from pymongo import MongoClient
from scrapy.conf import settings
from scrapy.exceptions import DropItem
from scrapy import log
class MongoDBPipeline(object):
collection_name= 'members'
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_URI')
mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
)
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[self.collection_name].insert(dict(item))
return item