Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adiciona Spider para Japeri-RJ #1337

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Adiciona Spider para Japeri-RJ #1337

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions data_collection/gazette/spiders/rj/rj_japeri.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
from datetime import date

import dateparser

from gazette.items import Gazette
from gazette.spiders.base import BaseGazetteSpider


class RjJaperiSpider(BaseGazetteSpider):
TERRITORY_ID = "3302270"
name = "rj_japeri"
allowed_domains = ["pmjaperi.geosiap.net.br"]
start_date = date(2019, 7, 22)
start_urls = [
"https://pmjaperi.geosiap.net.br/portal-transparencia/api/default/publicacoes/publicacoes"
]

def parse(self, response):
for item in response.json()["publicacoes"]:
if item["ds_publicacao_tipo"] != "DIÁRIO OFICIAL":
continue
date = dateparser.parse(
item["dt_publicacao_formatado"], languages=["pt"]
).date()
url = f"https://pmjaperi.geosiap.net.br/portal-transparencia/api/default/publicacoes/get_arquivo?id_publicacao={item['id_publicacao']}"
yield Gazette(
date=date, file_urls=[url], is_extra_edition=False, power="executive"
)
Loading