# 需求:获取网页,用requests import requests url = "http://www.baidu.com/" resp = requests.get(url) resp.encoding = "utf-8" # 抓取内容写入文件 with open("mybaidu222.html",mode="w",encoding="utf-8") as f: f.write(resp.text) print("over!")
# 需求:搜狗搜索内容爬取,用requests # 1、安装requests # 2、导入requests # 3、准备URL;加入headers处理反爬;获取get请求返回的值;拿到页面源代码 import requests query = input("输入你的查询内容:") url = f'https://www.sogou.com/web?query={query}' # 加header伪装成浏览器发送请求,绕过反爬 header = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36" } resp = requests.get(url=url,headers=header) print(resp.text) resp.close() #关掉resp
实例来源:https://www.bilibili.com/video/BV1i54y1h75W?p=1