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 --- .../site_config/standard/joelonsoftware.com.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/joelonsoftware.com.txt (limited to 'inc/3rdparty/site_config/standard/joelonsoftware.com.txt') diff --git a/inc/3rdparty/site_config/standard/joelonsoftware.com.txt b/inc/3rdparty/site_config/standard/joelonsoftware.com.txt new file mode 100644 index 00000000..75fbee5a --- /dev/null +++ b/inc/3rdparty/site_config/standard/joelonsoftware.com.txt @@ -0,0 +1,21 @@ +# Works with old posts too, such as http://www.joelonsoftware.com/articles/fog0000000332.html + +author: substring-after(//div[@class="author"], 'by ') +date: //div[@class="date"] + +## Clean stuff at top ## + +strip: //h1[1] +strip: //h2[1] +strip: //div[@class="date"] +strip: //div[@class="author"] + +## Clean stuff at bottom ## + +strip: //blockquote[@class="textmessage"] +strip: //div[@style="width:500px"]/p[last()] +strip: //div[@style="width:500px"]/p[last()-1] +strip: //div[@style="width:500px"]/h4[last()] +strip: //div[@style="width:500px"]/h4[last()-1] +strip: //div[@style="width:500px"]/div[last()] +test_url: http://www.joelonsoftware.com/items/2011/09/15.html \ No newline at end of file -- cgit v1.2.3