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

import scrapy

import requests

class BiaoqingbaoSpider(scrapy.Spider):

    name = 'biaoqingbao'

    allowed_domains = ['doutula.com']

    start_urls = ['http://www.doutula.com/photo/list/?page=1']

    def parse(self, response):

        #提取地址和图片名称

        pictureUrls = response.xpath("//a[@class='col-xs-6 col-sm-3']/img/@data-original").extract()

        pictureName = response.xpath("//a[@class='col-xs-6 col-sm-3']/p/text()").extract()

        #提取网址后缀，用于实现自动翻页

        next_page = response.xpath("//li/a[@aria-label='Next »']/@href").extract_first()

        for i in range(len(pictureUrls)):

            url = pictureUrls[i]

            name = pictureName[i]

            self.getPicture(url=url, name=name) #对每个图片调用getPicture下载图片并命名

        #自动翻页

        if next_page:

            next_url = response.urljoin(next_page) #返回新的网址

            yield scrapy.Request(next_url, callback=self.parse) #回调函数

    #自定义函数，用于下载图片，因为刚学太菜，就只有先用requests下载了

    def getPicture(self, url, name):

        response = requests.get(url)

        suffix = url.split(".")[-1] #提取图片链接地址的后缀，因为有jpg和gif图片格式

        #二进制格式写入图片

        with open("biaoqingbaoSpider/spiders/images/"+name+ "." + suffix, "wb") as fp:

            fp.write(response.content)