b0025900fea04/',
81 'md5': 'f8efe9656017da948369aa099788c8ea',
83 'id': '3c496fec365911e7a6500025900fea04',
85 'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
89 'skip_download': True,
92 'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
93 'only_matching': True,
96 def _parse_video_metadata(self
, js
, video_id
, live_js
=None):
97 data
= self
._parse
_json
(js
, video_id
, transform_source
=js_to_json
)
99 data
.update(self
._parse
_json
(
100 live_js
, video_id
, transform_source
=js_to_json
))
102 title
= unescapeHTML(data
['title'])
105 for video
in data
['sources']:
106 video_url
= video
.get('file')
109 video_type
= video
.get('type')
110 ext
= determine_ext(video_url
, mimetype2ext(video_type
))
111 if video_type
== 'application/vnd.apple.mpegurl' or ext
== 'm3u8':
112 formats
.extend(self
._extract
_m
3u8_formats
(
113 video_url
, video_id
, 'mp4', entry_protocol
='m3u8_native',
114 m3u8_id
='hls', fatal
=False))
115 elif video_type
== 'application/dash+xml' or ext
== 'mpd':
116 formats
.extend(self
._extract
_mpd
_formats
(
117 video_url
, video_id
, mpd_id
='dash', fatal
=False))
119 label
= video
.get('label')
120 height
= self
._search
_regex
(
121 r
'^(\d+)[pP]', label
or '', 'height', default
=None)
123 for f
in (ext
, label
):
128 'format_id': '-'.join(format_id
),
129 'height': int_or_none(height
),
131 self
._sort
_formats
(formats
)
134 'id': data
.get('mediaid') or video_id
,
136 'description': data
.get('description'),
137 'thumbnail': data
.get('image'),
138 'duration': int_or_none(data
.get('duration')),
139 'timestamp': int_or_none(data
.get('pubtime')),
143 def _real_extract(self
, url
):
144 video_id
= self
._match
_id
(url
)
146 webpage
= self
._download
_webpage
(url
, video_id
)
149 live_item
= self
._search
_regex
(
150 r
'(?s)embedData[0-9a-f]{32}\.asset\.liveStarter\s*=\s*(\{.+?\});',
151 webpage
, 'video', default
=None)
154 item
= self
._search
_regex
(
155 r
'(?s)embedData[0-9a-f]{32}\[["\']asset
["\']\]\s*=\s*(\{.+?\});',
156 webpage, 'video', default=None)
159 return self._parse_video_metadata(item, video_id, live_item)
163 r"(?s
)BBX\
.context\
.assets\
['[0-9a-f]{32}'\
]\
.push\
(({.+?
})\
);",
166 items = re.findall(r'(?s)var\s+asset\s*=\s*({.+?});\n', webpage)
172 'title': self._og_search_title(webpage),
173 'entries': [self._parse_video_metadata(i, video_id) for i in items]
176 raise ExtractorError('Could not find neither video nor playlist')