#!/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)
image.png
