#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):
''' Download the images from the web page
@dir Save to the local path
@url Web page 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)
# To obtain html, To extract the image 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)
# Download the pictures
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()