From 5b012dfce87e4f7dd9ab4a2f5a01ab8f2e16adad Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 1 Apr 2016 01:42:16 +0800 Subject: [PATCH] [tudou] Improve error handling (closes #8988) --- youtube_dl/extractor/tudou.py | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 9892e8a62..63b5d5924 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + ExtractorError, int_or_none, InAdvancePagedList, float_or_none, @@ -46,6 +47,19 @@ 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: @@ -63,6 +77,15 @@ def _real_extract(self, url): 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')