Usa urllib.parse para lidar melhor com URLs

AtilioA · Apr 1, 2020 · d6362f7 · d6362f7
1 parent dc61e11
commit d6362f7
Showing 1 changed file with 7 additions and 2 deletions.
diff --git a/COVID19_ES_Py/boletim.py b/COVID19_ES_Py/boletim.py
@@ -4,6 +4,7 @@
 """
 
 import re
+from urllib.parse import urljoin
 import logging
 import unicodedata
 import requests
@@ -135,7 +136,7 @@ def url_ultimo_boletim(self, html=None):
                 "article", class_="noticia list-content-item content-item"
             )
             ultimaNoticia = articleNoticia.find("a")["href"]
-            return ultimaNoticia
+            return urljoin(DOMINIO_BOLETINS, ultimaNoticia)
         except AttributeError:
             return None
 
@@ -182,7 +183,7 @@ def pesquisa_boletim_data(self, data):
                             dataBoletim = arrow.get(
                                 matchData.group(0), "DD/MM/YYYY")
                             if dataBoletim == dataArrow:
-                                return Boletim(f"{DOMINIO_BOLETINS}{linkBoletim}")
+                                return Boletim(urljoin(DOMINIO_BOLETINS, linkBoletim))
         return None
 
 
@@ -434,3 +435,7 @@ def filtra_municipios_com_casos(self):
         }
 
         return municipiosComCasos
+
+
+a = ScraperBoletim()
+b = a.url_ultimo_boletim()