第一步：

get

# -*- coding:utf-8  -*-
# 日期：2018/5/15 19:39
# Author:小鼠標
from urllib import request

url = ‘http://news.sina.com.cn/guide/‘
response = request.urlopen(url)  #返回http對象
web_data = response.read().decode(‘utf-8‘)  #響應內容
web_status = response.status                #響應狀態碼
print(web_status,web_data)

post

# -*- coding:utf-8  -*-
# 日期：2018/5/15 19:39
# Author:小鼠標
from urllib import request,parse

url = ‘http://news.sina.com.cn/guide/‘
#post表單提交的內容
data = [
    (‘name‘,‘xiaoshubiao‘),
    (‘pwd‘,‘xiaoshubiao‘)
]
login_data = parse.urlencode(data).encode(‘utf-8‘)
response = request.urlopen(url,data = login_data)  #
 
返回http對象
web_data = response.read().decode(‘utf-8‘)  #響應內容
web_status = response.status                #響應狀態碼
print(web_status,web_data)

第二步：偽裝瀏覽器

# -*- coding:utf-8  -*-
# 日期：2018/5/15 19:39
# Author:小鼠標
from urllib import request,parse

url = ‘http://news.sina.com.cn/guide/‘
req = request.Request(url) 
req.add_header(
 
‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36‘)
req.add_header(‘Accept‘,‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘)
response = request.urlopen(req)
web_data = response.read().decode(‘utf-8‘)  #響應內容
web_status = response.status                #響應狀態碼
print(web_status,web_data)

第三步：使用代理ip

# -*- coding:utf-8  -*-
# 日期：2018/5/15 19:39
# Author:小鼠標
from urllib import request,parse

url = ‘http://news.sina.com.cn/guide/‘
req = request.Request(url)
#使用代理ip
proxy = request.ProxyHandler({‘http‘:‘221.207.29.185:80‘})
opener = request.build_opener(proxy, request.HTTPHandler)
request.install_opener(opener)

req.add_header(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36‘)
req.add_header(‘Accept‘,‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘)
response = request.urlopen(req)
web_data = response.read().decode(‘utf-8‘)  #響應內容
web_status = response.status                #響應狀態碼
print(web_status,web_data)

第四步：內容解析

　　可以使用封裝好的BeautifulSoup，也可以使用re正則來匹配，原理都差不多。

學習筆記 urllib