2014-01-31 13:05:33 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2013-06-23 20:08:28 +00:00
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 11:24:42 +00:00
|
|
|
from ..compat import (
|
2013-09-13 17:55:49 +00:00
|
|
|
compat_urlparse,
|
|
|
|
)
|
2015-10-05 16:30:38 +00:00
|
|
|
from ..utils import (
|
|
|
|
ExtractorError,
|
|
|
|
int_or_none,
|
|
|
|
float_or_none,
|
|
|
|
)
|
2013-06-23 20:08:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
class UstreamIE(InfoExtractor):
|
2016-09-08 11:29:05 +00:00
|
|
|
_VALID_URL = r'https?://(?:www\.)?ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)'
|
2014-01-31 13:05:33 +00:00
|
|
|
IE_NAME = 'ustream'
|
2015-04-23 10:33:25 +00:00
|
|
|
_TESTS = [{
|
2014-01-31 13:05:33 +00:00
|
|
|
'url': 'http://www.ustream.tv/recorded/20274954',
|
|
|
|
'md5': '088f151799e8f572f84eb62f17d73e5c',
|
|
|
|
'info_dict': {
|
2014-05-29 13:22:36 +00:00
|
|
|
'id': '20274954',
|
|
|
|
'ext': 'flv',
|
|
|
|
'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
|
2015-10-05 16:52:51 +00:00
|
|
|
'description': 'Young Americans for Liberty February 7, 2012 2:28 AM',
|
|
|
|
'timestamp': 1328577035,
|
|
|
|
'upload_date': '20120207',
|
|
|
|
'uploader': 'yaliberty',
|
|
|
|
'uploader_id': '6780869',
|
2014-01-31 13:05:33 +00:00
|
|
|
},
|
2015-04-23 10:33:25 +00:00
|
|
|
}, {
|
|
|
|
# From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444
|
|
|
|
# Title and uploader available only from params JSON
|
|
|
|
'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct',
|
|
|
|
'md5': '5a2abf40babeac9812ed20ae12d34e10',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '59307601',
|
|
|
|
'ext': 'flv',
|
|
|
|
'title': '-CG11- Canada Games Figure Skating',
|
|
|
|
'uploader': 'sportscanadatv',
|
2015-10-05 16:52:51 +00:00
|
|
|
},
|
|
|
|
'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.',
|
2016-04-16 11:39:25 +00:00
|
|
|
}, {
|
|
|
|
'url': 'http://www.ustream.tv/embed/10299409',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '10299409',
|
|
|
|
},
|
|
|
|
'playlist_count': 3,
|
2015-04-23 10:33:25 +00:00
|
|
|
}]
|
2013-06-23 20:08:28 +00:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
m = re.match(self._VALID_URL, url)
|
2015-10-05 16:40:20 +00:00
|
|
|
video_id = m.group('id')
|
2014-05-28 12:47:13 +00:00
|
|
|
|
2016-01-17 14:06:00 +00:00
|
|
|
# some sites use this embed format (see: https://github.com/rg3/youtube-dl/issues/2990)
|
2014-05-29 13:22:36 +00:00
|
|
|
if m.group('type') == 'embed/recorded':
|
2015-10-05 16:40:20 +00:00
|
|
|
video_id = m.group('id')
|
2014-05-28 12:47:13 +00:00
|
|
|
desktop_url = 'http://www.ustream.tv/recorded/' + video_id
|
|
|
|
return self.url_result(desktop_url, 'Ustream')
|
2014-04-04 14:23:09 +00:00
|
|
|
if m.group('type') == 'embed':
|
2015-10-05 16:40:20 +00:00
|
|
|
video_id = m.group('id')
|
2014-04-04 14:23:09 +00:00
|
|
|
webpage = self._download_webpage(url, video_id)
|
2016-04-16 11:39:25 +00:00
|
|
|
content_video_ids = self._parse_json(self._search_regex(
|
|
|
|
r'ustream\.vars\.offAirContentVideoIds=([^;]+);', webpage,
|
|
|
|
'content video IDs'), video_id)
|
|
|
|
return self.playlist_result(
|
|
|
|
map(lambda u: self.url_result('http://www.ustream.tv/recorded/' + u, 'Ustream'), content_video_ids),
|
|
|
|
video_id)
|
2014-04-04 14:23:09 +00:00
|
|
|
|
2015-10-05 16:40:20 +00:00
|
|
|
params = self._download_json(
|
|
|
|
'https://api.ustream.tv/videos/%s.json' % video_id, video_id)
|
2015-04-23 09:57:49 +00:00
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
error = params.get('error')
|
|
|
|
if error:
|
|
|
|
raise ExtractorError(
|
|
|
|
