#print e.message
continue
def run(self):
self.checkProxy()
#获取图片地址函数
def imgurlList(url_home):
global imgurl_list
home_page = urllib2.urlopen(url_home)
url_re = re.compile(r'<li><a href="(.+?)" target="_blank" rel="nofollow">')
pic_re = re.compile(r'<img src="(.*?.w{3,4})"')
url_list = re.findall(url_re,home_page.read())
for url in url_list:
#print url_home+url
url_page = urllib2.urlopen(url_home+url)
for imgurlList in re.findall(pic_re,url_page.read()):
imgurl_list.append(imgurlList)
#下载图片的类
class getPic(threading.Thread):
def __init__(self,imgurl_list):
threading.Thread.__init__(self)
self.imgurl_list = imgurl_list
self.timeout = 5
def downloadimg(self):
for imgurl in self.imgurl_list:
pic_suffix = imgurl.split('.')[-1] #获取图片后缀
pic_name = str(random.randint(0,10000000000))+'.'+pic_suffix
cookies = urllib2.HTTPCookieProcessor()
randomCheckedProxy = random.choice(checkedProxyList) #随机取一组代理服务器
proxyHandler = urllib2.ProxyHandler({"http" : r'http://%s:%s' %(randomCheckedProxy[0],randomCheckedProxy[1])})
opener = urllib2.build_opener(cookies,proxyHandler)
opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.2; WOW64; rv:22.0) Gecko/20100101 Firefox/22.0')]
urllib2.install_opener(opener)
try:
data_img = opener.open(imgurl,timeout=self.timeout)
f = open (pic_name,'wb')
f.write(data_img.read())
