From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/latimes.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..0d6ac851 --- /dev/null +++ b/inc/3rdparty/site_config/standard/latimes.com.txt @@ -0,0 +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_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