本文共 1405 字,大约阅读时间需要 4 分钟。
转自:http://blog.csdn.net/jgood/article/details/5471626
原文地址:
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~~
-
-
- import os
- import sys
- import re
- import urllib
-
- URL_REG = re.compile(r'(http://[^///]+)', re.I)
- IMG_REG = re.compile(r'<img[^>]*?src=([/'"])([^/1]*?)/1', re.I)
-
- def download(dir, url):
- ''
-
-
-
-
- global URL_REG, IMG_REG
-
- m = URL_REG.match(url)
- if not m:
- print '[Error]Invalid URL: ', url
- return
- host = m.group(1)
-
- if not os.path.isdir(dir):
- os.mkdir(dir)
-
-
- html = 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 + '/' + path
- imgs = list(set(map(f, imgs)))
- print '[Info]Find %d images.' % len(imgs)
-
-
- 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.'
- return
- dir, url = sys.argv[1:]
- download(dir, url)
-
- if __name__ == '__main__':
-
- main()
上面图片链接的正则有点问题,可以用下面的代替:
IMG_REG = re.compile(r'<\s*img\s+([^http]*)((http):(\/\/|\\\\)(.[^\[]*)\.(gif|jpg|jpeg|bmp|png|ico))([^>]*)>', re.I)