youtube-dl/youtube_dl/extractor/ustream.py

82 lines
2.9 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-09-12 12:30:14 +02:00
import json
2013-06-23 22:08:28 +02:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
get_meta_content,
)
2013-06-23 22:08:28 +02:00
class UstreamIE(InfoExtractor):
_VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)'
IE_NAME = 'ustream'
2014-04-04 18:56:29 +02:00
_TEST = {
'url': 'http://www.ustream.tv/recorded/20274954',
'file': '20274954.flv',
'md5': '088f151799e8f572f84eb62f17d73e5c',
'info_dict': {
"uploader": "Young Americans for Liberty",
"title": "Young Americans for Liberty February 7, 2012 2:28 AM",
},
2013-06-27 20:46:46 +02:00
}
2013-06-23 22:08:28 +02:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
if m.group('type') == 'embed':
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
desktop_video_id = self._html_search_regex(r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
return self.url_result(desktop_url, 'Ustream')
2013-06-23 22:08:28 +02:00
video_id = m.group('videoID')
video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
2013-06-23 22:08:28 +02:00
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
webpage, 'title')
2013-06-23 22:08:28 +02:00
uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
webpage, 'uploader', fatal=False, flags=re.DOTALL)
2013-06-23 22:08:28 +02:00
thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': video_url,
'ext': 'flv',
'title': video_title,
'uploader': uploader,
'thumbnail': thumbnail,
}
2013-09-12 12:30:14 +02:00
class UstreamChannelIE(InfoExtractor):
_VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
IE_NAME = 'ustream:channel'
2013-09-12 12:30:14 +02:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
slug = m.group('slug')
webpage = self._download_webpage(url, slug)
channel_id = get_meta_content('ustream:channel_id', webpage)
2013-09-12 12:30:14 +02:00
BASE = 'http://www.ustream.tv'
next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
video_ids = []
2013-09-12 12:30:14 +02:00
while next_url:
reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
2013-09-12 12:30:14 +02:00
next_url = reply['nextUrl']
urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids]
url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls]
return self.playlist_result(url_entries, channel_id)