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/telegraaf.nl.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/telegraaf.nl.txt (limited to 'inc/3rdparty/site_config/standard/telegraaf.nl.txt') diff --git a/inc/3rdparty/site_config/standard/telegraaf.nl.txt b/inc/3rdparty/site_config/standard/telegraaf.nl.txt old mode 100644 new mode 100755 index ff3cd06e..91b5baf9 --- a/inc/3rdparty/site_config/standard/telegraaf.nl.txt +++ b/inc/3rdparty/site_config/standard/telegraaf.nl.txt @@ -1,9 +1,9 @@ -body: //div[@id='artikelKolom'] -strip: //div[@class='broodMediaBox']/div[@class='docbox' or @class='artBannerWrapper'] -strip: //div[@id='artikeltoolbar'] -strip: //div[@class='reactiebalk artspacer' or @class='bannercenter clearfix artspacer'] -strip: //div[@id='artikelKolomRechts' or @id='TMGTweetWidget'] -tidy: no -prune: no +body: //div[@id='artikelKolom'] +strip: //div[@class='broodMediaBox']/div[@class='docbox' or @class='artBannerWrapper'] +strip: //div[@id='artikeltoolbar'] +strip: //div[@class='reactiebalk artspacer' or @class='bannercenter clearfix artspacer'] +strip: //div[@id='artikelKolomRechts' or @id='TMGTweetWidget'] +tidy: no +prune: no test_url: http://www.telegraaf.nl/binnenland/10275097/__Identiteit_man_in_sloot_onbekend__.html?cid=rss \ No newline at end of file -- cgit v1.2.3