首页 > 代码库 > scrapy MysqlPipeline 同步和异步
scrapy MysqlPipeline 同步和异步
import MySQLdb import MySQLdb.cursors class MysqlPipeline(object): #采用同步的机制写入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将mysql插入变成异步执行 query = self.dbpool.runInteraction(self.do_insert, item) query.addErrback(self.handle_error, item, spider) #处理异常 def handle_error(self, failure, item, spider): # 处理异步插入的异常 print (failure) def do_insert(self, cursor, item): #执行具体的插入 #根据不同的item 构建不同的sql语句并插入到mysql中 insert_sql, params = item.get_insert_sql() print (insert_sql, params) cursor.execute(insert_sql, params)
scrapy MysqlPipeline 同步和异步
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。