aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ustream.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-13 22:05:29 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-13 22:05:29 +0200
commita921f40799d2ecb4be53b3241d2dbfc80f804d73 (patch)
tree4443b3d29704e032aa161d0ceb0cf970c6669e99 /youtube_dl/extractor/ustream.py
parent74ac9bdd82b8a625ea9782251258ab7da1463877 (diff)
[ustream] Simplify channel extraction
the ChannelParser has been moved to a new function in utils get_meta_content Instead of the SocialStreamParser now it uses a regex
Diffstat (limited to 'youtube_dl/extractor/ustream.py')
-rw-r--r--youtube_dl/extractor/ustream.py49
1 files changed, 5 insertions, 44 deletions
diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py
index f69b27d44..74c82587f 100644
--- a/youtube_dl/extractor/ustream.py
+++ b/youtube_dl/extractor/ustream.py
@@ -4,7 +4,7 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
- compat_html_parser,
+ get_meta_content,
)
@@ -49,40 +49,6 @@ class UstreamIE(InfoExtractor):
}
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'
@@ -90,21 +56,16 @@ class UstreamChannelIE(InfoExtractor):
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)
- 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
+ video_ids = []
while next_url:
reply = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
- p.feed(reply['data'])
+ video_ids.extend(re.findall(r'data-content-id="(\d.*)"', 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]