# -*- coding: utf-8 -*-

 from lxml import html

 import requests

 page = requests.get('http://book.douban.com/latest?icn=index-latestbook-all')

 tree = html.fromstring(page.text)

 # 若保存了html文件，可使用下面方法

 # page = open('/home/freyr/codeHouse/python/512.htm', 'r').read()

 # tree = html.fromstring(page)

 #提取图书信息

 bookname = tree.xpath('//div[@class="detail-frame"]/h2/text()')    # 书名

 author = tree.xpath('//div[@class="detail-frame"]/p[@class="color-gray"]/text()')    # 作者

 info = tree.xpath('//div[@class="detail-frame"]/p[2]/text()')    # 简介

 url = tree.xpath('//ul[@class="cover-col-4 clearfix"]/li/a[@href]')    # URL

 booknames = map(lambda x:x.strip(), bookname)

 authors = map(lambda x:x.strip(), author)

 infos = map(lambda x:x.strip(), info)

 urls = map(lambda p: p.values()[0], url)

 with open('/home/freyr/codeHouse/python/dbBook.txt','w+') as f:

     for book, author, info, url in zip(booknames, authors, infos, urls):

         f.write('%s\n\n%s\n\n%s' % (book.encode('utf-8'), author.encode('utf-8'), info.encode('utf-8')))

         f.write('\n\n%s\n' % url )

         f.write('\n\n-----------------------------------------\n\n\n')