爬虫，未完成

import re
import os
import urllib
re_favliststart = re.compile(r'<div class="fav_list">')
re_url = re.compile(r'<a href="(?P<url>http.+)" target=.*>(?P<title>.*)</a>')
myfavourite = open('myfavourite.html')
savedata = open('savedata.txt','w')
workspace = os.getcwd()
for line in myfavourite:
	if re_favliststart.search(line) != None:
		break

for line in myfavourite:
	result = re_url.search(line)
	if result == None:
		continue
#	print result.group('url')
#	print result.group('title') 
	savedata.write(result.group('url') +'\n')
	savedata.write(result.group('title') +'\n')
	filename = workspace + '/' + result.group('title') + '.html'
	urllib.urlretrieve(result.group('url'),filename)
myfavourite.close()
savedata.close()