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/latimes.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/latimes.com.txt (limited to 'inc/3rdparty/site_config/standard/latimes.com.txt') diff --git a/inc/3rdparty/site_config/standard/latimes.com.txt b/inc/3rdparty/site_config/standard/latimes.com.txt old mode 100644 new mode 100755 index 0d6ac851..b2db37bf --- a/inc/3rdparty/site_config/standard/latimes.com.txt +++ b/inc/3rdparty/site_config/standard/latimes.com.txt @@ -1,11 +1,11 @@ -strip: //div[@id="tugs_story_display"] -strip: //div[@id="search_overlay"] -strip: //div[@id="adv_search"] -body: //div[@class='story'] -tidy: no -convert_double_br_tags: yes -single_page_link: //a[contains(@href, ',print.')] -strip: //p[starts-with(., 'latimes.com')] -strip: //h1[starts-with(., 'latimes.com')] +strip: //div[@id="tugs_story_display"] +strip: //div[@id="search_overlay"] +strip: //div[@id="adv_search"] +body: //div[@class='story'] +tidy: no +convert_double_br_tags: yes +single_page_link: //a[contains(@href, ',print.')] +strip: //p[starts-with(., 'latimes.com')] +strip: //h1[starts-with(., 'latimes.com')] strip_id_or_class: cubead test_url: http://www.latimes.com/news/opinion/commentary/la-oe-gartonash-wilders-20110512,0,2876761.story \ No newline at end of file -- cgit v1.2.3