下载豆瓣相册图片

get_douban_album_pic.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
# Filename: get_douban_album_pic.py

import urllib2, re, os, sys
from os.path import basename
from urlparse import urlsplit

def fetch(url):
    try:
        return urllib2.urlopen(url).read()
    except Exception as e:
        print(e)

def get_count(url):
    urlContent = fetch(url)
    ptn = u'<span class="count">\(\u5171(\d+)\u5f20\)</span>'
    count = re.findall(ptn, unicode(urlContent, "utf-8"))
    if len(count) < 1:
        return 1
    return int(count[0])

def down_img(url):
    urlContent = fetch(url)
    spans = r'(http://img\d.douban.com/view/photo/thumb/public/p\d+.jpg)'
    imgUrls = re.findall(spans, urlContent)
    #1770000000 号以后的照片都有更大尺寸的原图，url 中含 large. via: 豆藤
    imgUrls = [
        i.replace('thumb', 'large')
        if int(re.findall(r'.*?public/p(\d+).jpg', i)[0]) > 1770000000
        else i.replace('thumb', 'photo')
        for i in imgUrls
    ]
    for imgUrl in imgUrls:
        imgData = fetch(imgUrl)
        fileName = basename(urlsplit(imgUrl)[2])
        with open('douban/'+fileName, 'wb') as output:
            output.write(imgData)

def download(url):
    base = url
    num = 0
    count = get_count(url)
    start = 0
    while (start < count):
       num += 1
       print("Downloading images in page %d ...") % num
       down_img(url)
       start += 18
       url = base + '?start=' + str(start)
    print("Finished")

def input_url():
    link = r'(^http://www.douban.com/photos/album/\d+).*?'
    if len(sys.argv) == 1:
        inputString = raw_input('Enter album url --> ')
    else:
        inputString = sys.argv[1]
    url = re.findall(link, inputString)[0] + '/'
    return url

if __name__ == "__main__":
    if (os.path.exists('douban') == False):
        os.mkdir('douban')
    download(input_url())