第一步：requests

get請求

# -*- coding:utf-8  -*-
# 日期：2018/5/15 17:46
# Author:小鼠標
import requests
url = "http://www.baidu.com"

#res = requests.get(url)　　#方法1

res = requests.request(‘get‘,url) #方法2

print(‘響應狀態碼：‘,res.status_code) print(‘響應內容：‘,res.text)

post請求

# -*- coding:utf-8  -*-
# 日期：2018/5/15 17:46
# Author:小鼠標
 

import requests
url = "http://www.baidu.com"
data = {
    ‘username‘: ‘xiaoshubiao‘,
    ‘pwd‘: ‘xiaoshubiao‘
}
res = requests.post(url,data)
print(‘響應狀態碼：‘,res.status_code)
print(‘響應內容：‘,res.text)

第二步：偽裝瀏覽器和偽造cookie

# -*- coding:utf-8  -*-
# 日期：2018/5/15 17:46
# Author:小鼠標
import requests
url = "http://www.baidu.com
 
"
headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36‘
                         ‘ (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.39‘
                         ‘64.2 Safari/537.36‘,
            ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0‘
                      ‘
 
.9,image/webp,*/*;q=0.8‘,
            ‘Accept-Encoding‘: ‘gzip, deflate, sdch‘,
            ‘Accept-Language‘: ‘zh-CN,zh;q=0.8,en;q=0.6‘,
            ‘Cache-Control‘: ‘max-age=0‘,
            ‘Connection‘: ‘keep-alive‘
          }
cookies = dict(name=‘xiaoshubiao‘)
res = requests.get(url,headers = headers,cookies = cookies)
print(‘響應狀態碼：‘,res.status_code)
print(‘響應內容：‘,res.text)

第三步：使用代理ip

# -*- coding:utf-8  -*-
# 日期：2018/5/15 17:46
# Author:小鼠標
import requests
url = "http://www.baidu.com"
headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36‘
                         ‘ (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.39‘
                         ‘64.2 Safari/537.36‘,
            ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0‘
                      ‘.9,image/webp,*/*;q=0.8‘,
            ‘Accept-Encoding‘: ‘gzip, deflate, sdch‘,
            ‘Accept-Language‘: ‘zh-CN,zh;q=0.8,en;q=0.6‘,
            ‘Cache-Control‘: ‘max-age=0‘,
            ‘Connection‘: ‘keep-alive‘
            }
cookies = dict(name=‘xiaoshubiao‘)
proxies = {‘http‘:‘218.73.134.234:36602‘}
res = requests.get(url,headers = headers,cookies = cookies,proxies = proxies)
print(‘響應狀態碼：‘,res.status_code)
print(‘響應內容：‘,res.text)

學習筆記 requests + BeautifulSoup