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
|
import re
from .common import InfoExtractor
from ..utils import (
determine_protocol,
float_or_none,
int_or_none,
parse_iso8601,
unescapeHTML,
update_url_query,
)
class SendtoNewsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
_TEST = {
# From http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/
'url': 'http://embed.sendtonews.com/player2/embedplayer.php?SC=GxfCe0Zo7D-175909-5588&type=single&autoplay=on&sound=YES',
'info_dict': {
'id': 'GxfCe0Zo7D-175909-5588',
},
'playlist_count': 8,
# test the first video only to prevent lengthy tests
'playlist': [{
'info_dict': {
'id': '240385',
'ext': 'mp4',
'title': 'Indians introduce Encarnacion',
'description': 'Indians president of baseball operations Chris Antonetti and Edwin Encarnacion discuss the slugger\'s three-year contract with Cleveland',
'duration': 137.898,
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20170105',
'timestamp': 1483649762,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}
_URL_TEMPLATE = '//embed.sendtonews.com/player2/embedplayer.php?SC=%s'
@classmethod
def _extract_embed_urls(cls, url, webpage):
mobj = re.search(r'''(?x)<script[^>]+src=([\'"])
(?:https?:)?//embed\.sendtonews\.com/player/responsiveembed\.php\?
.*\bSC=(?P<SC>[0-9a-zA-Z-]+).*
\1>''', webpage)
if mobj:
sc = mobj.group('SC')
yield cls._URL_TEMPLATE % sc
def _real_extract(self, url):
playlist_id = self._match_id(url)
data_url = update_url_query(
url.replace('embedplayer.php', 'data_read.php'),
{'cmd': 'loadInitial'})
playlist_data = self._download_json(data_url, playlist_id)
entries = []
for video in playlist_data['playlistData'][0]:
info_dict = self._parse_jwplayer_data(
video['jwconfiguration'],
require_title=False, m3u8_id='hls', rtmp_params={'no_resume': True})
for f in info_dict['formats']:
if f.get('tbr'):
continue
tbr = int_or_none(self._search_regex(
r'/(\d+)k/', f['url'], 'bitrate', default=None))
if not tbr:
continue
f.update({
'format_id': f'{determine_protocol(f)}-{tbr}',
'tbr': tbr,
})
thumbnails = []
if video.get('thumbnailUrl'):
thumbnails.append({
'id': 'normal',
'url': video['thumbnailUrl'],
})
if video.get('smThumbnailUrl'):
thumbnails.append({
'id': 'small',
'url': video['smThumbnailUrl'],
})
info_dict.update({
'title': video['S_headLine'].strip(),
'description': unescapeHTML(video.get('S_fullStory')),
'thumbnails': thumbnails,
'duration': float_or_none(video.get('SM_length')),
'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
# 'tbr' was explicitly set to be preferred over 'height' originally,
# So this is being kept unless someone can confirm this is unnecessary
'_format_sort_fields': ('tbr', 'res'),
})
entries.append(info_dict)
return self.playlist_result(entries, playlist_id)
|
