豆瓣相册下载脚本

GetDoubanAlbum.py

'''
Created on Aug 7, 2011

@author: Agassi


'''

#_*_encoding:utf-8_*_
from lxml import html
import os
import urllib2


def format_html_from_url(url):
	response = urllib2.urlopen(url)
	content = response.read()
	doc=html.document_fromstring(content)

	return doc

if __name__=='__main__':
	url = raw_input("Album url:>>>")
	#url='http://www.douban.com/photos/album/75440685/'

	doc = format_html_from_url(url)

	photolst = doc.xpath('//div[@class="photolst clearfix"]/div/a/img/@src')

	for url in photolst:
		url = url.replace('thumb','photo')
		os.system('wget -nc -P album ' + url)

	other_page_urls = doc.xpath('//div[@class="paginator"]/a/@href')

	for url in other_page_urls:
		other_doc = format_html_from_url(url)

		o_lst = other_doc.xpath('//div[@class="photolst clearfix"]/div/a/img/@src')

		for p_url in o_lst:
			p_url = p_url.replace('thumb','photo')
			os.system('wget -nc -P album ' + p_url)