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/sfgate.com.txt | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/sfgate.com.txt (limited to 'inc/3rdparty/site_config/standard/sfgate.com.txt') diff --git a/inc/3rdparty/site_config/standard/sfgate.com.txt b/inc/3rdparty/site_config/standard/sfgate.com.txt new file mode 100644 index 00000000..5f73fbcb --- /dev/null +++ b/inc/3rdparty/site_config/standard/sfgate.com.txt @@ -0,0 +1,12 @@ +title: /html/head/title + +body: //div[@id = 'articlecontent']/div[contains(@class, 'bodytext')] +author: //div[@class = 'articleheadings']/p[contains(@class,'author')]/span[@class = 'fn'] +date: //div[@class = 'articleheadings']/span[@class = 'updated'] +strip: //div[div[contains(@class, 'imgbox')]] + +body: //div[@class = 'blogitem'] +author: //p[@class="credit"]/span[@class="author"]/a[position() = 1] +date: //span[@class = 'pubdate'] + +test_url: http://www.sfgate.com/columnists/garchik/ \ No newline at end of file -- cgit v1.2.3