From 853784301c1e822d6c2ced7082db93a5e0e0a973 Mon Sep 17 00:00:00 2001 From: coolius Date: Wed, 20 Aug 2014 14:35:23 +0100 Subject: Create bit-tech.net.txt --- bit-tech.net.txt | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 bit-tech.net.txt diff --git a/bit-tech.net.txt b/bit-tech.net.txt new file mode 100644 index 0000000..c6f5b20 --- /dev/null +++ b/bit-tech.net.txt @@ -0,0 +1,19 @@ +body: //div[@id='column_1'] +next_page_link: //div[@class='next']/a[not(contains(@href, '/comments') or contains(@href, '/news/'))] +prune: no + +author: substring-after(//p[@class='byline'], 'by ') +date: substring-before(substring-after(//p[@class='byline'], 'on '), ' by') + +strip: //h1 +strip_id_or_class: socialLinks +strip_id_or_class: byline +strip_id_or_class: pageSelector +strip_id_or_class: articleTabs +strip_id_or_class: pageNav +strip_id_or_class: share +strip_id_or_class: commentsContainer +strip_id_or_class: below_article_related + +test_url: http://www.bit-tech.net/hardware/storage/2014/08/13/ocz-arc-100-240gb-review/1 +test_url: http://www.bit-tech.net/news/bits/2014/08/15/google-trojan/1 -- cgit v1.3.1