Source code for kingfisher_scrapy.spiders.spain_zaragoza

import scrapy

from kingfisher_scrapy.base_spiders import SimpleSpider
from kingfisher_scrapy.util import BROWSER_USER_AGENT, components




class SpainZaragoza(SimpleSpider):
    """
    Domain
      Ayuntamiento de Zaragoza
    Caveats
      The API's before and after query string parameters have no effect and are therefore not implemented.
    Swagger API documentation
      https://www.zaragoza.es/docs-api_sede/
    """

    name = "spain_zaragoza"
    custom_settings = {
        "USER_AGENT": BROWSER_USER_AGENT,  # to avoid HTTP 500
    }

    # SimpleSpider
    data_type = "release_package"

    # Local
    url_prefix = "https://www.zaragoza.es/sede/servicio/contratacion-publica/ocds/contracting-process/"

    async def start(self):
        # `rows=100000` avoids pagination.
        yield scrapy.Request(f"{self.url_prefix}?rf=html&rows=100000", callback=self.parse_list)

    def parse_list(self, response):
        for item in response.json():
            yield self.build_request(f"{self.url_prefix}{item['ocid']}", formatter=components(-1))  # ocid