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
|
2013-06-23 20:08:28 +00:00
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
video = params['video']
|
2015-04-23 10:24:44 +00:00
|
|
|
|
2015-10-05 16:48:47 +00:00
|
|
|
title = video['title']
|
|
|
|
filesize = float_or_none(video.get('file_size'))
|
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
formats = [{
|
2015-10-05 16:51:04 +00:00
|
|
|
'id': video_id,
|
2015-10-05 16:30:38 +00:00
|
|
|
'url': video_url,
|
|
|
|
'ext': format_id,
|
2015-10-05 16:48:47 +00:00
|
|
|
'filesize': filesize,
|
2015-10-05 16:30:38 +00:00
|
|
|
} for format_id, video_url in video['media_urls'].items()]
|
|
|
|
self._sort_formats(formats)
|
2013-06-23 20:08:28 +00:00
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
description = video.get('description')
|
|
|
|
timestamp = int_or_none(video.get('created_at'))
|
|
|
|
duration = float_or_none(video.get('length'))
|
|
|
|
view_count = int_or_none(video.get('views'))
|
2015-04-23 10:33:25 +00:00
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
uploader = video.get('owner', {}).get('username')
|
|
|
|
uploader_id = video.get('owner', {}).get('id')
|
2013-06-23 20:08:28 +00:00
|
|
|
|
2015-10-05 16:30:38 +00:00
|
|
|
thumbnails = [{
|
|
|
|
'id': thumbnail_id,
|
|
|
|
'url': thumbnail_url,
|
|
|
|
} for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()]
|
2014-01-31 13:05:33 +00:00
|
|
|
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
2015-10-05 16:30:38 +00:00
|
|
|
'title': title,
|
|
|
|
'description': description,
|
|
|
|
'thumbnails': thumbnails,
|
|
|
|
'timestamp': timestamp,
|
|
|
|
'duration': duration,
|
|
|
|
'view_count': view_count,
|
2014-01-31 13:05:33 +00:00
|
|
|
'uploader': uploader,
|
2015-10-05 16:30:38 +00:00
|
|
|
'uploader_id': uploader_id,
|
|
|
|
'formats': formats,
|
2014-01-31 13:05:33 +00:00
|
|
|
}
|
|
|
|
|
2013-09-12 10:30:14 +00:00
|
|
|
|
|
|
|
class UstreamChannelIE(InfoExtractor):
|
2016-09-08 11:29:05 +00:00
|
|
|
_VALID_URL = r'https?://(?:www\.)?ustream\.tv/channel/(?P<slug>.+)'
|
2014-01-31 13:05:33 +00:00
|
|
|
IE_NAME = 'ustream:channel'
|
2014-08-27 22:58:24 +00:00
|
|
|
_TEST = {
|
|
|
|
'url': 'http://www.ustream.tv/channel/channeljapan',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '10874166',
|
|
|
|
},
|
2014-10-26 23:18:10 +00:00
|
|
|
'playlist_mincount': 17,
|
2014-08-27 22:58:24 +00:00
|
|
|
}
|
2013-09-12 10:30:14 +00:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
m = re.match(self._VALID_URL, url)
|
2014-08-27 22:58:24 +00:00
|
|
|
display_id = m.group('slug')
|
|
|
|
webpage = self._download_webpage(url, display_id)
|
2014-11-04 22:15:16 +00:00
|
|
|
channel_id = self._html_search_meta('ustream:channel_id', webpage)
|
2013-09-12 10:30:14 +00:00
|
|
|
|
|
|
|
BASE = 'http://www.ustream.tv'
|
|
|
|
next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
|
2013-09-13 20:05:29 +00:00
|
|
|
video_ids = []
|
2013-09-12 10:30:14 +00:00
|
|
|
while next_url:
|
2014-08-27 22:58:24 +00:00
|
|
|
reply = self._download_json(
|
|
|
|
compat_urlparse.urljoin(BASE, next_url), display_id,
|
|
|
|
note='Downloading video information (next: %d)' % (len(video_ids) + 1))
|
2013-09-13 20:05:29 +00:00
|
|
|
video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
|
2013-09-12 10:30:14 +00:00
|
|
|
next_url = reply['nextUrl']
|
|
|
|
|
2014-08-27 22:58:24 +00:00
|
|
|
entries = [
|
|
|
|
self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream')
|
|
|
|
for vid in video_ids]
|
|
|
|
return {
|
|
|
|
'_type': 'playlist',
|
|
|
|
'id': channel_id,
|
|
|
|
'display_id': display_id,
|
|
|
|
'entries': entries,
|
|
|
|
}
|