python学习笔记（二）—python爬取网页源代码

使用模块urllib

#coding:utf-8
import urllib.request

请求url，获取网页源代码

def getHtml(url):
    h = urllib.request.urlopen(url).read()
    return h

保存文档

def saveHtml(file_name,file_content):   
    with open (file_name,"wb") as f:
        f.write( file_content )  

循环访问并爬取网站内各网页源代码

for i in range(1,6365):    
    url='http://www.xxxx/home.php?mod=space&uid='
    h=getHtml(url)
    saveHtml('D:/工具/py脚本/pachong/html/%s.html'%i,h)
 
print ("结束")