#!/usr/bin/env python

#coding:utf-8

#date 20171202

#author maomao

from bs4 import BeautifulSoup

import os

import requests

import sys

reload(sys)

sys.setdefaultencoding('gbk')   ###解决windows 下python 中文的编码问题

class DownLoadBeautiful(object):

    def __init__(self,URL):

        self.URL = URL

    def allUrls(self):

        headers = {

            'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"

        }                                                             ###设置请求的头部，伪装成浏览器

        start_html = requests.get(self.URL,headers=headers)           ###使用了更为人性化的requests来发送请求

        soup = BeautifulSoup(start_html.text,'lxml')                 ###使用BS4 框架来解析网页源码

        hreflist = soup.find('div',attrs={'class':'all'}).find_all('a')      ###查找主页里面所有的图片链接html标签

        for href in hreflist:

            title = href.get_text()                                      ###图片链接的具体中文描述

            path = str(title).strip()

            os.makedirs(os.path.join("D:\meizitu",path))               ###在本地创建保存

            os.chdir("D:\meizi\\"+path)

            hrefs = href['href']                                        ###获取图片的URL

            html = requests.get(hrefs,headers=headers)                   ###请求图片的URL

            html_soup = BeautifulSoup(html.text,'lxml')                 ###解析图片URL的网页源码

            max_span = html_soup.find('div',attrs={'class':'pagenavi'}).find_all('span')[-2].get_text()  ###分析图片一共多少页

            for page in xrange(1,int(max_span)+1):

                page_url = hrefs + '/' + str(page)                       ###拼接每张图片的URL

                img_html = requests.get(page_url,headers=headers)         ###请求每张图片的URL

                img_soup = BeautifulSoup(img_html.text,'lxml')            ###解析每张图片的源码

                img_url = img_soup.find('div',attrs={'class':'main-image'}).find('img')['src'] ####查找实际每张图片的具体地址

                headers = {

                    'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",

                    'Referer':page_url

                }                                                         ###因为网站有防盗链，重新设置了头部的Referer ；F12里打开网络监听，在Request Headers 里面

                img = requests.get(img_url,headers=headers,stream=True)   ###请求图片的实际URL

                print img.url

                name = img_url[-9:-4]

                f = open(name+'.jpg','wb')                               ###将图片下载并保存，注意对于多媒体文件，必须使用二进制写入

                f.write(img.content)

                f.close()

if __name__ == "__main__":

    test = DownLoadBeautiful("http://www.mzitu.com/all")

    test.allUrls()