From 34568dc2967d227630ed9d7150deaa62a689b937 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sun, 17 Feb 2019 13:39:00 +0700
Subject: [PATCH] [tvp] Detect unavailable videos
---
youtube_dl/extractor/tvp.py | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py
index f9bf600b0..536b580fc 100644
--- a/youtube_dl/extractor/tvp.py
+++ b/youtube_dl/extractor/tvp.py
@@ -98,6 +98,7 @@ class TVPEmbedIE(InfoExtractor):
'title': 'Czas honoru, odc. 13 – Władek',
},
}, {
+ # not available
'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
'md5': '8c9cd59d16edabf39331f93bf8a766c7',
'info_dict': {
@@ -105,6 +106,7 @@ class TVPEmbedIE(InfoExtractor):
'ext': 'mp4',
'title': 'Panorama, 07.12.2015, 15:40',
},
+ 'skip': 'Transmisja została zakończona lub materiał niedostępny',
}, {
'url': 'tvp:22670268',
'only_matching': True,
@@ -116,10 +118,13 @@ class TVPEmbedIE(InfoExtractor):
webpage = self._download_webpage(
'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)
- error_massage = get_element_by_attribute('class', 'msg error', webpage)
- if error_massage:
+ error = self._html_search_regex(
+ r'(?s)<p[^>]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)</p>',
+ webpage, 'error', default=None) or clean_html(
+ get_element_by_attribute('class', 'msg error', webpage))
+ if error:
raise ExtractorError('%s said: %s' % (
- self.IE_NAME, clean_html(error_massage)), expected=True)
+ self.IE_NAME, clean_html(error)), expected=True)
title = self._search_regex(
r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',