Python urllib2抓取Wordpress用户学习笔记

#!/usr/bin/env python
#coding=utf-8
import sys
import urllib2
import string
import re
import os
demo = """

"""
try:
    if len(sys.argv) < 2:
        print "----------------------------------------"
        print demo
        print "----------------------------------------"
        sys.exit()
    lj = "/?author="
    url = sys.argv[1] + lj
    path = os.getcwd() #获取文件路径
    url_name = re.findall('http://(.*＼w)',sys.argv[1]) #获取域名
    url_name_txt = url_name[0] + '.txt'
    print "Username to %s＼＼%s"%(path,url_name_txt)
    for i in xrange(1,1111): #循环ID
        web = url + str(i)
        code = urllib2.urlopen(web).read() #获取源码
        username = re.findall('