scrapy框架mongodb正规存储

import pymongo


class SpiderPipeline(object):

    def __init__(self, mongo_uri, mongo_db):
        # mongodb的路由
        self.mongo_uri = mongo_uri
        # mongodb的库名
        self.mongo_db = mongo_db

    def open_spider(self, spider):
        # spider开始时被调用
        self.client = pymongo.MongoClient(self.mongo_uri)
        # db
        self.db = self.client[self.mongo_db]


    @classmethod
    def from_crawler(cls, crawler):
        # 获取配置文件
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DB'),
        )

    def process_item(self, item, spider):
        # 与数据库交互存储数据
        self.db['dunzi'].insert(dict(item))
        return item

    def close_spider(self, spider):
        # spider关闭时被调用
        self.client.close()