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/bizjournals.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/bizjournals.com.txt (limited to 'inc/3rdparty/site_config/standard/bizjournals.com.txt') diff --git a/inc/3rdparty/site_config/standard/bizjournals.com.txt b/inc/3rdparty/site_config/standard/bizjournals.com.txt new file mode 100755 index 00000000..cfba766f --- /dev/null +++ b/inc/3rdparty/site_config/standard/bizjournals.com.txt @@ -0,0 +1,13 @@ +date: //meta[@name='publish-date']/@content +body: //div[contains(@class, 'articleContentWrapper')] +prune: no + +strip: //div[contains(@class, 'staff_info')]//dd[contains(., 'Twitter')] + +strip_id_or_class: related_content +strip_id_or_class: enlarge +strip_id_or_class: photoBy +strip_id_or_class: older + +test_url: http://www.bizjournals.com/cincinnati/news/2013/10/03/harris-teeter-shareholders-vote-on.html +test_url: http://feeds.bizjournals.com/industry_20?format=xml \ No newline at end of file -- cgit v1.2.3