本文实例讲述了scrapy自定义pipeline类实现将采集数据保存到mongodb的方法。分享给大家供大家参考。具体如下:
# Standard Python library imports # 3rd party modules import pymongo from scrapy import log from scrapy.conf import settings from scrapy.exceptions import DropItem class MongoDBPipeline(object): def __init__(self): self.server = settings['MONGODB_SERVER'] self.port = settings['MONGODB_PORT'] self.db = settings['MONGODB_DB'] self.col = settings['MONGODB_COLLECTION'] connection = pymongo.Connection(self.server, self.port) db = connection[self.db] self.collection = db[self.col] def process_item(self, item, spider): err_msg = '' for field, data in item.items(): if not data: err_msg += 'Missing %s of poem from %sn' % (field, item['url']) if err_msg: raise DropItem(err_msg) self.collection.insert(dict(item)) log.msg('Item written to MongoDB database %s/%s' % (self.db, self.col), level=log.DEBUG, spider=spider) return item
希望本文所述对大家的python程序设计有所帮助。