From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/telegraph.co.uk.txt | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/telegraph.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/telegraph.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/telegraph.co.uk.txt b/inc/3rdparty/site_config/standard/telegraph.co.uk.txt old mode 100644 new mode 100755 index e1faf23b..8dcdb42b --- a/inc/3rdparty/site_config/standard/telegraph.co.uk.txt +++ b/inc/3rdparty/site_config/standard/telegraph.co.uk.txt @@ -1,10 +1,10 @@ -body: //div[@class='byline' or @id='storyEmbSlide' or @id='mainBodyArea'] -strip: //p[@class='comments'] -strip: //div[@id='storyEmbSlide']//div[contains(@class, "hide")] -strip: //div[@id='tmg-related-links' or @id='outbrain-related-links' or @id='onespot-related-links'] -strip: //p[@class='bbpTweet']/span[@class='timestamp'] -strip: //p[@class='bbpTweet']/span[@class='metadata']//img -tidy: no -prune: no +body: //div[@class='byline' or @id='storyEmbSlide' or @id='mainBodyArea'] +strip: //p[@class='comments'] +strip: //div[@id='storyEmbSlide']//div[contains(@class, "hide")] +strip: //div[@id='tmg-related-links' or @id='outbrain-related-links' or @id='onespot-related-links'] +strip: //p[@class='bbpTweet']/span[@class='timestamp'] +strip: //p[@class='bbpTweet']/span[@class='metadata']//img +tidy: no +prune: no test_url: http://www.telegraph.co.uk/news/worldnews/europe/ireland/8663451/Is-Ireland-divorcing-from-the-Catholic-Church.html \ No newline at end of file -- cgit v1.2.3