1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/sendtonews.py

106 lines
3.7 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
2016-08-15 05:31:08 +00:00
float_or_none,
parse_iso8601,
update_url_query,
2017-01-06 10:23:43 +00:00
int_or_none,
determine_protocol,
unescapeHTML,
)
class SendtoNewsIE(InfoExtractor):
2016-08-15 05:31:08 +00:00
_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/
2016-08-15 05:31:08 +00:00
'url': 'http://embed.sendtonews.com/player2/embedplayer.php?SC=GxfCe0Zo7D-175909-5588&type=single&autoplay=on&sound=YES',
'info_dict': {
2016-08-15 05:31:08 +00:00
'id': 'GxfCe0Zo7D-175909-5588'
},
2017-01-06 10:23:43 +00:00
'playlist_count': 8,
2016-08-15 05:31:08 +00:00
# test the first video only to prevent lengthy tests
'playlist': [{
'info_dict': {
2017-01-06 10:23:43 +00:00
'id': '240385',
2016-08-15 05:31:08 +00:00
'ext': 'mp4',
2017-01-06 10:23:43 +00:00
'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$',
2017-01-06 10:23:43 +00:00
'upload_date': '20170105',
'timestamp': 1483649762,
2016-08-15 05:31:08 +00:00
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}
2016-08-15 05:31:08 +00:00
_URL_TEMPLATE = '//embed.sendtonews.com/player2/embedplayer.php?SC=%s'
@classmethod
def _extract_url(cls, 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:
2016-08-15 05:31:08 +00:00
sc = mobj.group('SC')
return cls._URL_TEMPLATE % sc
def _real_extract(self, url):
2016-08-15 05:31:08 +00:00
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'],
2017-01-06 10:23:43 +00:00
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'))
2016-08-15 05:31:08 +00:00
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({
2017-01-06 10:23:43 +00:00
'title': video['S_headLine'].strip(),
'description': unescapeHTML(video.get('S_fullStory')),
2016-08-15 05:31:08 +00:00
'thumbnails': thumbnails,
'duration': float_or_none(video.get('SM_length')),
'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
})
entries.append(info_dict)
return self.playlist_result(entries, playlist_id)