mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-27 01:32:28 +02:00
[sendtonews] improve info extraction
This commit is contained in:
parent
a814da3f62
commit
e5dfdc8164
@ -8,6 +8,9 @@
|
|||||||
float_or_none,
|
float_or_none,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
update_url_query,
|
update_url_query,
|
||||||
|
int_or_none,
|
||||||
|
determine_protocol,
|
||||||
|
unescapeHTML,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -20,18 +23,18 @@ class SendtoNewsIE(JWPlatformBaseIE):
|
|||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'GxfCe0Zo7D-175909-5588'
|
'id': 'GxfCe0Zo7D-175909-5588'
|
||||||
},
|
},
|
||||||
'playlist_count': 9,
|
'playlist_count': 8,
|
||||||
# test the first video only to prevent lengthy tests
|
# test the first video only to prevent lengthy tests
|
||||||
'playlist': [{
|
'playlist': [{
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '198180',
|
'id': '240385',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Recap: CLE 5, LAA 4',
|
'title': 'Indians introduce Encarnacion',
|
||||||
'description': '8/14/16: Naquin, Almonte lead Indians in 5-4 win',
|
'description': 'Indians president of baseball operations Chris Antonetti and Edwin Encarnacion discuss the slugger\'s three-year contract with Cleveland',
|
||||||
'duration': 57.343,
|
'duration': 137.898,
|
||||||
'thumbnail': r're:https?://.*\.jpg$',
|
'thumbnail': r're:https?://.*\.jpg$',
|
||||||
'upload_date': '20160815',
|
'upload_date': '20170105',
|
||||||
'timestamp': 1471221961,
|
'timestamp': 1483649762,
|
||||||
},
|
},
|
||||||
}],
|
}],
|
||||||
'params': {
|
'params': {
|
||||||
@ -64,7 +67,20 @@ def _real_extract(self, url):
|
|||||||
for video in playlist_data['playlistData'][0]:
|
for video in playlist_data['playlistData'][0]:
|
||||||
info_dict = self._parse_jwplayer_data(
|
info_dict = self._parse_jwplayer_data(
|
||||||
video['jwconfiguration'],
|
video['jwconfiguration'],
|
||||||
require_title=False, rtmp_params={'no_resume': True})
|
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': '%s-%d' % (determine_protocol(f), tbr),
|
||||||
|
'tbr': tbr,
|
||||||
|
})
|
||||||
|
self._sort_formats(info_dict['formats'], ('tbr', 'height', 'width', 'format_id'))
|
||||||
|
|
||||||
thumbnails = []
|
thumbnails = []
|
||||||
if video.get('thumbnailUrl'):
|
if video.get('thumbnailUrl'):
|
||||||
@ -78,8 +94,8 @@ def _real_extract(self, url):
|
|||||||
'url': video['smThumbnailUrl'],
|
'url': video['smThumbnailUrl'],
|
||||||
})
|
})
|
||||||
info_dict.update({
|
info_dict.update({
|
||||||
'title': video['S_headLine'],
|
'title': video['S_headLine'].strip(),
|
||||||
'description': video.get('S_fullStory'),
|
'description': unescapeHTML(video.get('S_fullStory')),
|
||||||
'thumbnails': thumbnails,
|
'thumbnails': thumbnails,
|
||||||
'duration': float_or_none(video.get('SM_length')),
|
'duration': float_or_none(video.get('SM_length')),
|
||||||
'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
|
'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
|
||||||
|
Loading…
Reference in New Issue
Block a user