用Python写的图片蜘蛛人代码

#coding=utf-8

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):
'''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_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)

# 获取html,提取图片url
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)

# 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.'
return
dir, url = sys.argv[1:]
download(dir, url)

if __name__ == '__main__':
# download('d://imgs', 'http://www.163.com')
main()