scrapy中把数据写入mongodb

1.setting.py中打开管道

ITEM_PIPELINES = {
   # ‘tianmao.pipelines.TianmaoPipeline‘: 300,
}

2.setting.py中写入mongodb配置

# mongodb
HOST = "127.0.0.1"  # 服务器地址
PORT = 27017  # mongo默认端口号
USER = "用户名"
PWD = "密码"
DB = "数据库名"
TABLE = "表名"

3.pipeline.py文件中倒入pymongo，数据写入数据库

from pymongo import MongoClient

class TianmaoPipeline(object):
    def __init__(self, host, port, user, pwd, db, table):
        self.host = host
        self.port = port
        self.user = user
        self.pwd = pwd
        self.db = db
        self.table = table

    @classmethod
    def from_crawler(cls, crawler):
        HOST = crawler.settings.get(‘HOST‘)
        PORT = crawler.settings.get(‘PORT‘)
        USER = crawler.settings.get(‘USER‘)
        PWD = crawler.settings.get(‘PWD‘)
        DB = crawler.settings.get(‘DB‘)
        TABLE = crawler.settings.get(‘TABLE‘)
        return cls(HOST, PORT, USER, PWD, DB, TABLE)

    def open_spider(self, spider):
        self.client = MongoClient(‘mongodb://%s:%[email protected]%s:%s‘ %(self.user,self.pwd,self.host,self.port))

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

    def process_item(self, item, spider):
        self.client[self.db][self.table].save(dict(item))