python mongodb scrapy例子

#-*-coding:utf8-*-
import pymongo

connection = pymongo.MongoClient()
tdb = connection.test
post_info = tdb.abc
cursor = post_info.find()


jike = {'name':u'极客', 'age':'5', 'skill': 'Python'}
god = {'name': u'玉皇大帝', 'age': 36000, 'skill': 'creatanything', 'other': u'王母娘娘不是他的老婆'}
godslaver = {'name': u'月老', 'age': 'unknown', 'other': u'他的老婆叫孟婆'}
post_info.insert(jike)
post_info.insert(god)
post_info.insert(godslaver)
for document in cursor:
    print(document)
post_info.remove({'name': u'极客'})


print u'操作数据库完成！'

scrapy内

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
from items import NovelspiderItem  #这里的Novelspider其实是没有用到的，可以删除
from scrapy.conf import settings
import pymongo

class NovelspiderPipeline(object):
    def __init__(self):
        host = settings['MONGODB_HOST']
        port = settings['MONGODB_PORT']
        dbName = settings['MONGODB_DBNAME']
        client = pymongo.MongoClient(host=host, port=port)
        tdb = client[dbName]
        self.post = tdb[settings['MONGODB_DOCNAME']]

    def process_item(self, item, spider):
        bookInfo = dict(item)
        self.post.insert(bookInfo)
        return item