htmlparsing0.1.0 release! 添加类似 restful 的语法解析网页.

Github: https://github.com/gaojiuli/htmlparsing

解析列表

import requests
from htmlparsing import Element, HTMLParsing, Text, Attr, Parse, HTML, Markdown

url = 'https://news.ycombinator.com/'
r = requests.get(url)
article_list = HTMLParsing(r.text).list('.athing', {'title': Text('a.storylink'), # css selector
                                                    'link': Attr('a.storylink', 'href')})
print(article_list)

解析详情

import requests
from htmlparsing import Element, HTMLParsing, Text, Attr, Parse

url = 'https://news.ycombinator.com/item?id=16476454'
r = requests.get(url)
article_detail = HTMLParsing(r.text).detail({'title': Text('a.storylink'),
                                             'points': Parse('span.score', '>{} points'),
                                             'link': Attr('a.storylink', 'href')})
print(article_detail)