from .common import InfoExtractor
from ..utils import (
+ int_or_none,
unescapeHTML,
find_xpath_attr,
)
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
data = self._download_json(info_url, video_id)
- url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
- doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id + '&version=2014-01-23',
+ doc = self._download_xml(
+ 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
video_id)
- formats = [
- {
- 'url': url,
- }
- ]
-
- def find_string(node, s):
- return find_xpath_attr(node, './/string', 'name', s).text
-
- def find_number(node, s):
- return int(find_xpath_attr(node, './/number', 'name', s).text)
-
- def find_array(node, s):
- return find_xpath_attr(node, './/array', 'name', s)
+ title = find_xpath_attr(doc, './/string', 'name', 'title').text
+ thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
- def process_files(files, url, formats):
- for file in files:
- path = find_string(file, 'path')
- #duration = find_number(file, './number', 'name', 'length')
- hd = find_number(file, 'hd')
- formats.append({
- 'url': url,
- 'play_path': path,
- 'ext': 'flv',
- 'quality': hd,
- })
+ files = data['video']['files']
- def process_node(node, formats):
- url = find_xpath_attr(node, './string', 'name', 'url')
- if url is None:
- url = find_xpath_attr(node, './string', 'name', 'URL')
- if url is None:
- return
- url = url.text.replace('$(protocol)', 'rtmp').replace('$(port)', '1935')
- files = find_array(node, 'files')
- if files is None:
- return
- process_files(files, url, formats)
-
- process_node(doc.find('./media-link'), formats)
-
- streams = find_array(doc, 'streams')
- if streams is not None:
- for stream in streams:
- if find_string(stream, 'name') != 'vod':
- continue
- process_node(stream, formats)
+ entries = [{
+ 'id': '%s_%d' % (video_id, partnum + 1),
+ 'title': (
+ title if len(files) == 1 else
+ '%s part %d' % (title, partnum + 1)),
+ 'url': unescapeHTML(f['path']['#text']),
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': int_or_none(f.get('length', {}).get('#text')),
+ } for partnum, f in enumerate(files)]
return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'title': title,
'id': video_id,
- 'title': find_string(doc, 'title'),
- 'description': description,
- 'thumbnail': find_string(doc, 'poster'),
- 'formats': formats,
}