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 --- .../site_config/standard/joelonsoftware.com.txt | 38 +++++++++++----------- 1 file changed, 19 insertions(+), 19 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 75fbee5a..241a361f --- a/inc/3rdparty/site_config/standard/joelonsoftware.com.txt +++ b/inc/3rdparty/site_config/standard/joelonsoftware.com.txt @@ -1,21 +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] +# 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