Python爬虫requests库多种用法实例

#requests模块

import requests

#发送请求 content:以二进制的形式获取网页的内容
response=requests.get("http://www.baidu.com").content.decode()
#response=requests.request("get","http://www.baidu.com").content.decode()

print(response)

import requests

url="http://www.baidu.com/s?"

headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/81.0.4044.138 Safari/537.36"
}
wd={"wd":"中国"}
response=requests.get(url,params=wd,headers=headers)
# 返回一个字符串形式的数据
data=response.text
# 返回一个二进制形式的数据
data2=response.content
print(data2.decode())

import requests
import re

#构造请求头信息
header={
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/81.0.4044.122 Safari/537.36"
}#谷歌浏览器

#http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule 网页上的url
url="http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"

key="靓仔"

#发送到web服务器的表单数据
formdata={
"i":key,
"from":"AUTO",
"to":"AUTO",
"smartresult":"dict",
"client":"fanyideskweb",
"salt":"15880563488791",
"sign":"cc2c40d740538fc5edc0380891faef27",
"ts":"1588053583943",
"bv":"f9c86b1fdf2f53c1fefaef343285247b",
"doctype":"json",
"version":"2.1",
"keyfrom":"fanyi.web",
"action":"FY_BY_REALTlME"

}

response=requests.post(url,headers=header,data=formdata)

# 获取到的是json数据
# 对应的是字典
# print(response.json())

pat=r'"tgt":"(.*?)"}]]' #字符串中有"",再用''括起来表示字符串

# 获取到的是字符串
result=re.findall(pat,response.text)

print(result[0])

import requests

#设置ip地址
#proxy={"http":"http://代理ip地址:端口号"}
#可以设置多个
proxy={
"http":"http://222.82.130.23:8060",
"http":"http://101.248.64.68:80",
}

response=requests.get("http://www.baidu.com",proxies=proxy)

print(response.content.decode())

import requests
response=requests.get("http://www.baidu.com")
#1.获取返回的cooketjar对象
cookiejar=response.cookies
#2.将cookiejar转换成字典
cookiedict=requests.utils.dict_from_cookiejar(cookiejar)
print(cookiedict)

#使用session实现登陆

import requests

#构造请求头信息
header={
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/81.0.4044.122 Safari/537.36"
}#谷歌浏览器

#创建session对象
ses=requests.session()

#构造登陆需要的参数
data={"email":"325*****@qq.com","password":"123321a"}

#通过传递用户名密码得到cookie信息
ses.post("http://www.renren.com/PLogin.do",data=data,headers=header)

#请求需要的页面,每次请求会带入cookie信息
response=ses.get("http://www.renren.com/880151247/profile")

print(response.text)