X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftudou.py;h=2aae55e7e8f8742b471e4f8ffe94ab2ae79bae25;hb=baa3e1845b26d9756642325bbb0d58e22025b2ec;hp=da3cd76f7591a8a9e2c39ba65a47c7855104dcae;hpb=40cf7fcbd2e30747065ca7b8bf4467a9582a4aa9;p=youtube-dl diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index da3cd76f7..2aae55e7e 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -5,7 +5,9 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + ExtractorError, int_or_none, + InAdvancePagedList, float_or_none, unescapeHTML, ) @@ -21,7 +23,7 @@ class TudouIE(InfoExtractor): 'id': '159448201', 'ext': 'f4v', 'title': '卡马乔国足开大脚长传冲吊集锦', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1372113489000, 'description': '卡马乔卡家军,开大脚先进战术不完全集锦!', 'duration': 289.04, @@ -34,7 +36,7 @@ class TudouIE(InfoExtractor): 'id': '117049447', 'ext': 'f4v', 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1349207518000, 'description': 'md5:294612423894260f2dcd5c6c04fe248b', 'duration': 5478.33, @@ -45,11 +47,27 @@ class TudouIE(InfoExtractor): _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' + # Translated from tudou/tools/TVCHelper.as in PortalPlayer_193.swf + # 0001, 0002 and 4001 are not included as they indicate temporary issues + TVC_ERRORS = { + '0003': 'The video is deleted or does not exist', + '1001': 'This video is unavailable due to licensing issues', + '1002': 'This video is unavailable as it\'s under review', + '1003': 'This video is unavailable as it\'s under review', + '3001': 'Password required', + '5001': 'This video is available in Mainland China only due to licensing issues', + '7001': 'This video is unavailable', + '8001': 'This video is unavailable due to licensing issues', + } + def _url_for_id(self, video_id, quality=None): 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') + error = xml_data.attrib.get('error') + if error is not None: + raise ExtractorError('Tudou said: %s' % error, expected=True) final_url = xml_data.text return final_url @@ -62,6 +80,15 @@ class TudouIE(InfoExtractor): if youku_vcode: return self.url_result('youku:' + youku_vcode, ie='Youku') + if not item_data.get('itemSegs'): + tvc_code = item_data.get('tvcCode') + if tvc_code: + err_msg = self.TVC_ERRORS.get(tvc_code) + if err_msg: + raise ExtractorError('Tudou said: %s' % err_msg, expected=True) + raise ExtractorError('Unexpected error %s returned from Tudou' % tvc_code) + raise ExtractorError('Unxpected error returned from Tudou') + title = unescapeHTML(item_data['kw']) description = item_data.get('desc') thumbnail_url = item_data.get('pic') @@ -75,15 +102,16 @@ class TudouIE(InfoExtractor): quality = sorted(filter(lambda k: k.isdigit(), segments.keys()), key=lambda k: int(k))[-1] parts = segments[quality] - result = [] len_parts = len(parts) if len_parts > 1: self.to_screen('%s: found %s parts' % (video_id, len_parts)) - for part in parts: + + def part_func(partnum): + part = parts[partnum] part_id = part['k'] final_url = self._url_for_id(part_id, quality) ext = (final_url.split('?')[0]).split('.')[-1] - part_info = { + return [{ 'id': '%s' % part_id, 'url': final_url, 'ext': ext, @@ -97,12 +125,13 @@ class TudouIE(InfoExtractor): 'http_headers': { 'Referer': self._PLAYER_URL, }, - } - result.append(part_info) + }] + + entries = InAdvancePagedList(part_func, len_parts, 1) return { '_type': 'multi_video', - 'entries': result, + 'entries': entries, 'id': video_id, 'title': title, }