Apr-05-2020, 04:06 PM
I'am creating a spider to crawl webpage' json-ld schema markup and store data in mongodb. actually I want to scrape json-ld schema markup and extract the data type("@type" : "_____") from schema markup and store this @type in mongodb. My spiders crawl well whole schema markup code. But I want to know that How to extract @type from that json-ld schema markup and store it in mongodb.
This is my spider files
apple_spider.py
This is my spider files
apple_spider.py
import scrapy from pprint import pprint from extruct.jsonld import JsonLdExtractor from ..items import ApplespiderItem class AppleSpider(scrapy.Spider): name = 'apple' allowed_domains = ['apple.com'] start_urls = ( 'http://www.apple.com/shop/mac/mac-accessories', ) def parse(self, response): extractor = JsonLdExtractor() items = extractor.extract(response.body_as_unicode(), response.url) pprint(items) for item in items: if item.get('properties', {}).get('name'): properties = item['properties'] yield { 'name': properties['name'], 'price': properties['offers']['properties']['price'], 'url': properties['url'] }items.py
import scrapy class ApplespiderItem(scrapy.Item): # define the fields for your item here like: name = scrapy.Field() price = scrapy.Field() url = scrapy.Field()pipelines.py
import pymongo class ApplespiderPipeline(object): def __init__(self): self.conn = pymongo.MongoClient( 'localhost', 27017 ) db = self.conn['newdb'] self.collection = db['app_tb'] def process_item(self, item, spider): self.collection.insert(dict(item)) return item