Python基于BeautifulSoup和requests实现的爬虫功能示例

# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
url = 'http://www.qianlima.com/zb/area_305/'
user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'
headers = { 'User-Agent' : user_agent}
r = requests.get(url,headers=headers)#连接
content = r.text#获取内容，自动转码unicode
soup = BeautifulSoup(content,"lxml")
tags1 = soup.select('div .shixian_zhaobiao')
tag1 = tags1[0]
tag2 = tag1.find(name = 'dl')
tags2 = tag2.find_all(name = 'a')
tags3 = tag2.find_all(name = 'dd')
for tag in tags2:
 print tag.get('href')
 print tag.string
 print tag.next_element.next_element.string