3 from .common
import InfoExtractor
12 class PlaytvakIE(InfoExtractor
):
13 IE_DESC
= 'Playtvak.cz, iDNES.cz and Lidovky.cz'
14 _VALID_URL
= r
'https?://(?:.+?\.)?(?:playtvak|idnes|lidovky|metro)\.cz/.*\?(?:c|idvideo)=(?P<id>[^&]+)'
16 'url': 'http://www.playtvak.cz/vyzente-vosy-a-srsne-ze-zahrady-dn5-/hodinovy-manzel.aspx?c=A150730_150323_hodinovy-manzel_kuko',
17 'md5': '4525ae312c324b4be2f4603cc78ceb4a',
19 'id': 'A150730_150323_hodinovy-manzel_kuko',
21 'title': 'Vyžeňte vosy a sršně ze zahrady',
22 'description': 'md5:4436e61b7df227a093778efb7e373571',
23 'thumbnail': r
're:(?i)^https?://.*\.(?:jpg|png)$',
25 'timestamp': 1438732860,
26 'upload_date': '20150805',
29 }, { # live video test
30 'url': 'http://slowtv.playtvak.cz/planespotting-0pr-/planespotting.aspx?c=A150624_164934_planespotting_cat',
32 'id': 'A150624_164934_planespotting_cat',
34 'title': 're:^Planespotting [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
35 'description': 'Sledujte provoz na ranveji Letiště Václava Havla v Praze',
39 'skip_download': True, # requires rtmpdump
41 }, { # another live stream, this one without Misc.videoFLV
42 'url': 'https://slowtv.playtvak.cz/zive-sledujte-vlaky-v-primem-prenosu-dwi-/hlavni-nadrazi.aspx?c=A151218_145728_hlavni-nadrazi_plap',
44 'id': 'A151218_145728_hlavni-nadrazi_plap',
46 'title': 're:^Hlavní nádraží [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
50 'skip_download': True, # requires rtmpdump
53 'url': 'http://zpravy.idnes.cz/pes-zavreny-v-aute-rozbijeni-okynek-v-aute-fj5-/domaci.aspx?c=A150809_104116_domaci_pku',
54 'md5': '819832ba33cd7016e58a6658577fe289',
56 'id': 'A150809_104116_domaci_pku',
58 'title': 'Zavřeli jsme mraženou pizzu do auta. Upekla se',
59 'description': 'md5:01e73f02329e2e5760bd5eed4d42e3c2',
60 'thumbnail': r
're:(?i)^https?://.*\.(?:jpg|png)$',
62 'timestamp': 1438969140,
63 'upload_date': '20150807',
67 'url': 'http://www.lidovky.cz/dalsi-demonstrace-v-praze-o-migraci-duq-/video.aspx?c=A150808_214044_ln-video_ELE',
68 'md5': 'c7209ac4ba9d234d4ad5bab7485bcee8',
70 'id': 'A150808_214044_ln-video_ELE',
72 'title': 'Táhni! Demonstrace proti imigrantům budila emoce',
73 'description': 'md5:97c81d589a9491fbfa323c9fa3cca72c',
74 'thumbnail': r
're:(?i)^https?://.*\.(?:jpg|png)$',
75 'timestamp': 1439052180,
76 'upload_date': '20150808',
80 'url': 'http://www.metro.cz/video-pod-billboardem-se-na-vltavske-roztocil-kolotoc-deti-vozil-jen-par-hodin-1hx-/metro-extra.aspx?c=A141111_173251_metro-extra_row',
81 'md5': '84fc1deedcac37b7d4a6ccae7c716668',
83 'id': 'A141111_173251_metro-extra_row',
85 'title': 'Recesisté udělali z billboardu kolotoč',
86 'description': 'md5:7369926049588c3989a66c9c1a043c4c',
87 'thumbnail': r
're:(?i)^https?://.*\.(?:jpg|png)$',
88 'timestamp': 1415725500,
89 'upload_date': '20141111',
93 'url': 'http://www.playtvak.cz/embed.aspx?idvideo=V150729_141549_play-porad_kuko',
94 'only_matching': True,
97 def _real_extract(self
, url
):
98 video_id
= self
._match
_id
(url
)
100 webpage
= self
._download
_webpage
(url
, video_id
)
102 info_url
= self
._html
_search
_regex
(
103 r
'Misc\.video(?:FLV)?\(\s*{\s*data\s*:\s*"([^"]+)"', webpage
, 'info url')
105 parsed_url
= urllib
.parse
.urlparse(info_url
)
107 qs
= urllib
.parse
.parse_qs(parsed_url
.query
)
113 info_url
= urllib
.parse
.urlunparse(
114 parsed_url
._replace
(query
=urllib
.parse
.urlencode(qs
, True)))
116 json_info
= self
._download
_json
(
118 transform_source
=lambda s
: s
[s
.index('{'):s
.rindex('}') + 1])
121 for i
in json_info
['items']:
122 if i
.get('type') == 'video' or i
.get('type') == 'stream':
126 raise ExtractorError('No suitable stream found')
128 quality
= qualities(('low', 'middle', 'high'))
131 for fmt
in item
['video']:
132 video_url
= fmt
.get('file')
136 format_
= fmt
['format']
137 format_id
= '{}_{}'.format(format_
, fmt
['quality'])
140 if format_
in ('mp4', 'webm'):
142 elif format_
== 'rtmp':
144 elif format_
== 'apple':
146 # Some streams have mp3 audio which does not play
147 # well with ffmpeg filter aac_adtstoasc
149 elif format_
== 'adobe': # f4m manifest fails with 404 in 80% of requests
151 else: # Other formats not supported yet
157 'format_id': format_id
,
158 'quality': quality(fmt
.get('quality')),
159 'preference': preference
,
162 title
= item
['title']
163 is_live
= item
['type'] == 'stream'
164 description
= self
._og
_search
_description
(webpage
, default
=None) or self
._html
_search
_meta
(
165 'description', webpage
, 'description', default
=None)
169 duration
= int_or_none(item
.get('length'))
170 timestamp
= item
.get('published')
172 timestamp
= parse_iso8601(timestamp
[:-5])
177 'description': description
,
178 'thumbnail': item
.get('image'),
179 'duration': duration
,
180 'timestamp': timestamp
,