检测网页编码+读取网页内容 原

import chardet #字符集检测 import urllib.request # 网址 url = "http://www.baidu.com/"

def automatic_detect(url):      content=urllib.request.urlopen(url).read()      result=chardet.detect(content)     encoding=result['encoding']      return encoding 

print(url)  print(automatic_detect(url))

# 请求 request = urllib.request.Request(url) # 爬取结果 response = urllib.request.urlopen(request) data = response.read() # 设置解码方式 data = data.decode('utf-8')

# 打印爬取网页的各类信息 # 打印结果 print(data) print(type(response)) print(response.geturl()) print(response.info()) print(response.getcode())

需要安装chardet

(adsbygoogle = window.adsbygoogle || []).push({});