scarpy中把数据保存到mysql怎么实现

实现步骤如下：

1. 安装mysql-connector-python模块

pip install mysql-connector-python

2. 在settings.py文件中配置MySQL数据库连接信息

MYSQL_HOST = 'localhost'
MYSQL_PORT = 3306
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'your_password'
MYSQL_DATABASE = 'your_database_name'

3. 在pipelines.py文件中编写MySQL存储管道

import mysql.connector

class MysqlPipeline(object):
    def __init__(self, mysql_host, mysql_port, mysql_user, mysql_password, mysql_database):
        self.mysql_host = mysql_host
        self.mysql_port = mysql_port
        self.mysql_user = mysql_user
        self.mysql_password = mysql_password
        self.mysql_database = mysql_database

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mysql_host = crawler.settings.get('MYSQL_HOST'),
            mysql_port = crawler.settings.get('MYSQL_PORT'),
            mysql_user = crawler.settings.get('MYSQL_USER'),
            mysql_password = crawler.settings.get('MYSQL_PASSWORD'),
            mysql_database = crawler.settings.get('MYSQL_DATABASE')
        )

    def open_spider(self, spider):
        self.conn = mysql.connector.connect(
            host=self.mysql_host,
            port=self.mysql_port,
            user=self.mysql_user,
            password=self.mysql_password,
            database=self.mysql_database
        )
        self.cursor = self.conn.cursor()

    def close_spider(self, spider):
        self.conn.commit()
        self.cursor.close()
        self.conn.close()

    def process_item(self, item, spider):
        insert_sql = '''
            INSERT INTO table_name (field1, field2, field3)
            VALUES (%s, %s, %s)
        '''
        self.cursor.execute(insert_sql, (item['field1'], item['field2'], item['field3']))
        return item

4. 在settings.py文件中启用MySQL存储管道

ITEM_PIPELINES = {
    'your_project_name.pipelines.MysqlPipeline': 300,
}

其中，300是优先级，数字越小，优先级越高。

5. 在Spider中编写item数据

import scrapy

class MySpider(scrapy.Spider):
    name = 'my_spider'

    def start_requests(self):
        yield scrapy.Request(url='http://example.com', callback=self.parse)

    def parse(self, response):
        item = {}
        item['field1'] = response.xpath('//h1/text()').get()
        item['field2'] = response.xpath('//h2/text()').get()
        item['field3'] = response.xpath('//h3/text()').get()
        yield item

这样，当Spider爬取到数据时，会自动调用MysqlPipeline进行存储。