# coding:utf-8
import os
import urllib2
from bs4 import BeautifulSoup
import datetime

baseUrl = "http://design-patterns.readthedocs.io/zh_CN/latest/"
seed_url = "http://design-patterns.readthedocs.io/zh_CN/latest/index.html"


def getFileName(url):
    splitResult = os.path.split(url)  # str分割为tuple
    return splitResult


def parseHtml(html):
    soup = BeautifulSoup(html)
    list = soup.findAll('li')
    for tag in list:
        if tag.a != None:
            final_url = baseUrl + tag.a['href']
            # print dirs
            downLoad(final_url, False)


def downLoad(url, needParse):
    try:
        html = urllib2.urlopen(url).read()  # 读取url 返回html
        if (needParse):
            parseHtml(html)
        list = getFileName(url)
        name_dir = '图解设计模式'
        if (not os.path.exists(name_dir)):
            dir = os.mkdir(name_dir)
        f = open(name_dir + '/' + str(list[list.count("foo") - 1]), 'w')  # 保存为html文件
        f.write(bytes(html))
        f.close()
        print "downLoading..." + url
    except urllib2.URLError as e:  # 异常处理  读取失败时显示失败原因
        print "downLoad Error:" + str(e.reason)
        html = None
    return html

downLoad(seed_url, True)