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/baltimoresun.com.txt | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/baltimoresun.com.txt (limited to 'inc/3rdparty/site_config/standard/baltimoresun.com.txt') diff --git a/inc/3rdparty/site_config/standard/baltimoresun.com.txt b/inc/3rdparty/site_config/standard/baltimoresun.com.txt new file mode 100644 index 00000000..32adff8d --- /dev/null +++ b/inc/3rdparty/site_config/standard/baltimoresun.com.txt @@ -0,0 +1,12 @@ +single_page_link: //div[@class='toppaginate']//a[@rel='nofollow'] +convert_double_br_tags: yes + +title: //div[@class="story"]/h1 +body: //div[@id="story-body-text"] +author: //span[@class="byline"] +date: //p[@class="date"] + +strip: //*[@class='all'] +strip: //*[@class='articlerail'] + +test_url: http://www.baltimoresun.com/news/maryland/bs-md-omalley-budget-2-20120116,0,5340585.story \ No newline at end of file -- cgit v1.2.3