#coding = utf-8

import urllib2

import re

path = "aaa.txt"

f = open(path, 'w+')

for i in range(4980, 4991):

    print i

    # get webpage content

    url = "http://*" + str(i) + "*"

    page = urllib2.urlopen(url).read()

    # Regular matching

    matchTitle = re.search(r'<dt>(.*?)</dt>', page)

    matchMarketPrice = re.search(r'<del.*?>(.*?)</del>', page)

    matchCurrentPrice = re.search(r'<b>(.*?)</b>', page)

    # save result

    if matchTitle and matchMarketPrice and matchCurrentPrice:

        f.write(matchTitle.group(1) + '\t' + matchMarketPrice.group(1) + '\t' + matchCurrentPrice.group(1) + '\n')

f.close()

欧莱雅奇焕光感粉嫩透亮修颜霜30ml ¥120.00 109.00

欧莱雅复颜洁面乳125ml	¥130.00	105.00

欧莱雅复颜抗皱紧致滋润眼霜15ml	¥210.00	179.00

欧莱雅复颜清漾柔肤水175ml	¥160.00	138.00