import re #正则表达式模块
import urllib.request
import time #时间模块
import string #字符串模块

def getHtml(url):

f=urllib.request.urlopen(url)

print(f.read())

if name == '__main__':
getHtml('http://www.baidu.com/')

下面的是获取网页代码不乱码

import re #正则表达式模块
import urllib.request
import time #时间模块
import string #字符串模块

def getHtml(url):

f=urllib.request.urlopen(url)
print(str(f.read(),'utf-8'))

if name == '__main__':

getHtml('http://www.baidu.com/')

第三种获取网页源代码方法

import requests

req = requests.get("http://news.sina.com.cn/")

if req.encoding == 'ISO-8859-1':

encodings = requests.utils.get_encodings_from_content(req.text)
if encodings:
    encoding = encodings[0]
else:
    encoding = req.apparent_encoding

# encode_content = req.content.decode(encoding, 'replace').encode('utf-8', 'replace')
global encode_content
encode_content = req.content.decode(encoding, 'replace') #如果设置为replace，则会用?取代非法字符；

print(encode_content)

with open('test.html','w',encoding='utf-8') as f:

f.write(encode_content)

赏 支付宝打赏 微信打赏

如果文章或资源对您有帮助，欢迎打赏作者。一路走来，感谢有您！