Pipeline MongoDB

class scrapy_pipelines.pipelines.mongo.MongoPipeline(uri: str, settings: scrapy.settings.Settings)

A pipeline saved into MongoDB asynchronously with txmongo

close_spider(spider: scrapy.spiders.Spider)
Parameters

spider (Spider) –

Returns

Return type

create_indexes(spider: scrapy.spiders.Spider)
Parameters

spider (Spider) –

Returns

Return type

classmethod from_crawler(crawler: scrapy.crawler.Crawler)
Parameters

crawler (Crawler) –

Returns

Return type

MongoPipeline

classmethod from_settings(settings: scrapy.settings.Settings)
Parameters

settings (Settings) –

Returns

Return type

MongoPipeline

item_completed(result: str, item: scrapy.item.Item, spider: scrapy.spiders.Spider) → scrapy.item.Item
Parameters
  • result (str) –

  • item (Item) –

  • spider (Spider) –

Returns

Return type

Item

open_spider(spider: scrapy.spiders.Spider)
Parameters

spider (Spider) –

Returns

Return type

process_item(item: scrapy.item.Item, spider: scrapy.spiders.Spider) → scrapy.item.Item
Parameters
  • item (Item) –

  • spider (Spider) –

Returns

Return type

Item

process_item_id(signal: object, sender: scrapy.crawler.Crawler, item: scrapy.item.Item, spider: scrapy.spiders.Spider) → pymongo.results.InsertOneResult
Parameters
  • signal (object) –

  • sender (Crawler) –

  • item (Item) –

  • spider (Spider) –

Returns

Return type

InsertOneResult