import reimport urllib.requestdef Schedule(a,b,c): per = 100.0 * a * b / c if per>100: per = 100 print(‘完成!‘) print(‘%.2f%%‘ % per)def getHtml(url): page = urllib.request.urlopen(url) html = page.read() return htmldef getImg(html): html = html.decode(‘utf-8‘) reg = r‘src="(.*?\.jpg)" width‘ imgre = re.compile(reg) imglist = imgre.findall(html) x = 0 for imgurl in imglist: # 写好你的路径 urllib.request.urlretrieve(imgurl,‘D:\\test\\%s.jpg‘ % x,Schedule) x += 1html = getHtml(‘http://tieba.baidu.com/p/741081023‘)print(getImg(html)) |
运行结果:
原文:https://www.cnblogs.com/ruiy/p/9091061.html