第一步:requests
get请求
# -*- coding:utf-8 -*-
# 日期:2018/5/15 17:46
# Author:小鼠标
import requests
url = "http://www.baidu.com"
#res = requests.get(url) #方法1 res = requests.request('get',url) #方法2
print('响应状态码:',res.status_code) print('响应内容:',res.text)
post请求
# -*- coding:utf-8 -*-
# 日期:2018/5/15 17:46
# Author:小鼠标
import requests
url = "http://www.baidu.com"
data = {
'username': 'xiaoshubiao',
'pwd': 'xiaoshubiao'
}
res = requests.post(url,data)
print('响应状态码:',res.status_code)
print('响应内容:',res.text)
第二步:伪装浏览器和伪造cookie
# -*- coding:utf-8 -*-
# 日期:2018/5/15 17:46
# Author:小鼠标
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('响应状态码:',res.status_code)
print('响应内容:',res.text)
第三步:使用代理ip
# -*- coding:utf-8 -*-
# 日期:2018/5/15 17:46
# Author:小鼠标
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('响应状态码:',res.status_code)
print('响应内容:',res.text)
第四步:内容解析
# -*- coding:utf-8 -*-
# 日期:2018/5/15 17:46
# Author:小鼠标
import requests
from bs4 import BeautifulSoup
url = "http://news.sina.com.cn/guide/"
res = requests.get(url)
res.encoding = 'utf-8'
web_data = res.text
#内容解析
soup = BeautifulSoup(web_data,'lxml')
title_list = soup.select('title') #获取标签内容 返回为列表
a_list = soup.select('a')
ul_list = soup.select('ul.list01') #获取类名为list01的ul的内容 返回为列表
div_list = soup.select('div#tab01') #获取id为tab01的内容 返回为列表
for title , a in zip(title_list,a_list):
title_content = title.get_text() #获取标签内容的值
a_href = a.get('href') #获取标签的属性的值
print(title_content,a_href)