From d59536deea443f4bdac2c5cf1bfeea690810a817 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Si=C3=B4n=20Le=20Roux?= Date: Thu, 10 Jul 2014 18:30:44 +0200 Subject: [PATCH] Add support for *.about.com Includes next_page_link for multi-page articles and strips pesky in-line 'next' links from the article body. Also includes an Xpath for author but I can't see where this is used in the wallabag UI. The 'tidy' option is turned off because it messed up bulleted lists. Tested with psychology.about.com and food.about.com. --- inc/3rdparty/site_config/standard/.about.com.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/.about.com.txt diff --git a/inc/3rdparty/site_config/standard/.about.com.txt b/inc/3rdparty/site_config/standard/.about.com.txt new file mode 100644 index 0000000..e1ebaee --- /dev/null +++ b/inc/3rdparty/site_config/standard/.about.com.txt @@ -0,0 +1,14 @@ +body: //div[@id='articlebody'] +title: //h1 +author: //p[@id='by']//a + +next_page_link: //span[@class='next']/a +# Not the same as below! + +prune: yes +tidy: no + +# Annoying 'next' links plainly inside the article body +strip: //*[text()[contains(.,'Next: ')]] + +test_url: http://psychology.about.com/od/theoriesofpersonality/ss/defensemech.htm