Scrapy框架（爬虫中间件）：TypeError: __init__() missing 5 required positional arguments

Question

问题遇到的现象和发生背景

        使用Scrapy抓取数据写入MySql数据库，抛出异常TypeError: __init__() missing 5 required positional arguments
        

问题相关代码，请勿粘贴截图

代码片段：

# 爬虫模块代码
from scrapy import Spider,Request
from urllib.parse import urlencode
import json
from ItemPipeline.items import ImageItem

class ImageSpider(Spider):
    name = 'images'
    start_urls = ['https://images.so.com']
    def start_requests(self):
        # 定义Restful API
        data = {'ch':'beauty','listtype':'new'}
        # 定义Restful API的参数
        base_url = 'https://image.so.com/zj?'
        # 通过for-in循环想服务端请求MAX_PAGE参数指定的次数
        for page in range(1,self.settings.get('MAX_PAGE')+1):
            # 产生每次提交的sn参数的值
            data['sn'] = page * 30
            # 将data编码成URL参数（主要转换某些无法放在URL中的特殊字符，如空格）
            params = urlencode(data)
            # 组成完整的URL
            url = base_url + params
            # 通过yield实现一个产生器，只有读取，才会返回当前的Request
            yield Request(url,self.parse)

    # 分析HTTP响应信息（Response）
    def parse(self, response, **kwargs):
        # 将HTTP响应信息抓好为JSON对象
        result = json.loads(response.text)
        # 得到list属性中的每一个元素
        for image in result.get('list'):
            item = ImageItem()
            item['id'] = image.get('imageid')
            item['url'] = image.get('qhimg_url')
            item['title'] = image.get('group_title')
            item['thumb'] = image.get('qhimg_thumb_url')
            yield item

# 管道中间件的代码
from itemadapter import ItemAdapter

class ItempipelinePipeline:
    def process_item(self, item, spider):
        return item

import pymongo
import pymysql
from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline

class MysqlPipeline():
    def __init__(self, host, database, user, password, port):
        self.host = host
        self.database = database
        self.user = user
        self.password = password
        self.port = port

    @classmethod
    def from_crawl(cls,crawler):

        # 创建MysqlPipeline类的实例
        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            database=crawler.settings.get('MYSQL_DATABASE'),
            user=crawler.settings.get('MYSQL_USER'),
            password=crawler.settings.get('MYSQL_PASSWORD'),
            port=crawler.settings.get('MYSQL_PORT'),
        )

    def open_spider(self,spider):
        # 连接数据库
        self.db = pymysql.connect(host=self.host,user=self.user,password=self.password,database=self.database,
                                  charset='utf8',port=self.port)
        self.cursor = self.db.cursor()

    def close_spider(self,spider):
        # 关闭数据库
        self.db.close()

    def process_item(self,item,spider):
        print(item['title'])
        data = dict(item)
        keys = ', '.join(data.keys())
        values = ', '.join(['%s'] * len(data))
        sql = 'insert into %s (%s) values (%s)' % (item.table, keys, values)
        # 将与图片相关的数据插入MySQL数据库的images表中
        self.cursor.execute(sql,tuple(data.values()))
        self.db.commit()
        return item

# 将图片保存到本地
class ImagePipeline(ImagesPipeline):
    # 返回对应本地图像文件的文件名
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split('/')[-1]
        return file_name
    # 过滤不符合条件的图片,单个Item对象完成下载后调用该方法
    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok,x in results if ok]
        if not image_paths:
            # 抛出异常，剔除当前下载的图片
            raise DropItem('Image Downloaded Failed')
        return item
    # 根据当前URL创建Request对象，并返回该对象，Request对象会加到调度队列中猪呢比下载该图像
    def get_media_requests(self, item, info):
        yield Request(item['url'])

运行结果及报错内容

Answer 1

在init函数内部引入settings然后依次赋值就解决了