51Testing软件测试论坛

标题: python抓取网页图片 python爬虫实例 [打印本页]
作者: 测试积点老人    时间: 2019-1-14 14:18
标题: python抓取网页图片 python爬虫实例

使用python抓取网页图片的示例(python网络爬虫)。

代码：
  1. #-*- encoding: utf-8 -*-'''Created on 2014-4-24
  2. @author: Leon Wong'''import urllib2import urllibimport reimport timeimport osimport uuid#获取二级页面urldef findUrl2(html):
  3. re1 = r'http://tuchong.com/\d+/\d+/|http://\w+(?<!photos).tuchong.com/\d+/'url2list = re.findall(re1,html)
  4. url2lstfltr = list(set(url2list))
  5. url2lstfltr.sort(key=url2list.index)#print url2lstfltrreturn url2lstfltr#获取html文本def getHtml(url):
  6. html = urllib2.urlopen(url).read().decode('utf-8')#解码为utf-8return html#下载图片到本地def download(html_page , pageNo):
  7. #定义文件夹的名字x = time.localtime(time.time())
  8. foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
  9. re2=r'http://photos.tuchong.com/.+/f/.+\.jpg'imglist=re.findall(re2,html_page)print imglist
  10. download_img=Nonefor imgurl in imglist:
  11. picpath = 'D:\\TuChong\\%s\\%s' % (foldername,str(pageNo))
  12. filename = str(uuid.uuid1())if not os.path.exists(picpath):
  13. os.makedirs(picpath)
  14. target = picpath+"\\%s.jpg" % filenameprint "The photos location is:"+target
  15. download_img = urllib.urlretrieve(imgurl, target)#将图片下载到指定路径中time.sleep(1)print(imgurl)return download_img# def callback(blocknum, blocksize, totalsize):# '''回调函数 www.jbxue.com# @blocknum: 已经下载的数据块# @blocksize: 数据块的大小# @totalsize: 远程文件的大小# '''# print str(blocknum),str(blocksize),str(totalsize)# if blocknum * blocksize >= totalsize:# print '下载完成'def quitit():print "Bye!"exit(0)if __name__ == '__main__':print ''' *****************************************
  16. ** Welcome to Spider for TUCHONG **
  17. ** Created on 2014-4-24 **
  18. ** @author: Leon Wong **
  19. *****************************************'''pageNo = raw_input("Input the page number you want to scratch (1-100),please input 'quit' if you want to quit>")while not pageNo.isdigit() or int(pageNo) > 100 :if pageNo == 'quit':quitit()print "Param is invalid , please try again."pageNo = raw_input("Input the page number you want to scratch >")#针对图虫人像模块来爬取html = getHtml("http://tuchong.com/tags/%E4%BA%BA%E5%83%8F/?page="+str(pageNo))

  21. detllst = findUrl2(html)for detail in detllst:
  22. html2 = getHtml(detail)
  23. download(html2,pageNo)print "Finished."
复制代码


作者: Miss_love    时间: 2021-1-5 13:38
支持分享



欢迎光临 51Testing软件测试论坛 (http://bbs.51testing.com/) Powered by Discuz! X3.2