- for idx in itertools.count(0):
- if idx == 0:
- playlist_data_url = 'http://list.youku.com/show/module'
- query = {'id': page_config['showid'], 'tab': 'point'}
- else:
- playlist_data_url = 'http://list.youku.com/show/point'
- query = {
- 'id': page_config['showid'],
- 'stage': 'reload_%d' % (self._PAGE_SIZE * idx + 1),
- }
- query['callback'] = 'cb'
- playlist_data = self._download_json(
- playlist_data_url, show_id, query=query,
+ first_page, initial_entries = self._extract_entries(
+ 'http://list.youku.com/show/module', show_id,
+ note='Downloading initial playlist data page',
+ query={
+ 'id': page_config['showid'],
+ 'tab': 'showInfo',
+ })
+ first_page_reload_id = self._html_search_regex(
+ r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
+ # The first reload_id has the same items as first_page
+ reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
+ for idx, reload_id in enumerate(reload_ids):
+ if reload_id == first_page_reload_id:
+ entries.extend(initial_entries)
+ continue
+ _, new_entries = self._extract_entries(
+ 'http://list.youku.com/show/episode', show_id,