# 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(.), '+')] test_url: http://www.csoonline.com/article/3168357/security/windows-trojan-hacks-into-embedded-devices-to-install-mirai.html