title: //meta[@name="og:title"]/@content body: //div[contains(concat(' ',normalize-space(@class),' '),' content ')] author: //div[contains(concat(' ',normalize-space(@class),' '),' author ')]/a[1] date: substring-before(substring-after(//div[contains(concat(' ',normalize-space(@class),' '),' author ')], ' on '), ' at') date: substring-before(substring-after(//div[contains(concat(' ',normalize-space(@class),' '),' author ')], ' on '), '.') next_page_link: //div[@id='content-bg']/div/div[@id='main-wrap']/div/article/div[@class="foot"]/div/a[@title="Go To Next Page"] find_string: replace_string: " /> test_url: https://www.phoronix.com/scan.php?page=article&item=clear-fall-2020&num=8 test_url: https://www.phoronix.com/news/Linux-6.7-sysctl