注：若运行以下代码报出有关“PIL”的错误，则只需安装pillow即可。

实现思路：

（1）使用Fiddler抓包工具，找出为斗鱼APP颜值区提供数据的URL（Json格式）
（2）在items中定义需要记录的相关信息
（3）在spider中实现迭代爬取各主播的信息
（4）在Pipeline中通过继承内置的ImagesPipeline类，重写其功能，实现图片的下载 
（5）在settings.py文件中进行相关配置

代码实现：

items.py

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

import scrapy


class DouyuItem(scrapy.Item):
    #图片链接
    vertical_src = scrapy.Field()
    #主播名
    nickname = scrapy.Field()
    #图片保存路径
    imagePath = scrapy.Field()

爬虫文件（spiders/douyuMM.py）

# -*- coding: utf-8 -*-
import scrapy
import json
from Douyu.items import DouyuItem


class DouyummSpider(scrapy.Spider):
    name = 'douyuMM'
    allowed_domains = ['capi.douyucdn.cn']
    initial_URL = 'http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset='
    offset = 0
    URL = initial_URL + str(offset)
    start_urls = [URL]

    def parse(self, response):
        data = json.loads(response.text)['data']
        for each in data:
            item = DouyuItem()
            item['nickname'] = each['nickname']
            #将图片链接存储成列表形式，供pipelines迭代
            image_url = each['vertical_src']
            item['vertical_src'] = [image_url]
            yield item

        self.offset += 20
        #抓取前100个主播的图片
        if self.offset < 100:
            self.URL = self.initial_URL + str(self.offset)
            yield scrapy.Request(url=self.URL, callback=self.parse)

pipelines.py

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

import os
import scrapy
"""
    pipelines提供了图片相关的方法，因此只需继承ImagesPipeline
    并对“get_media_requests”和“item_completed”重写即可实现图片的下载
"""
from scrapy.pipelines.images import ImagesPipeline
#通过get_project_settings来获取settings.py文件中设置的变量
from scrapy.utils.project import get_project_settings


class DouyuImagesPipeline(ImagesPipeline):
    IMAGES_STORE = get_project_settings().get('IMAGES_STORE')

    def get_media_requests(self, item, info):
        for image_url in item['vertical_src']:
            yield scrapy.Request(image_url)

        """
            亦可用下面的代码，只不过下面的代码只能抓取一张图片
            image_url = item['vertical_src']
            yield scrapy.Request(image_url)
        """

    def item_completed(self, results, item, info):
        """
            result结构:
                [(True,
                  {'checksum': '2b00042f7481c7b056c4b410d28f33cf',
                   'path': 'full/0a79c461a4062ac383dc4fade7bc09f1384a3910.jpg',
                   'url': 'http://www.example.com/files/product1.pdf'}),
                 (False,
                  Failure(...))]
        """
        image_path = [x['path'] for ok, x in results if ok]
        # 修改图片保存名称为主播昵称
        # 并将爬取的图片存储在IMAGES_STORE设置的相对路径下，用“full”文件存储
        os.rename(self.IMAGES_STORE + image_path[0], self.IMAGES_STORE + 'full/' + item["nickname"] + ".jpg")
        item['imagePath'] = self.IMAGES_STORE + 'full/' + item["nickname"]
        return item

settings.py

BOT_NAME = 'Douyu'

SPIDER_MODULES = ['Douyu.spiders']
NEWSPIDER_MODULE = 'Douyu.spiders'

ROBOTSTXT_OBEY = True
DEFAULT_REQUEST_HEADERS = {
    'User-Agent':'DYZB/4.100 (iPhone; iOS 11.3.1; Scale/3.00)',
    'Accept': 'application/vnd.mapi-yuba.douyu.com.4.0+json',
    'Accept-Language': 'zh-Hans-CN;q=1'
}

IMAGES_STORE = 'data/斗鱼主播图片/'

ITEM_PIPELINES = {
    'Douyu.pipelines.DouyuImagesPipeline': 300,
}