Skip to content

Commit

Permalink
malta: Order requests to get most recent data first #451
Browse files Browse the repository at this point in the history
  • Loading branch information
jpmckinney committed Mar 26, 2021
1 parent f06fd7e commit a3c4cbe
Show file tree
Hide file tree
Showing 3 changed files with 3 additions and 1 deletion.
1 change: 1 addition & 0 deletions kingfisher_scrapy/spiders/france.py
Expand Up @@ -16,6 +16,7 @@ class France(BigFileSpider):
def start_requests(self):
# A CKAN API JSON response.
# Ministère de l'économie, des finances et de la relance
# https://www.data.gouv.fr/fr/datasets/donnees-essentielles-de-la-commande-publique-fichiers-consolides/
url = 'https://www.data.gouv.fr/api/1/datasets/donnees-essentielles-de-la-commande-publique-fichiers' \
'-consolides/'
yield scrapy.Request(url, meta={'file_name': 'page-1.json'}, callback=self.parse_list)
Expand Down
2 changes: 1 addition & 1 deletion kingfisher_scrapy/spiders/malta.py
Expand Up @@ -30,7 +30,7 @@ def parse_list(self, response):
urls = response.json()['packagesPerMonth']

netloc = urlsplit(response.request.url).netloc
for url in urls:
for url in reversed(urls):
# URL looks like http://malta-demo-server.eurodyn.com/ocds/services/recordpackage/getrecordpackage/2020/1
yield self.build_request(urlsplit(url)._replace(netloc=netloc).geturl(),
formatter=join(components(-2), extension='zip'))
Expand Up @@ -28,4 +28,5 @@ class MexicoAdministracionPublicaFederalAPI(IndexSpider):

def start_requests(self):
url = 'https://api.datos.gob.mx/v2/contratacionesabiertas'
# The pages are in reverse chronological order.
yield scrapy.Request(url, meta={'file_name': 'page-1.json'}, callback=self.parse_list)

0 comments on commit a3c4cbe

Please sign in to comment.