京东

import urllib.requestimport reimport osdef crawl(url, page):    html = urllib.request.urlopen(url).read()    html = str(html)    pattern = '
    
     '    result = re.compile(pattern).findall(html)    result = result[0]    pattern2 = '
     '    imglist = re.compile(pattern2).findall(result)    x = 1    for imgurl in imglist:        imgname = os.getcwd() + os.sep + str(page) + str(x) + ".jpg"        imgurl = "http://" + imgurl        try:            urllib.request.urlretrieve(imgurl, filename=imgname)        except urllib.error.URLError as e:            if hasattr(e, "code"):                x += 1            if hasattr(e, "reason"):                x += 1        x += 1for i in range(1, 6):    url = "https://list.jd.com/list.html?cat=9987,653,655&page=" + str(i)    crawl(url, i)
    

千图网

import urllib.requestimport redef download_page(url):    request = urllib.request.Request(url)    reponse = urllib.request.urlopen(request)    data = reponse.read()    return datadef get_image(html):    regx = r'http://[\S]*\.jpg'    pattern = re.compile(regx)    image = re.findall(pattern, repr(html))  # repr用来转换表达式类型字符串    num = 1    for img in image:        i = download_page(img)  # 将每个img链接重新解析        with open('%s.jpg' % num, 'wb') as fp:            fp.write(i)            print('正在下载第%s张图片' % num)            num += 1    returnurl = 'http://www.58pic.com'html = download_page(url)get_image(html)