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

import xlwt

import urllib

import re

def getHtml(url):

    page = urllib.urlopen(url)

    html = page.read()

    return html

def get_book_message(url):

    page = urllib.urlopen(url)

    html = page.read()

    urls = []

    page.close()

    imgReg = r'src="(.+?\.jpg)"'

    titlReg = r'rel="bookmark">(.+?)</a>'

    divre = re.compile(imgReg)

    divreTitle = re.compile(titlReg)

    divlist = re.findall(divre,html)

    titleList = re.findall(divreTitle,html)

    bookMessage = {}

    for url,title in zip(divlist,titleList):

        bookMessage[title] = url

    return bookMessage

def run():

    value = get_book_message('http://www.allitebooks.com/')

    workbook = xlwt.Workbook(encoding = 'ascii')

    worksheet = workbook.add_sheet('MyBookMessage')

    worksheet.write(0,1,u'地址')

    worksheet.write(0,2,u'标题')

    index = 1

    for x in value:

        worksheet.write(index,1,x)

        worksheet.write(index,2,value[x])

        index = index + 1

    workbook.save('MyBookMessage.xls')

run()