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/sfgate.com.txt | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 5f73fbcb..54691122 --- a/inc/3rdparty/site_config/standard/sfgate.com.txt +++ b/inc/3rdparty/site_config/standard/sfgate.com.txt @@ -1,12 +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'] +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