1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
|
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
qualities,
)
class PlaytvakIE(InfoExtractor):
IE_DESC = 'Playtvak.cz, iDNES.cz and Lidovky.cz'
_VALID_URL = r'https?://(?:.+?\.)?(?:playtvak|idnes|lidovky|metro)\.cz/.*\?(?:c|idvideo)=(?P<id>[^&]+)'
_TESTS = [{
'url': 'http://www.playtvak.cz/vyzente-vosy-a-srsne-ze-zahrady-dn5-/hodinovy-manzel.aspx?c=A150730_150323_hodinovy-manzel_kuko',
'md5': '4525ae312c324b4be2f4603cc78ceb4a',
'info_dict': {
'id': 'A150730_150323_hodinovy-manzel_kuko',
'ext': 'mp4',
'title': 'Vyžeňte vosy a sršně ze zahrady',
'description': 'md5:4436e61b7df227a093778efb7e373571',
'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
'duration': 279,
'timestamp': 1438732860,
'upload_date': '20150805',
'is_live': False,
},
}, { # live video test
'url': 'http://slowtv.playtvak.cz/planespotting-0pr-/planespotting.aspx?c=A150624_164934_planespotting_cat',
'info_dict': {
'id': 'A150624_164934_planespotting_cat',
'ext': 'flv',
'title': 're:^Planespotting [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'Sledujte provoz na ranveji Letiště Václava Havla v Praze',
'is_live': True,
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, { # another live stream, this one without Misc.videoFLV
'url': 'https://slowtv.playtvak.cz/zive-sledujte-vlaky-v-primem-prenosu-dwi-/hlavni-nadrazi.aspx?c=A151218_145728_hlavni-nadrazi_plap',
'info_dict': {
'id': 'A151218_145728_hlavni-nadrazi_plap',
'ext': 'flv',
'title': 're:^Hlavní nádraží [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, { # idnes.cz
'url': 'http://zpravy.idnes.cz/pes-zavreny-v-aute-rozbijeni-okynek-v-aute-fj5-/domaci.aspx?c=A150809_104116_domaci_pku',
'md5': '819832ba33cd7016e58a6658577fe289',
'info_dict': {
'id': 'A150809_104116_domaci_pku',
'ext': 'mp4',
'title': 'Zavřeli jsme mraženou pizzu do auta. Upekla se',
'description': 'md5:01e73f02329e2e5760bd5eed4d42e3c2',
'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
'duration': 39,
'timestamp': 1438969140,
'upload_date': '20150807',
'is_live': False,
},
}, { # lidovky.cz
'url': 'http://www.lidovky.cz/dalsi-demonstrace-v-praze-o-migraci-duq-/video.aspx?c=A150808_214044_ln-video_ELE',
'md5': 'c7209ac4ba9d234d4ad5bab7485bcee8',
'info_dict': {
'id': 'A150808_214044_ln-video_ELE',
'ext': 'mp4',
'title': 'Táhni! Demonstrace proti imigrantům budila emoce',
'description': 'md5:97c81d589a9491fbfa323c9fa3cca72c',
'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
'timestamp': 1439052180,
'upload_date': '20150808',
'is_live': False,
},
}, { # metro.cz
'url': 'http://www.metro.cz/video-pod-billboardem-se-na-vltavske-roztocil-kolotoc-deti-vozil-jen-par-hodin-1hx-/metro-extra.aspx?c=A141111_173251_metro-extra_row',
'md5': '84fc1deedcac37b7d4a6ccae7c716668',
'info_dict': {
'id': 'A141111_173251_metro-extra_row',
'ext': 'mp4',
'title': 'Recesisté udělali z billboardu kolotoč',
'description': 'md5:7369926049588c3989a66c9c1a043c4c',
'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
'timestamp': 1415725500,
'upload_date': '20141111',
'is_live': False,
},
}, {
'url': 'http://www.playtvak.cz/embed.aspx?idvideo=V150729_141549_play-porad_kuko',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
info_url = self._html_search_regex(
r'Misc\.video(?:FLV)?\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url')
parsed_url = urllib.parse.urlparse(info_url)
qs = urllib.parse.parse_qs(parsed_url.query)
qs.update({
'reklama': ['0'],
'type': ['js'],
})
info_url = urllib.parse.urlunparse(
parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
json_info = self._download_json(
info_url, video_id,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
item = None
for i in json_info['items']:
if i.get('type') == 'video' or i.get('type') == 'stream':
item = i
break
if not item:
raise ExtractorError('No suitable stream found')
quality = qualities(('low', 'middle', 'high'))
formats = []
for fmt in item['video']:
video_url = fmt.get('file')
if not video_url:
continue
format_ = fmt['format']
format_id = '{}_{}'.format(format_, fmt['quality'])
preference = None
if format_ in ('mp4', 'webm'):
ext = format_
elif format_ == 'rtmp':
ext = 'flv'
elif format_ == 'apple':
ext = 'mp4'
# Some streams have mp3 audio which does not play
# well with ffmpeg filter aac_adtstoasc
preference = -10
elif format_ == 'adobe': # f4m manifest fails with 404 in 80% of requests
continue
else: # Other formats not supported yet
continue
formats.append({
'url': video_url,
'ext': ext,
'format_id': format_id,
'quality': quality(fmt.get('quality')),
'preference': preference,
})
title = item['title']
is_live = item['type'] == 'stream'
description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'description', webpage, 'description', default=None)
timestamp = None
duration = None
if not is_live:
duration = int_or_none(item.get('length'))
timestamp = item.get('published')
if timestamp:
timestamp = parse_iso8601(timestamp[:-5])
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': item.get('image'),
'duration': duration,
'timestamp': timestamp,
'is_live': is_live,
'formats': formats,
}
|
