scrapy Pipeline使用twisted异步实现mysql数据插入

from twisted.enterprise import adbapi
class MySQLAsyncPipeline:
    def open_spider(self, spider):
        db = spider.settings.get('MYSQL_DB_NAME', 'scrapy_default')
        host = spider.settings.get('MYSQL_HOST', 'localhost')
        port = spider.settings.get('MYSQL_PORT', 3306)
        user = spider.settings.get('MYSQL_USER', 'root')
        passwd = spider.settings.get('MYSQL_PASSWORD', 'root')


        self.dbpool = adbapi.ConnectionPool('MySQLdb', host=host, db=db,
                                    user=user, passwd=passwd, port=port, charset='utf8')
                                    
    def close_spider(self, spider):
        self.dbpool.close()


    def process_item(self, item, spider):
        self.dbpool.runInteraction(self.insert_db, item)

        return item


    def insert_db(self, tx, item):
        values = (
            item['f1'],
            item['f2'],
        )

        sql = 'INSERT INTO books VALUES (%s,%s)'
        tx.execute(sql, values)

 #redis入库

import redis
from scrapy import Item


class RedisPipeline:
    def open_spider(self, spider):
        db_host = spider.settings.get('REDIS_HOST', 'localhost')
        db_port = spider.settings.get('REDIS_PORT', 6379)
        db_index = spider.settings.get('REDIS_DB_INDEX', 0)

        self.db_conn = redis.StrictRedis(host=db_host, port=db_port, db=db_index)
        self.item_i = 0

    def close_spider(self, spider):
        self.db_conn.connection_pool.disconnect()
    
    def process_item(self, item, spider):
        self.insert_db(item)
        return item

    def insert_db(self, item):
        if isinstance(item, Item):
            item = dict(item)

        self.item_i += 1
        self.db_conn.hmset('book:%s' % self.item_i, item)

　　

转载于:https://www.cnblogs.com/mahailuo/p/11224107.html