scrapy编辑mysql数据库

ITEM_PIPELINES = {
    'your_project.pipelines.MySQLPipeline': 300,  # 设置优先级，数字越小优先级越高
}

MYSQL_HOST = 'localhost'  # MySQL主机
MYSQL_PORT = 3306  # MySQL端口
MYSQL_DATABASE = 'scrapy_db'  # 数据库名
MYSQL_USER = 'your_username'  # MySQL用户名
MYSQL_PASSWORD = 'your_password'  # MySQL密码

import pymysql

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

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            port=crawler.settings.get('MYSQL_PORT'),
            database=crawler.settings.get('MYSQL_DATABASE'),
            user=crawler.settings.get('MYSQL_USER'),
            password=crawler.settings.get('MYSQL_PASSWORD')
        )

    def open_spider(self, spider):
        self.db = pymysql.connect(
            host=self.host,
            port=self.port,
            database=self.database,
            user=self.user,
            password=self.password
        )
        self.cursor = self.db.cursor()

    def close_spider(self, spider):
        self.db.close()

    def process_item(self, item, spider):
        sql = "INSERT INTO items(title, url) VALUES(%s, %s)"
        values = (item['title'], item['url'])
        self.cursor.execute(sql, values)
        self.db.commit()
        return item

from your_project.items import YourItem

class YourSpider(scrapy.Spider):
    name = 'your_spider'
    allowed_domains = ['example.com']
    start_urls = ['http://www.example.com']

    def parse(self, response):
        item = YourItem()
        item['title'] = response.css('h1::text').get()
        item['url'] = response.url
        yield item

scrapy crawl your_spider