python爬虫-2 requests使用

基本用法-获取内容

import requests

headers = {'Accept-Encoding': 'gzip, deflate',
           'Accept-Language': 'zh-CN,zh;q=0.8',
           'Connection': 'keep-alive',
           'content-type': 'application/json',
           'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0',
           'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'}

url = 'http://www.people.com.cn/'
r = requests.get(url=url, headers=headers)
r.encoding='utf-8'
# byte类型内容
# print(str(r.content))
# unicode内容
# print(r.text)
# 响应头
print(r.headers)
# cookies
print(r.cookies)
# 状态码
print(r.status_code)

模拟登录，模拟请求，状态保持等 

#构建一个有Cookie内容的请求
headers_had_JSEID = {'Accept-Encoding':'gzip, deflate','Accept-Language':'zh-CN,zh;q=0.8','Connection':'keep-alive',
            'Cookie':'JSESSIONID='+in_jsessionid,'content-type': 'application/json','User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0',
            'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'}

#get模拟请求
source_xj=requests.get(url_xj,headers=headers_had_JSEID)

 

会话维持

每次get相当于重新用个浏览器访问新网站，Session相当于在网站内浏览不同页面，可以维持之前的记录

# 会话维持
s=requests.Session()
r=s.get(url=url)
print(r.text)