import MySQLdb
import MySQLdb.cursors


class MysqlPipeline(object):
    #采用同步的機制寫入mysql
    def __init__(self):
        self.conn = MySQLdb.connect(‘192.168.0.106‘, ‘root‘, ‘root‘, ‘article_spider‘, charset="utf8", use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql = """
            insert into jobbole_article(title, url, create_date, fav_nums)
            VALUES (%s, %s, %s, %s)
        """
        self.cursor.execute(insert_sql, (item["title"], item["url"], item["create_date"], item["fav_nums"]))
        self.conn.commit()


class MysqlTwistedPipline(object):
    def __init__(self, dbpool):
        self.dbpool = dbpool

    @classmethod
    def from_settings(cls, settings):
        dbparms = dict(
            host = settings["MYSQL_HOST"],
            db = settings["MYSQL_DBNAME"],
            user = settings["MYSQL_USER"],
            passwd = settings["MYSQL_PASSWORD"],
            charset=‘utf8‘,
            cursorclass=MySQLdb.cursors.DictCursor,
            use_unicode=True,
        )
        dbpool = adbapi.ConnectionPool("MySQLdb", **dbparms)

        return cls(dbpool)

    def process_item(self, item, spider):
        #使用twisted將mysql插入變成異步執行
        query = self.dbpool.runInteraction(self.do_insert, item)
        query.addErrback(self.handle_error, item, spider) #處理異常

    def handle_error(self, failure, item, spider):
        # 處理異步插入的異常
        print (failure)

    def do_insert(self, cursor, item):
        #執行具體的插入
        #根據不同的item 構建不同的sql語句並插入到mysql中
        insert_sql, params = item.get_insert_sql()
        print (insert_sql, params)
        cursor.execute(insert_sql, params)

scrapy MysqlPipeline 同步和異步