python爬虫利器之requests库的用法(超全面的爬取网页案例)

req = requests.get("https://www.baidu.com/")
req = requests.post("https://www.baidu.com/")
req = requests.put("https://www.baidu.com/")
req = requests.delete("https://www.baidu.com/")
req = requests.head("https://www.baidu.com/")
req = requests.options(https://www.baidu.com/)

import requests
from fake_useragent import UserAgent#请求头部库
headers = {"User-Agent":UserAgent().random}#获取一个随机的请求头
url = "https://www.baidu.com/s"#网址
params={
  "wd":"豆瓣"  #网址的后缀
}

requests.get(url,headers=headers,params=params)

#get请求

headers = {"User-Agent":UserAgent().random}
url = "https://www.baidu.com/s"
params={
  "wd":"豆瓣"
}

response = requests.get(url,headers=headers,params=params)
response.text

import requests 
from fake_useragent import UserAgent

headers = {"User-Agent":UserAgent().random}

url = "https://www.baidu.cn/index/login/login" #登录账号密码的网址
params = {
  "user":"1351351335",#账号
  "password":"123456"#密码
}

response = requests.post(url,headers=headers,data=params)
response.text

#IP代理

import requests 
from fake_useragent import UserAgent

headers = {"User-Agent":UserAgent().random}
url = "http://httpbin.org/get" #返回当前IP的网址

proxies = {
  "http":"http://yonghuming:123456@192.168.1.1:8088"#http://用户名:密码@IP:端口号
  #"http":"https://182.145.31.211:4224"# 或者IP：端口号
}

requests.get(url,headers=headers,proxies=proxies)

#设置访问时间
requests.get("http://baidu.com/",timeout=0.1)

import requests 
from fake_useragent import UserAgent #请求头部库

url = "https://www.12306.cn/index/" #需要证书的网页地址
headers = {"User-Agent":UserAgent().random}#获取一个随机请求头

requests.packages.urllib3.disable_warnings()#禁用安全警告
response = requests.get(url,verify=False,headers=headers)
response.encoding = "utf-8" #用来显示中文，进行转码
response.text

import requests
from fake_useragent import UserAgent

headers = {"User-Agent":UserAgent().chrome}
login_url = "https://www.baidu.cn/index/login/login" #需要登录的网页地址
params = {
  "user":"yonghuming",#用户名
  "password":"123456"#密码
}
session = requests.Session() #用来保存cookie

#直接用session 歹意requests 
response = session.post(login_url,headers=headers,data=params)

info_url = "https://www.baidu.cn/index/user.html" #登录完账号密码以后的网页地址
resp = session.get(info_url,headers=headers)
resp.text

#cookie 

import requests
from fake_useragent import UserAgent

headers = {"User-Agent":UserAgent().chrome}
login_url = "https://passport.zhihuishu.com/login" #需要登录的网页地址
params = {
  "user":"12121212",#用户名
  "password":"123456"#密码
}
session = requests.Session() #用来保存cookie

#直接用session 歹意requests 
response = session.post(login_url,headers=headers,data=params)

info_url = "https://onlne5.zhhuishu.com/onlinWeb.html#/stdetInex" #登录完账号密码以后的网页地址
resp = session.get(info_url,headers=headers)
resp.encoding = "utf-8"
resp.text