how to not scrape data which is already present in mongodb in scrapy code example

Example 1: How to send data to scrapy pipeline to mongodb

# In your pipeline

class EPGD_pipeline(object):
    def __init__(self):
        self.collections = {
            spider_name: self.setup_db_connection(dj_mongo_database_url.parse(url))
            for spider_name, url in settings['MONGODB_PIPELINE_SETTINGS'].iterItems()
        )
    }

    def process_item(self, item, spider):
        collection = self.collections[spider.name]
        ...


# In settings.py

MONGODB_PIPELINE_SETTINGS = {
    "GenDis": "mongodb://myhost:29297/test_db/collection",
    "EPGD": "mongodb://myhost:29297/test_db/collection2",
}

Example 2: How to send data to scrapy pipeline to mongodb

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

Tags:

Misc Example