python模拟浏览器爬取数据

#coding=utf-8
import requests
from bs4 import BeautifulSoup

headers = {‘Accept‘:‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘,
        ‘Accept-Encoding‘:‘gzip,deflate,sdch‘,
        ‘Accept-Language‘:‘en,zh-CN;q=0.8,zh;q=0.6‘,
        ‘Cache-Control‘:‘max-age=0‘,
        ‘Host‘:‘www.xxx.com‘,   #此处为财经网的主页
        ‘Connection‘:‘keep-alive‘,
         ‘Upgrade-Insecure-Requests‘:‘1‘,
        ‘Content-Type‘:‘application/x-www-form-urlencoded‘,
        ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.131 Safari/537.36‘
    }
response = requests.get("http://www.xxxxxx.com", headers=headers) #请求的地址
soup = BeautifulSoup(response.content, ‘html.parser‘)  #返回的html信息用soup解析
print(response.status_code)  #请求状态码
print(soup.prettify())　　#以格式输出html