aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ustream.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-13 19:55:49 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-13 21:34:31 +0200
commit74ac9bdd82b8a625ea9782251258ab7da1463877 (patch)
treea9f023d452361aa65cd5289a613f1da8eab9e0f4 /youtube_dl/extractor/ustream.py
parent94518f208799dde250f5fd8dd0ce77dd7ea05b1c (diff)
parentbfd5c93af9f9eee938c628f19c997f999f21c74e (diff)
Merge pull request #1413 from tewe/master
Add Ustream channel support
Diffstat (limited to 'youtube_dl/extractor/ustream.py')
-rw-r--r--youtube_dl/extractor/ustream.py66
1 files changed, 66 insertions, 0 deletions
diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py
index 5f423870a..f69b27d44 100644
--- a/youtube_dl/extractor/ustream.py
+++ b/youtube_dl/extractor/ustream.py
@@ -1,6 +1,11 @@
+import json
import re
from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ compat_html_parser,
+)
class UstreamIE(InfoExtractor):
@@ -43,3 +48,64 @@ class UstreamIE(InfoExtractor):
'thumbnail': thumbnail,
}
return info
+
+# More robust than regular expressions
+
+class ChannelParser(compat_html_parser.HTMLParser):
+ """
+ <meta name="ustream:channel_id" content="1234">
+ """
+ channel_id = None
+
+ def handle_starttag(self, tag, attrs):
+ if tag != 'meta':
+ return
+ values = dict(attrs)
+ if values.get('name') != 'ustream:channel_id':
+ return
+ value = values.get('content', '')
+ if value.isdigit():
+ self.channel_id = value
+
+class SocialstreamParser(compat_html_parser.HTMLParser):
+ """
+ <li class="content123 video" data-content-id="123" data-length="1452"
+ data-href="/recorded/123" data-og-url="/recorded/123">
+ """
+ def __init__(self):
+ compat_html_parser.HTMLParser.__init__(self)
+ self.content_ids = []
+
+ def handle_starttag(self, tag, attrs):
+ if tag != 'li':
+ return
+ for (attr, value) in attrs:
+ if attr == 'data-content-id' and value.isdigit():
+ self.content_ids.append(value)
+
+class UstreamChannelIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
+ IE_NAME = u'ustream:channel'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ slug = m.group('slug')
+
+ p = ChannelParser()
+ p.feed(self._download_webpage(url, slug))
+ p.close()
+ channel_id = p.channel_id
+
+ p = SocialstreamParser()
+ BASE = 'http://www.ustream.tv'
+ next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
+ while next_url:
+ reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
+ p.feed(reply['data'])
+ next_url = reply['nextUrl']
+ p.close()
+ video_ids = p.content_ids
+
+ 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)