先把程式碼函式化了！不過好像沒什麼用...

#! /usr/bin/env python
#-*- coding: utf-8 -*-
import urllib.request
import re

def get_attr( TagList, targetList, hostUrl ):
	siteMap = []
	for y in TagList :
		#print( y[1] )
		if y[0] in targetList : #尋找<a>標籤
			Attr = y[1].split(" ")
			for z in Attr: 
				IgCh = [ '"' , "'" ] #去除前後分號
				if re.search( r'^href=' , z ):
					if z[5] in IgCh: #判斷是否有分號
						if z[6:-1] not in siteMap: #判斷是否重複
							rehostUrl = "^" + hostUrl #判斷是否為同一個Domain #尚未判斷相對路徑
							if re.search( hostUrl , z[6:-1] ):
								siteMap.append( z[6:-1] )
					else:
						if z[5:] not in siteMap:
							siteMap.append( z[5:] )
	
	return siteMap

def get_sitmap( TagList, hostUrl ):
	targetList = [ "a" ]
	siteMap = []
	
	siteMap.append( get_attr( TagList, targetList, hostUrl ) )
	
	return siteMap

def get_tag( data ):
	reStr = "<([\w]+) (.*?)>";
	reObj = re.compile( reStr.format() )
	
	targetTag = reObj.findall( str( data.decode( "utf-8" ) ) )
	
	TagList = []
	for x in targetTag:
		TagList.append( x ) 
	
	return TagList

def get_url_data( targetUrl ):
	
	urlobj = urllib.request.urlopen( targetUrl )
	data = urlobj.read()
	hostUrl = urlobj.geturl()
	urlobj.close()
	
	return data, hostUrl

def test():
	targetUrl = "http://192.168.1.8/"
	
	data, hostUrl = get_url_data( targetUrl )
	
	TagList = get_tag( data )
	
	sitemap = get_sitmap( TagList, hostUrl )
	print( sitemap )

if __name__ == "__main__":
	test()

明天繼續努力！以上！晚安！