From db3e1ccfe1698c9f3f55d0d0b4c0757d184ab7bf Mon Sep 17 00:00:00 2001
From: =?utf8?q?Roland=20H=C3=A4der?= <roland@mxchange.org>
Date: Tue, 20 Jun 2023 23:11:56 +0200
Subject: [PATCH] Continued: - also check for '<html', if not found then skip
 this broken HTML

---
 fba/csrf.py       | 3 ++-
 fba/federation.py | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fba/csrf.py b/fba/csrf.py
index 4eedcc7..859d5cb 100644
--- a/fba/csrf.py
+++ b/fba/csrf.py
@@ -50,8 +50,9 @@ def determine(domain: str, headers: dict) -> dict:
     )
 
     # DEBUG: print(f"DEBUG: response.ok='{response.ok}',response.status_code={response.status_code},response.text()={len(response.text)}")
-    if response.ok and len(response.text) > 0:
+    if response.ok and response.status_code < 300 and response.text.find("<html") > 0:
         # Save cookies
+        # DEBUG: print(f"DEBUG: Parsing response.text()={len(response.text)} Bytes ...")
         cookies.store(domain, response.cookies.get_dict())
 
         # Parse text
diff --git a/fba/federation.py b/fba/federation.py
index ec71617..1d15450 100644
--- a/fba/federation.py
+++ b/fba/federation.py
@@ -401,8 +401,8 @@ def fetch_generator_from_path(domain: str, path: str = "/") -> str:
     response = network.fetch_response(domain, path, network.web_headers, (config.get("connection_timeout"), config.get("read_timeout")))
 
     # DEBUG: print("DEBUG: domain,response.ok,response.status_code,response.text[]:", domain, response.ok, response.status_code, type(response.text))
-    if response.ok and response.status_code < 300 and len(response.text) > 0:
-        # DEBUG: print("DEBUG: Search for <meta name='generator'>:", domain)
+    if response.ok and response.status_code < 300 and response.text.find("<html") > 0:
+        # DEBUG: print(f"DEBUG: Parsing response.text()={len(response.text)} Bytes ...")
         doc = bs4.BeautifulSoup(response.text, "html.parser")
 
         # DEBUG: print("DEBUG: doc[]:", type(doc))
-- 
2.39.5