数据库轮子

1.MONGODB

MONGO_URL='localhost'
MONGO_DB='image360'

 

import pymongo

class HtestPipeline(object):
    def process_item(self, item, spider):
        return item

class MongoDBPipeline(object):
    def __init__(self,mongo_uri,mongo_db):
        self.mongo_uri=mongo_uri
        self.mongo_db=mongo_db

    @classmethod
    def from_crawler(cls,crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URL'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )

    def open_spider(self,spider):
        self.client=pymongo.MongoClient(self.mongo_uri)
        self.db=self.client[self.mongo_db]


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

    def process_item(self, item, spider):
        self.db[item.collection].insert(dict(item))
        return item

2.MYSQL 提前建好表文件

MYSQL_HOST='localhost'
MYSQL_DATABASER='imag360'
MYSQL_USER='root'
MYSQL_PASSWORD='123456'
MYSQL_PORT=3306

 

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

    @classmethod
    def from_crawler(cls,crawler):

        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            database = crawler.settings.get('MYSQL_DATABASER'),
            user = crawler.settings.get('MYSQL_USER'),
            password = crawler.settings.get('MYSQL_PASSWORD'),
            port = crawler.settings.get('MYSQL_PORT'),
        )

    def open_spider(self,spider):
        self.db=pymysql.connect(self.host,
                                self.user,
                                self.password,
                                self.database,
                                charset='utf8',
                                port=self.port)
        self.cursor=self.db.cursor()

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

    def process_item(self,item,spider):
        data=dict(item)
        keys=','.join(data.keys())
        values=','.join(['%s']*len(data))
        sql='INSERT INTO %s (%s) VALUES (%s)' % (item.table,keys,values)
        self.cursor.execute(sql,tuple(data.values()))
        self.db.commit()
        return item

 

转载于:https://www.cnblogs.com/404NooFound/p/10385819.html