ITEM_PIPELINES = {
# 'xx.pipelines.FirstPipeline': 1,
'xx.pipelines.DuplicatesPipeline': 2,
'xx.pipelines.MongoPipeline': 3,
}

# -*- coding: utf-8 -*-
import pymongo
from scrapy.exceptions import DropItem
class FirstPipeline(object):
def process_item(self, item, spider):
    pass
class DuplicatesPipeline(object):
def __init__(self):
    self.urls_seen = set()
def process_item(self, item, spider):
    #item['url']是和items.py的Fields保持一致的
    if item['url'] in self.urls_seen:
        raise DropItem("Duplicat item found: %s" % item)
    else:
        self.urls_seen.add(item['url'])
        return item
class MongoPipeline(object):
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):
    collection_name = item.__class__.__name__
    self.db[collection_name].insert(dict(item))
    return item