Python爬虫之Scrapy数据保存MongoDB

首先在Pipelines.py中创建一个类：

class MongoPipline(object):
    def __init__(self, mongo_url, mongo_db):
        self.mongo_url = mongo_url
        self.mongo_db = mongo_db

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

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

    def process_item(self, item, spider):
        # name =item.__class__.__name__
        self.db['Article'].insert(dict(item))
        return item

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

在Settings.py文件中加入MongoDB的地址和数据库如：

MONGO_URL = 'localhost'
MONGO_DB = 'Article'