Revision: 58215
Updated Code
at July 1, 2012 18:09 by hlongmore
Updated Code
# 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 %s\n' % (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
Revision: 58214
Initial Code
Initial URL
Initial Description
Initial Title
Initial Tags
Initial Language
at July 1, 2012 18:06 by hlongmore
Initial Code
# TODO: finish after posting, to get around the capthca not showing up.
Initial URL
Initial Description
In connection with my [poetry spider](http://snipplr.com/view/65893/a-simple-spider-using-scrapy/), this scrapy pipeline class facilitates storing the scraped data to a MongoDB database.
Initial Title
Scrapy pipeline class to store scraped data in MongoDB
Initial Tags
Initial Language
Python