Scraping multiple pages with multiple start_urls

Question

I want to scrape the details present in json form using scrapy. They are multiple start_urls and each start_url have multiple pages to scrape with. I am just not able to get the logic of how to do so.

import scrapy
from scrapy.http import Request

BASE_URL = ["https://www.change.org/api-proxy/-/tags/animals-19/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/civic/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/human-rights-en-in/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/child-rights-2/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/health-9/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/environment-18/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/education-en-in/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/women-s-rights-13/petitions?offset={}&limit=8&show_promoted_cards=true"
        ]

class ChangeSpider(scrapy.Spider):
    name = 'change'

    def start_requests(self):
        for i in range(len(BASE_URL)):
            yield Request(BASE_URL[i], callback = self.parse)

    pageNumber = 11

    def parse(self, response):
        data = response.json()
        for item in range(len(data['items'])):
            yield {
                "petition_id": data['items'][item]['petition']['id'],
            }

        next_page = "https://www.change.org/api-proxy/-/tags/animals-19/petitions?offset=" + str(ChangeSpider.pageNumber) + "&limit=8&show_promoted_cards=true"       
        if data['last_page'] == False:
            ChangeSpider.pageNumber += 1
            yield response.follow(next_page, callback=self.parse) 

Answer 1

Try like this:

import scrapy
from scrapy.http import Request


class ChangeSpider(scrapy.Spider):
    name = 'change'

    start_urls = ["https://www.change.org/api-proxy/-/tags/animals-19/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/civic/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/human-rights-en-in/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/child-rights-2/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/health-9/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/environment-18/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/education-en-in/petitions?offset={}&limit=8&show_promoted_cards=true",
        "https://www.change.org/api-proxy/-/tags/women-s-rights-13/petitions?offset={}&limit=8&show_promoted_cards=true"
        ]

    pageNumber = 11

    def parse(self, response):
        data = response.json()
        for item in range(len(data['items'])):
            yield {
                "petition_id": data['items'][item]['petition']['id'],
            }

        next_page = "https://www.change.org/api-proxy/-/tags/animals-19/petitions?offset=" + str(ChangeSpider.pageNumber) + "&limit=8&show_promoted_cards=true"       
        if data['last_page'] == False:
            ChangeSpider.pageNumber += 1
            yield response.follow(next_page, callback=self.parse)