一个python爬图片的小爬虫

来源：互联网发布：哪里能下载windows正版编辑：程序博客网时间：2024/04/30 06:35

import reimport urllib2import urllibdef get_herf(): for i in xrange(1,2): url = "http://www.meizitu.com/a/list_1_%d.html" %i request = urllib2.Request(url) respond = urllib2.urlopen(request) content = respond.read() pattern = re.compile('

',re.S) #print content result = re.findall(pattern,content) #print result return result def get_img(): url_add = get_herf() print "total:", len(url_add),"catagory" for url in url_add: num_cat = int(url_add.index(url)+1) print "saving catagory:", num_cat request = urllib2.Request(url) respond = urllib2.urlopen(request) content = respond.read().decode("gbk") pattern = re.compile(' .*?

',re.S) result = re.findall(pattern,content) for item in result: number = int(result.index(item))+1 save(str(item),num_cat,number) print "finished all saving, total", len(result), "pictures" print "finished all saving, total", len(result), "pictures" def save(imageURL,num_cat,number): filename = str(num_cat)+"_"+str(number)+".jpg" urllib.urlretrieve(imageURL,filename) print "finished saving picture:", num_cat, number get_img()

0 0