url |
^https?://www\.huffingtonpost\.jp/(entry|[0-9]*)/ |
pageElement |
//div[contains(@class,'post-contents')]/*[not(self::figure) and not(contains(@class,'related-entries')) and not(contains(@class,'extra-content')) and not(contains(@class,'ad_spot'))] |
title |
//h1[contains(@class,'headline__title')] |
subtitle |
//h2[contains(@class,'headline__subtitle')] |
author |
//span[contains(@class,'author-card__details__name')] |
tag |
//div[contains(@class,'tag-cloud')]/a[contains(@class,'tag')] |
exampleUrl |
https://www.huffingtonpost.jp/2018/07/17/school-ac_a_23483652/ |