使用xpath解析网页

最新推荐文章于 2025-01-06 11:58:31 发布

原创最新推荐文章于 2025-01-06 11:58:31 发布 · 273 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#xpath #html #js #linux #url

#!/usr/bin/python

# -*- coding: utf-8 -*- 

from lxml import etree
import requests


base_url = 'http://www.yinhangzhaopin.com/'

move_url = "http://www.yinhangzhaopin.com/tag/changsha_119_1.html"

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0'}
sourceHtml = requests.get(move_url, headers=headers)
    
html = etree.HTML(sourceHtml.text)

final_result = []

for i in range(1,20):
    xxpath = ".//*[@id='midder']/div[1]/div/div[3]/dl[" + str(i) + "]/dt/a"
    result = html.xpath(xxpath)
    xxx = result[0]
    result_text = xxx.attrib['title']
    result_url = base_url + xxx.attrib['href']
    result_dict = {result_text:result_url}
    final_result.append(result_dict)