From 8f39adb980ba3bc615e17fe1b7617a3486a06cc2 Mon Sep 17 00:00:00 2001
From: Bastien Le Querrec <blq@laquadrature.net>
Date: Wed, 20 Mar 2024 23:11:08 +0100
Subject: [PATCH] =?UTF-8?q?pref13:=20am=C3=A9liore=20la=20d=C3=A9tection?=
=?UTF-8?q?=20des=20balises=20a=20et=20valide=20la=20pr=C3=A9sence=20d'un?=
=?UTF-8?q?=20lien?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
RAAspotter_pref13.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/RAAspotter_pref13.py b/RAAspotter_pref13.py
index d8edba8..0285e12 100644
--- a/RAAspotter_pref13.py
+++ b/RAAspotter_pref13.py
@@ -42,8 +42,8 @@ class RAAspotter_pref13(RAAspotter):
soup = BeautifulSoup(page_content, 'html.parser')
# Pour chaque balise a, on regarde si c'est un PDF, et si oui on le parse
- for a in soup.find_all('a', href=True, class_='fr-link--download'):
- if a['href'].endswith('.pdf'):
+ for a in soup.select('a.fr-link.fr-link--download'):
+ if a.get('href') and a['href'].endswith('.pdf'):
if a['href'].startswith('/'):
url = f"{self.__HOST}{a['href']}"
else:
--
GitLab