用Python写的图片蜘蛛人

qepwqnp

写了个图片蜘蛛人玩玩，抓了几个网页试试，感觉不不错。核心的代码可能20行也不到，简洁明了，嘻嘻。废话少说，翠花，上代码~~
#coding=utf-8import osimport sysimport reimport urllibURL_REG = re.compile(r'(http://[^/\\]+)', re.I)IMG_REG = re.compile(r'<img[^>]*?src=([\'"])([^\1]*?)\1', re.I)def download(dir, url):'''下载网页中的图片@dir 保存到本地的路径@url 网页url'''global URL_REG, IMG_REGm = URL_REG.match(url)if not m: print '[Error]Invalid URL: ', urlreturnhost = m.group(1)if not os.path.isdir(dir):os.mkdir(dir)# 获取html,提取图片urlhtml = urllib.urlopen(url).read()imgs = [item[1].lower() for item in IMG_REG.findall(html)]f = lambda path: path if path.startswith('http://') else \host + path if path.startswith('/') else url + '/' + pathimgs = list(set(map(f, imgs)))print '[Info]Find %d images.' % len(imgs)# 下载图片for idx, img in enumerate(imgs):name = img.split('/')[-1]path = os.path.join(dir, name)try: print '[Info]Download(%d): %s'% (idx + 1, img)urllib.urlretrieve(img, path)except: print "[Error]Cant't download(%d): %s" % (idx + 1, img)def main():if len(sys.argv) != 3:print 'Invalid argument count.'returndir, url = sys.argv[1:]download(dir, url)if __name__ == '__main__':# download('D:\\Imgs', 'http://www.163.com')main()