requests模块学习

requests

1. response = request.get(url)
2. print(response) // 获取请求状态码
3. response.text
4. response.encoding // 推测网页编码
5. response.content // byte形式显示原始网页
6. response.content.decode（） //解码

p = requests.get("https://www.sina.com.cn/")
print(p)
p.text
p.content.endoce()
p.ecoding
p.ecode
p.encoding
p.content.decode(encoding='ISO-8859-1')
p.content.decode(encoding='utf-8')

7.存储图片

with open("a.png","wb") as f:
    f.write(img1.content)

8.贴吧爬取实例

# -*- coding: utf-8 -*-
"""
Created on Wed Feb 26 09:16:08 2020

@author: Administrator
"""
import requests
import os
os.chdir(r"H:\实操\学习\01\spyder")
class TieSpyder:
    def __init__(self,name):
        self.name = name
        self.url_temp = "https://tieba.baidu.com/f?kw="+self.name+"&ie=utf-8&pn={}"
        self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'}
    #获取url_list池塘
    def get_url_list(self):
        url_list = []
        for i in range(0,1000):
            url_list.append(self.url_temp.format(i*50))
        return url_list
        
    def html_parse(self,url):
        print(url)
        response = requests.get(url,self.headers)
        return response.content.decode()   
        
    def save_html(self,html_str,pageNum):
        
        filepath = "{}-第{}页".format(self.name,pageNum)
        with open(filepath,"w",encoding = "utf-8") as f:
            f.write(html_str)
        
    def run(self):
        pageNum = 1
        #1.获取url_list
        url_list = self.get_url_list()
        #2.遍历list，发送请求，获取响应
        for url in url_list:
            html_str = self.html_parse(url)    
        #3.存储数据
            self.save_html(html_str,pageNum)
            pageNum++
            

if __name__ =="__main__":
    liyi = TieSpyder("摄影")
    liyi.run()

-----------视频学习 小酥仙儿 2020.2.26------------------------------------------------------------------

来源：CSDN

作者：小酥仙儿

链接：https://blog.csdn.net/qq_40278637/article/details/104510452