Created
March 6, 2015 09:07
-
-
Save marianmoldovan/03996da2151586a6e600 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pymongo | |
from scrapy.exceptions import DropItem | |
from scrapy.conf import settings | |
from scrapy import log | |
class MongoDBPipeline(object): | |
def __init__(self): | |
connection = pymongo.Connection(settings['MONGODB_SERVER'], settings['MONGODB_PORT']) | |
db = connection[settings['MONGODB_DB']] | |
self.collection = db[settings['MONGODB_COLLECTION']] | |
def process_item(self, item, spider): | |
valid = True | |
for data in item: | |
# here we only check if the data is not null | |
# but we could do any crazy validation we want | |
if not data: | |
valid = False | |
raise DropItem("Missing %s of blogpost from %s" %(data, item['url'])) | |
if valid: | |
self.collection.insert(dict(item)) | |
log.msg("Item wrote to MongoDB database %s/%s" % | |
(settings['MONGODB_DB'], settings['MONGODB_COLLECTION']), | |
level=log.DEBUG, spider=spider) | |
return item |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment