Melhora coleta de metadado usando regex

Signed-off-by: Juliana Trevine <44185775+trevineju@users.noreply.github.com>
okfn-brasil · Sep 25, 2024 · f023d01 · f023d01
1 parent d924ff2
commit f023d01
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/data_collection/gazette/spiders/rj/rj_macae.py b/data_collection/gazette/spiders/rj/rj_macae.py
@@ -31,7 +31,9 @@ def parse(self, response):
             gazette_edition = data["edicao"]
             gazette_edition_number = re.search(r"\d+", gazette_edition).group(0)
 
-            raw_gazette_date = data["publicacao"][0:10]
+            raw_gazette_date = re.search(
+                r"\d{2}\/\d{2}\/\d{4}", data["publicacao"]
+            ).group()
             gazette_date = dt.strptime(raw_gazette_date, "%d/%m/%Y").date()
 
             gazette_item = {