Python 爬虫网页抓图保存

来源：互联网发布：seo招聘北京编辑：程序博客网时间：2024/05/01 03:18

网站选择桌面壁纸网站的汽车主题：

下面的两个print在调试时打开

#print tag#print attrs

#!/usr/bin/env pythonimport reimport urllib2import HTMLParserbase = "http://desk.zol.com.cn"path = '/home/mk/cars/'star = ''def get_url(html):parser = parse(False)request = urllib2.Request(html)response = urllib2.urlopen(request)resp = response.read()parser.feed(resp)def download(url):content = urllib2.urlopen(url).read()format = '[0-9]*\.jpg';res = re.search(format,url);print 'downloading:',res.group()filename = path+res.group()f = open(filename,'w+')f.write(content)f.close() class parse(HTMLParser.HTMLParser):def __init__(self,Index):self.Index = Index;HTMLParser.HTMLParser.__init__(self)def handle_starttag(self,tag,attrs):#print tag#print attrsif(self.Index):if not cmp(tag,'a'):if(len(attrs) == 4):if(attrs[0] ==('class','pic')):#print tag#print attrsnew = base+attrs[1][1]print 'found a link:',newglobal starstar = newget_url(new)else:if not cmp(tag,'img'):if(attrs[0] == ('id','bigImg')):#print tag#print attrsImage_url = attrs[1][1]print 'found a picture:',Image_urldownload(Image_url)if not cmp(tag,'a'):if (len(attrs) == 4):if (attrs[1] == ('class','next')):#print tag#print attrsnext = base + attrs[2][1]print 'found a link:',nextif (star != next):get_url(next)Index_url = 'http://desk.zol.com.cn/qiche/'con = urllib2.urlopen(Index_url).read()Parser_index = parse(True)Parser_index.feed(con)

仅仅就是抓桌面壁纸网站上的优美的壁纸。。。

1 0