+
+
+class YoukuShowIE(InfoExtractor):
+ _VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
+ IE_NAME = 'youku:show'
+
+ _TESTS = [{
+ 'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
+ 'info_dict': {
+ 'id': 'zc7c670be07ff11e48b3f',
+ 'title': '花千骨 DVD版',
+ 'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
+ },
+ 'playlist_count': 50,
+ }, {
+ # Episode number not starting from 1
+ 'url': 'http://list.youku.com/show/id_zefbfbd70efbfbd780bef.html',
+ 'info_dict': {
+ 'id': 'zefbfbd70efbfbd780bef',
+ 'title': '超级飞侠3',
+ 'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
+ },
+ 'playlist_count': 24,
+ }, {
+ # Ongoing playlist. The initial page is the last one
+ 'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
+ 'only_matchine': True,
+ }]
+
+ def _extract_entries(self, playlist_data_url, show_id, note, query):
+ query['callback'] = 'cb'
+ playlist_data = self._download_json(
+ playlist_data_url, show_id, query=query, note=note,
+ transform_source=lambda s: js_to_json(strip_jsonp(s)))['html']
+ drama_list = (get_element_by_class('p-drama-grid', playlist_data) or
+ get_element_by_class('p-drama-half-row', playlist_data))
+ if drama_list is None:
+ raise ExtractorError('No episodes found')
+ video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
+ return playlist_data, [
+ self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
+ for video_url in video_urls]
+
+ def _real_extract(self, url):
+ show_id = self._match_id(url)
+ webpage = self._download_webpage(url, show_id)
+
+ entries = []
+ page_config = self._parse_json(self._search_regex(
+ r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
+ show_id, transform_source=js_to_json)
+ 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,
+ note='Downloading playlist data page %d' % (idx + 1),
+ query={
+ 'id': page_config['showid'],
+ 'stage': reload_id,
+ })
+ entries.extend(new_entries)
+
+ desc = self._html_search_meta('description', webpage, fatal=False)
+ playlist_title = desc.split(',')[0] if desc else None
+ detail_li = get_element_by_class('p-intro', webpage)
+ playlist_description = get_element_by_class(
+ 'intro-more', detail_li) if detail_li else None
+
+ return self.playlist_result(
+ entries, show_id, playlist_title, playlist_description)
Rapsys Git / youtubedl / blobdiff