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 --- cio.com.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 cio.com.txt (limited to 'cio.com.txt') diff --git a/cio.com.txt b/cio.com.txt new file mode 100644 index 0000000..9898309 --- /dev/null +++ b/cio.com.txt @@ -0,0 +1,17 @@ +# 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