python爬虫代码_网络爬虫python代码

python爬虫主要需要urllib

方法1

import urllib.parse,urllib.request
import ssl ssl._create_default_https_context = ssl._create_unverified_context
req = urllib.request.Request(url = url,headers = headers)
response = urllib.request.urlopen(req)
return response.read().decode(coding)

方法2

#导入包
 
import urllib.request
 
#函数
 
def main():
 
    preservation()
 
def gethtml_http(url):
 
    try:
 
        response = urllib.request.urlopen(url,timeout = 5)
 
        htmlfile = response.read().decode("utf-8")
 
    except urllib.error.URLError as e:
 
        print("超时")
 
    return htmlfile
 
def preservation():
 
    h = gethtml_http("http://www.baidu.com")
 
    print(h)
 
    #import os
 
    #os.rename("内部储存\hhh.py\baidu.txt","内部储存\hhh.py\baidu.html")
 
if __name__ == "__main__":
 
    main()