SpiderAdmin

$ scrapyd-deploy -a

$ pip3 install spideradmin

$ spideradmin init  # 初始化，可选配置，也可以使用默认配置

$ spideradmin       # 启动服务

pip install PureMySQL

CREATE TABLE `log_spider` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `spider_name` varchar(50) DEFAULT NULL,
  `item_count` int(11) DEFAULT NULL,
  `duration` int(11) DEFAULT NULL,
  `log_error` int(11) DEFAULT NULL,
  `create_time` datetime DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='爬虫执行结果统计'

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

import logging

from scrapy import signals
from puremysql import PureMysql
from datetime import datetime


class SpiderItemCountExtension(object):
    
    # 设置为数据库链接url eg: mysql://root:123456@127.0.0.1:3306/mydata 
    ITEM_LOG_DATABASE_URL = None
    
    # 设置数据表
    ITEM_LOG_TABLE = "log_spider"

    @classmethod
    def from_crawler(cls, crawler):
        ext = cls()
        crawler.signals.connect(ext.spider_closed, signal=signals.spider_closed)
        return ext

    def spider_closed(self, spider, reason):
        stats = spider.crawler.stats.get_stats()
        scraped_count = stats.get("item_scraped_count", 0)
        dropped_count = stats.get("item_dropped_count", 0)

        log_error = stats.get("log_count/ERROR", 0)
        start_time = stats.get("start_time")
        finish_time = stats.get("finish_time")
        duration = (finish_time - start_time).seconds

        count = scraped_count + dropped_count

        logging.debug("*" * 50)
        logging.debug("* {}".format(spider.name))
        logging.debug("* item count: {}".format(count))
        logging.debug("*" * 50)

        item = {
            "spider_name": spider.name,
            "item_count": count,
            "duration": duration,
            "log_error": log_error,
            "create_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        }

        mysql = PureMysql(db_url=self.ITEM_LOG_DATABASE_URL)
        table = mysql.table(self.ITEM_LOG_TABLE)
        table.insert(item)
        mysql.close()

EXTENSIONS = {
    # 'scrapy.extensions.telnet.TelnetConsole': None,
    "item_count_extension.SpiderItemCountExtension": 100
}

ITEM_LOG_DATABASE_URL = "mysql://root:123456@127.0.0.1:3306/mydata"
ITEM_LOG_TABLE = "log_spider"