[Novo spider base]: NucleoGov - Anápolis, GO

data_collection/gazette/spiders/base/nucleogov.py

@@ -0,0 +1,41 @@
+import json
+from datetime import datetime
+
+import scrapy
+from dateutil.rrule import DAILY, rrule
+
+from gazette.items import Gazette
+from gazette.spiders.base import BaseGazetteSpider
+
+
+class NucleoGovGazetteSpider(BaseGazetteSpider):
+    def start_requests(self):
+        days = rrule(freq=DAILY, dtstart=self.start_date, until=self.end_date)
+        for day in days:
+            yield scrapy.Request(self.url_base.format(day.strftime("%Y-%m-%d")))
+
+    def parse(self, response):
+        data = json.loads(response.text)
+
+        gazettes = data.get("data")
+        for gazette in gazettes:
+            gazette_urls = []
+
+            if gazette.get("media_legacy"):
+                gazette_urls.append(gazette.get("media_legacy"))
+            else:
+                midias = gazette.get("midias")
+
+                for midia in midias:
+                    gazette_urls.append(midia.get("url"))
+
+            gazette_date = datetime.strptime(gazette.get("data"), "%Y-%m-%d")
+            edition_number = gazette.get("numero")
+
+            yield Gazette(
+                date=gazette_date.date(),
+                file_urls=gazette_urls,
+                edition_number=edition_number,
+                power="executive",
+                is_extra_edition=False,
+            )

data_collection/gazette/spiders/go/go_anapolis.py

@@ -0,0 +1,16 @@
+import datetime as dt
+
+from gazette.spiders.base.nucleogov import NucleoGovGazetteSpider
+
+
+class GoAnapolisSpider(NucleoGovGazetteSpider):
+    name = "go_anapolis"
+    TERRITORY_ID = "5201108"
+    allowed_domains = [
+        "dom.anapolis.go.gov.br",
+    ]
+    url_base = (
+        "https://dom.anapolis.go.gov.br/api/diarios?data={}&calendar=true&situacao=2"
+    )
+
+    start_date = dt.date(2010, 5, 31)

data_collection/gazette/spiders/go/go_valparaiso_de_goias.py

@@ -0,0 +1,14 @@
+import datetime as dt
+
+from gazette.spiders.base.nucleogov import NucleoGovGazetteSpider
+
+
+class GoValparaisoDeGoiasSpider(NucleoGovGazetteSpider):
+    name = "go_valparaiso_de_goias"
+    TERRITORY_ID = "5221858"
+    allowed_domains = [
+        "diariooficial.valparaisodegoias.go.gov.br",
+    ]
+    url_base = "https://diariooficial.valparaisodegoias.go.gov.br/api/diarios?data={}&calendar=true&situacao=2"
+
+    start_date = dt.date(2021, 2, 17)

data_collection/gazette/spiders/to/to_cariri_do_tocantins.py

@@ -0,0 +1,16 @@
+import datetime as dt
+
+from gazette.spiders.base.nucleogov import NucleoGovGazetteSpider
+
+
+class ToCaririDoTocantinsSpider(NucleoGovGazetteSpider):
+    name = "to_cariri_do_tocantins"
+    TERRITORY_ID = "1703867"
+    allowed_domains = [
+        "dom.cariri.to.gov.br",
+    ]
+    url_base = (
+        "https://dom.cariri.to.gov.br/api/diarios?data={}&calendar=true&situacao=2"
+    )
+
+    start_date = dt.date(2023, 1, 30)

data_collection/gazette/spiders/to/to_jau_do_tocantins.py

@@ -0,0 +1,14 @@
+import datetime as dt
+
+from gazette.spiders.base.nucleogov import NucleoGovGazetteSpider
+
+
+class ToJauDoTocantinsSpider(NucleoGovGazetteSpider):
+    name = "to_jau_do_tocantins"
+    TERRITORY_ID = "1711506"
+    allowed_domains = [
+        "diariooficial.jau.to.gov.br",
+    ]
+    url_base = "https://diariooficial.jau.to.gov.br/api/diarios?data={}&calendar=true&situacao=2"
+
+    start_date = dt.date(2023, 5, 15)

data_collection/gazette/spiders/to/to_parana.py

@@ -0,0 +1,14 @@
+import datetime as dt
+
+from gazette.spiders.base.nucleogov import NucleoGovGazetteSpider
+
+
+class ToParanaSpider(NucleoGovGazetteSpider):
+    name = "to_parana"
+    TERRITORY_ID = "1716208"
+    allowed_domains = [
+        "diariooficial.parana.to.gov.br",
+    ]
+    url_base = "https://diariooficial.parana.to.gov.br/api/diarios?data={}&calendar=true&situacao=2"
+
+    start_date = dt.date(2023, 5, 8)