X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftudou.py;h=f56b66d06f2f7323b60d2fc4788d26cb3274ef9e;hb=611c1dd96efc36a788475e14cc4de64d554d28a0;hp=5f7ac4b35b6c4576e5fb0998d56eb21ec522b58a;hpb=dade7245af16c4167575bb3759e7e64011602043;p=youtube-dl diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 5f7ac4b35..f56b66d06 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -4,10 +4,16 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, + unescapeHTML, +) class TudouIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/([^/]+/)*(?P[^/?#]+?)(?:\.html)?/?(?:$|[?#])' + IE_NAME = 'tudou' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P[\w-]{11})' _TESTS = [{ 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'md5': '140a49ed444bd22f93330985d8475fcb', @@ -16,6 +22,11 @@ class TudouIE(InfoExtractor): 'ext': 'f4v', 'title': '卡马乔国足开大脚长传冲吊集锦', 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1372113489000, + 'description': '卡马乔卡家军，开大脚先进战术不完全集锦！', + 'duration': 289.04, + 'view_count': int, + 'filesize': int, } }, { 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/', @@ -24,10 +35,12 @@ class TudouIE(InfoExtractor): 'ext': 'f4v', 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1349207518000, + 'description': 'md5:294612423894260f2dcd5c6c04fe248b', + 'duration': 5478.33, + 'view_count': int, + 'filesize': int, } - }, { - 'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html', - 'only_matching': True, }] _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' @@ -36,30 +49,26 @@ class TudouIE(InfoExtractor): info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id) if quality: info_url += '&hd' + quality - xml_data = self._download_xml(info_url, video_id, "Opening the info XML page") + xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page') final_url = xml_data.text return final_url def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + item_data = self._download_json( + 'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id) - youku_vcode = self._search_regex( - r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None) + youku_vcode = item_data.get('vcode') if youku_vcode: return self.url_result('youku:' + youku_vcode, ie='Youku') - title = self._search_regex( - r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title') - thumbnail_url = self._search_regex( - r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False) - - player_url = self._search_regex( - r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]', - webpage, 'player URL', default=self._PLAYER_URL) + title = unescapeHTML(item_data['kw']) + description = item_data.get('desc') + thumbnail_url = item_data.get('pic') + view_count = int_or_none(item_data.get('playTimes')) + timestamp = int_or_none(item_data.get('pt')) - segments = self._parse_json(self._search_regex( - r'segs: \'([^\']+)\'', webpage, 'segments'), video_id) + segments = self._parse_json(item_data['itemSegs'], video_id) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher # Also, filter non-number qualities (see issue #3643). @@ -80,8 +89,13 @@ class TudouIE(InfoExtractor): 'ext': ext, 'title': title, 'thumbnail': thumbnail_url, + 'description': description, + 'view_count': view_count, + 'timestamp': timestamp, + 'duration': float_or_none(part.get('seconds'), 1000), + 'filesize': int_or_none(part.get('size')), 'http_headers': { - 'Referer': player_url, + 'Referer': self._PLAYER_URL, }, } result.append(part_info) @@ -92,3 +106,47 @@ class TudouIE(InfoExtractor): 'id': video_id, 'title': title, } + + +class TudouPlaylistIE(InfoExtractor): + IE_NAME = 'tudou:playlist' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P[\w-]{11})\.html' + _TESTS = [{ + 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html', + 'info_dict': { + 'id': 'zzdE77v6Mmo', + }, + 'playlist_mincount': 209, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + playlist_data = self._download_json( + 'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id) + entries = [self.url_result( + 'http://www.tudou.com/programs/view/%s' % item['icode'], + 'Tudou', item['icode'], + item['kw']) for item in playlist_data['items']] + return self.playlist_result(entries, playlist_id) + + +class TudouAlbumIE(InfoExtractor): + IE_NAME = 'tudou:album' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P[\w-]{11})' + _TESTS = [{ + 'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html', + 'info_dict': { + 'id': 'v5qckFJvNJg', + }, + 'playlist_mincount': 45, + }] + + def _real_extract(self, url): + album_id = self._match_id(url) + album_data = self._download_json( + 'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id) + entries = [self.url_result( + 'http://www.tudou.com/programs/view/%s' % item['icode'], + 'Tudou', item['icode'], + item['kw']) for item in album_data['items']] + return self.playlist_result(entries, album_id)