Python爬虫实现获取动态gif格式搞笑图片的方法示例

#!/usr/bin/python
#coding:utf-8
import urllib2,time,uuid,urllib,os,sys,re
from bs4 import BeautifulSoup
reload(sys)
sys.setdefaultencoding('utf-8')
#获取页面内容
def getHtml(url):
    try:
        print url
        html = urllib2.urlopen(url).read()#.decode('utf-8')#解码为utf-8
    except:
        return
    return html
#获取动图所代表的url列表
def getImagUrl(html):
    if not html:
        print 'nothing can be found'
        return
    ImagUrlList=[]
    soup=BeautifulSoup(html,'lxml')
    #获取item列表
    items=soup.find("div",{"class":"main"}).find_all('div',{'class':'item'})
    for item in items:
        target={}
        #通过if语句，过滤广告项
        if item.find('div',{"class":"text"}):
            #获取url
            imgurl=item.find('div',{"class":"text"}).find('img').get('src')
            target['url']=imgurl
            #获取名字
            target['name']=item.find('h4').text
            ImagUrlList.append(target)
    return ImagUrlList
#下载图片到本地
def download(author,imgurl,typename,pageNo):
    #定义文件夹的名字
    x = time.localtime(time.time())
    foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
    download_img=None
    picpath = 'Jimy/%s/%s/%s' % (foldername,typename,str(pageNo))
    filename = author+str(uuid.uuid1())
    pic_type=imgurl[-3:]
    if not os.path.exists(picpath):
        os.makedirs(picpath)
    target = picpath+"/%s.%s" % (filename,pic_type)
    print "动图存贮位置:"+target
    download_img = urllib.urlretrieve(imgurl, target)#将图片下载到指定路径中
    print "图片出处为："+imgurl
    return download_img
#退出函数
def myquit():
    print "Bye Bye!"
    exit(0)
def start(pageNo):
    targeturl="http://www.zbjuran.com/dongtai/list_4_%s.html" % str(pageNo)
    html = getHtml(targeturl)
    urllist=getImagUrl(html)
    for imgurl in urllist:
        download(imgurl['name'],imgurl['url'],'搞笑动图',pageNo)
if __name__ == '__main__':
    print '''
            *****************************************
            **  Welcome to Spider of GIF     **
            **   Created on 2017-3-16      **
            **   @author: Jimy         **
            *****************************************'''
    pageNo = raw_input("Input the page number you want to scratch (1-50),please input 'quit' if you want to quit\n\
请输入要爬取的页面，范围为（1-100），如果退出，请输入Q>\n>")
    while not pageNo.isdigit() or int(pageNo) > 50 or int(pageNo) < 1:
        if pageNo == 'Q':
            myquit()
        print "Param is invalid , please try again."
        pageNo = raw_input("Input the page number you want to scratch >")
    print pageNo
    start(pageNo)
    #第一次爬取结束
    pageNo = raw_input("Input the page number you want to scratch (1-50),please input 'quit' if you want to quit\n\
请输入总共需要爬取的页面，范围为（1-5000），如果退出，请输入Q>\n>")
    while not pageNo.isdigit() or int(pageNo) > 5000 or int(pageNo) < 1:
        if pageNo == 'Q':
            myquit()
        print "Param is invalid , please try again."
        pageNo = raw_input("Input the page number you want to scratch >")
    #循环遍历，爬取多页
    for num in xrange(int(pageNo)):
        start(str(num+1))