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

"""

Created on {DATE}

---------

@summary:

---------

@author: {USER}

"""

import feapder

class ${spider_name}(feapder.BatchSpider):

# 自定义数据库，若项目中有setting.py文件，此自定义可删除

__custom_setting__ = dict(

REDISDB_IP_PORTS="localhost:6379",

REDISDB_USER_PASS="",

REDISDB_DB=0,

MYSQL_IP="localhost",

MYSQL_PORT=3306,

MYSQL_DB="feapder",

MYSQL_USER_NAME="feapder",

MYSQL_USER_PASS="feapder123",

)

def start_requests(self, task):

yield feapder.Request("https://spidertools.cn")

def parse(self, request, response):

# 提取网站title

print(response.xpath("//title/text()").extract_first())

# 提取网站描述

print(response.xpath("//meta[@name='description']/@content").extract_first())

print("网站地址: ", response.url)

if __name__ == "__main__":

spider = ${spider_name}(

redis_key="xxx:xxxx", # redis中存放任务等信息的根key

task_table="", # mysql中的任务表

task_keys=["id", "xxx"], # 需要获取任务表里的字段名，可添加多个

task_state="state", # mysql中任务状态字段

batch_record_table="xxx_batch_record", # mysql中的批次记录表

batch_name="xxx(周全)", # 批次名字

batch_interval=7, # 批次周期 天为单位 若为小时 可写 1 / 24

)

# spider.start_monitor_task() # 下发及监控任务

spider.start() # 采集