Home > Net >  Scrapy: can´t export json to csv
Scrapy: can´t export json to csv

Time:05-08

I have this script:

    import scrapy
    from scrapy.crawler import CrawlerProcess
    from datetime import datetime
    import os
    
    
    if os.path.exists('jfs_hombre.csv'):
        os.remove('jfs_hombre.csv')
        print("The file has been deleted successfully")
    else:
        print("The file does not exist!")
    
    
    class JfsSpider_hombre(scrapy.Spider):
        name = 'jfs_hombre'
        #start_urls = ["https://www.justforsport.com.ar/hombre?page=1"]
            
        def start_requests(self):
    
            yield scrapy.Request(
                url='https://www.justforsport.com.ar/_v/segment/graphql/v1?workspace=master&maxAge=short&appsEtag=remove&domain=store&locale=es-AR&__bindingId=e841e6ce-1216-4569-a2ad-0188ba5a92fc&operationName=productSearchV3&variables={}&extensions={"persistedQuery":{"version":1,"sha256Hash":"6869499be99f20964918e2fe0d1166fdf6c006b1766085db9e5a6bc7c4b957e5","sender":"[email protected]","provider":"[email protected]"},"variables":"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"}',
                callback=self.parse,
                method="GET"
            )
    
        def parse(self, response):
            resp = response.json()
            #print(resp)
            for item in range(0,576,32):
                resp['recordsFiltered']=item
           
                for result  in resp['data']['productSearch']['products']:
                    yield {
                        'Casa':'Just_For_Sports',
                        'Sku' :result['productReference'],
                        'Name': result['productName'],
                        'precio': result['priceRange']['sellingPrice']['highPrice'],
                        'Link': result['link'],
                        'Date':datetime.today().strftime('%Y-%m-%d')
    
                    }
    
    
    process= CrawlerProcess(
        settings = { 
            'FEED_URI':'jfs_hombre.csv' ,
            'FEED_FORMAT': 'csv',
            'FEED_EXPORT_ENCODING':'utf-8',
            } )   

if __name__ == "__main__":
    process =CrawlerProcess()
    process.crawl(JfsSpider_hombre)
    process.start()

It´s the first time I work with Call Api, Json...So I know nothing about it, bu I ´ve been working with scrapy. The problem is that I can't get the .csv , it´s not creating any file...The scraper works fine, I get all the data, but can´t export it...what am I doing wrong??

Thanks in advance!

CodePudding user response:

Now, it's working

import scrapy
from scrapy.crawler import CrawlerProcess
from datetime import datetime
import os
    
    
if os.path.exists('jfs_hombre.csv'):
    os.remove('jfs_hombre.csv')
    print("The file has been deleted successfully")
else:
    print("The file does not exist!")
    
    
class JfsSpider_hombre(scrapy.Spider):
    name = 'jfs_hombre'

    #start_urls = ["https://www.justforsport.com.ar/hombre?page=1"]

    custom_settings = {"FEEDS": {'jfs_hombre.csv': {'format': 'csv'}}} 

    def start_requests(self):
    
        yield scrapy.Request(
            url='https://www.justforsport.com.ar/_v/segment/graphql/v1?workspace=master&maxAge=short&appsEtag=remove&domain=store&locale=es-AR&__bindingId=e841e6ce-1216-4569-a2ad-0188ba5a92fc&operationName=productSearchV3&variables={}&extensions={"persistedQuery":{"version":1,"sha256Hash":"6869499be99f20964918e2fe0d1166fdf6c006b1766085db9e5a6bc7c4b957e5","sender":"[email protected]","provider":"[email protected]"},"variables":"eyJoaWRlVW5hdmFpbGFibGVJdGVtcyI6ZmFsc2UsInNrdXNGaWx0ZXIiOiJGSVJTVF9BVkFJTEFCTEUiLCJzaW11bGF0aW9uQmVoYXZpb3IiOiJkZWZhdWx0IiwiaW5zdGFsbG1lbnRDcml0ZXJpYSI6Ik1BWF9XSVRIT1VUX0lOVEVSRVNUIiwicHJvZHVjdE9yaWdpblZ0ZXgiOmZhbHNlLCJtYXAiOiJjIiwicXVlcnkiOiJob21icmUiLCJvcmRlckJ5IjoiT3JkZXJCeVJlbGVhc2VEYXRlREVTQyIsImZyb20iOjY0LCJ0byI6OTUsInNlbGVjdGVkRmFjZXRzIjpbeyJrZXkiOiJjIiwidmFsdWUiOiJob21icmUifV0sIm9wZXJhdG9yIjoiYW5kIiwiZnV6enkiOiIwIiwic2VhcmNoU3RhdGUiOm51bGwsImZhY2V0c0JlaGF2aW9yIjoiU3RhdGljIiwiY2F0ZWdvcnlUcmVlQmVoYXZpb3IiOiJkZWZhdWx0Iiwid2l0aEZhY2V0cyI6ZmFsc2V9"}',
            callback=self.parse,
            method="GET"
        )
    
    def parse(self, response):
        resp = response.json()
        #print(resp)
        for item in range(0,576,32):
            resp['recordsFiltered']=item
           
            for result  in resp['data']['productSearch']['products']:
                yield {
                    'Casa':'Just_For_Sports',
                    'Sku' :result['productReference'],
                    'Name': result['productName'],
                    'precio': result['priceRange']['sellingPrice']['highPrice'],
                    'Link': 'https://www.justforsport.com.ar'   result['link'],
                    'Date':datetime.today().strftime('%Y-%m-%d')
                    }
    
    
  

if __name__ == "__main__":
    process =CrawlerProcess()
    process.crawl(JfsSpider_hombre)
    process.start()
  • Related