title:
    xpath: //title/text()
host: https://www.xxx.com
noise_node_list:
    - //div[@class=\"comment-list\"]
    - //*[@style=\"display:none\"]
    - //*[@class="contheight"]
body:
    xpath: //div[@class="news_txt"]
with_body_html: false
author:
    xpath: //meta[@name="author"]/@content
publish_time:
    xpath: //em[@id="publish_time"]/text()