urllib 应用

该程序通过获取页面的源码，从源码中读取数字来组成下一个链接的URL。

import os
import sys
import urllib
import re

def getsrc(url):
    src=urllib.urlopen(url).read() # Get the page source of the page.
    num=re.search('[\d]\d+',src) # search the digit from the page source.
    if not num: # if cant find digits from the page source,
        print src #then print the source and return the Excepion.
        return num.group(1)
    else:
        return num.group(0) # Return the digits.

if __name__=='__main__':
    url=''
    for n in range(400):
        print n
        num=getsrc(url)
        url=''+str(num) # use the return value(num) to create the next url.
    print num