From 87eeefe9a1fa4d55c93a209314dcc5834a2e2391 Mon Sep 17 00:00:00 2001 From: Jordi De Groof Date: Mon, 31 Aug 2015 17:19:45 +0200 Subject: All sites in the IDG network have the same structure --- infoworld.com.txt | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'infoworld.com.txt') diff --git a/infoworld.com.txt b/infoworld.com.txt index d335bc4..9898309 100644 --- a/infoworld.com.txt +++ b/infoworld.com.txt @@ -1,12 +1,17 @@ -body: //div[@id='main_text'] -title: //div[@id='main_text']/h1 -strip: //div[@id='main_text']/h1 -strip: //div[@id='main_text']/h2 -strip_id_or_class: tools -strip_id_or_class: articleTools -strip_id_or_class: pagination -strip_id_or_class: byline -strip_id_or_class: tweet -date: //div[@class='date'] -strip: //div[@class='date'] -test_url: http://www.infoworld.com/d/the-industry-standard/it-jobs-the-rise-both-offshore-and-in-us-187689 \ No newline at end of file +# All sites of the IDG network can be extracted using the same rules, +# make sure to update all of them + +author: //meta[@name="author"]/@content +date: //meta[@name="DC.date.issued"]/@content + +body: //div[@itemprop="articleBody"] +body: //div[@itemprop="reviewBody"] +body: //figcaption|//div[@class="img-wrapper"]/noscript/img + +next_page_link: //a[@rel="next"] + +strip: //aside +strip: //h3[contains(., "See also:")] +strip: //div[@id="article-top-page-number"] +strip: //p[starts-with(normalize-space(.), '[')] +strip: //p[starts-with(normalize-space(.), '+')] -- cgit v1.3.1