Continued:

- also check for '<html', if not found then skip this broken HTML

diff --git a/fba/csrf.py b/fba/csrf.py
index 4eedcc77ce393db0c676306d8ce1293682dd1db0..859d5cbe338503b27ce93c07d34f86272bf3befc 100644 (file)
--- 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 ec716172a13e67b5e8e2dab37eaae1d868794664..1d154509fd2d58583a041c730118bd7e8f12a599 100644 (file)
--- 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))