Continued:

[fba.git] / fba / helpers / domain.py

diff --git a/fba/helpers/domain.py b/fba/helpers/domain.py
index 9f8c578b6314709683a163ce96f0b2c7d4ecb5fe..39fbb7797acee74c7c5207ed0b3b60c507276b2f 100644 (file)
--- a/fba/helpers/domain.py
+++ b/fba/helpers/domain.py
@@ -16,11 +16,13 @@
 
 import logging
 
+from functools import lru_cache
 from urllib.parse import urlparse
 
 import validators
 
 from fba.helpers import blacklist
+from fba.helpers import config
 
 from fba.models import instances
 
@@ -29,6 +31,7 @@ logger = logging.getLogger(__name__)
 
 def raise_on(domain: str):
     logger.debug("domain='%s' - CALLED!", domain)
+
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
     elif domain == "":
@@ -37,23 +40,30 @@ def raise_on(domain: str):
         raise ValueError(f"Parameter domain='{domain}' must be all lower-case")
     elif not validators.domain(domain.split("/")[0]):
         raise ValueError(f"domain='{domain}' is not a valid domain")
-    elif domain.endswith(".arpa"):
-        raise ValueError(f"domain='{domain}' is a domain for reversed IP addresses, please don't crawl them!")
     elif domain.endswith(".onion"):
         raise ValueError(f"domain='{domain}' is a TOR, please don't crawl them!")
+    elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
+        raise ValueError(f"domain='{domain}' is an I2P, please don't crawl them!")
+    elif domain.endswith(".arpa"):
+        raise ValueError(f"domain='{domain}' is a domain for reversed IP addresses, please don't crawl them!")
     elif domain.endswith(".tld"):
         raise ValueError(f"domain='{domain}' is a fake domain, please don't crawl them!")
 
     logger.debug("EXIT!")
 
+@lru_cache
 def is_in_url(domain: str, url: str) -> bool:
     logger.debug("domain='%s',url='%s' - CALLED!", domain, url)
     raise_on(domain)
 
-    if not isinstance(url, str):
+    if blacklist.is_blacklisted(domain):
+        raise ValueError(f"domain='{domain}' is blacklisted but function was invoked")
+    elif not isinstance(url, str):
         raise ValueError(f"Parameter url[]='{type(url)}' is not of type 'str'")
     elif url == "":
         raise ValueError("Parameter 'url' is empty")
+    elif not validators.url(url):
+        raise ValueError(f"Parameter url='{url}' is not a valid URL")
 
     punycode = domain.encode("idna").decode("utf-8")
 
@@ -65,8 +75,10 @@ def is_in_url(domain: str, url: str) -> bool:
     logger.debug("is_found='%s' - EXIT!", is_found)
     return is_found
 
+@lru_cache
 def is_wanted(domain: str) -> bool:
     logger.debug("domain='%s' - CALLED!", domain)
+
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
     elif domain == "":
@@ -74,6 +86,7 @@ def is_wanted(domain: str) -> bool:
 
     wanted = True
     if domain.lower() != domain:
+        logger.debug("domain='%s' is not all-lowercase - setting False ...", domain)
         wanted = False
     elif not validators.domain(domain.split("/")[0]):
         logger.debug("domain='%s' is not a valid domain name - setting False ...", domain)
@@ -84,6 +97,9 @@ def is_wanted(domain: str) -> bool:
     elif domain.endswith(".onion"):
         logger.debug("domain='%s' is a TOR .onion domain - setting False ...", domain)
         wanted = False
+    elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
+        logger.debug("domain='%s' is an I2P domain - setting False ...", domain)
+        wanted = False
     elif domain.endswith(".tld"):
         logger.debug("domain='%s' is a fake domain - setting False ...", domain)
         wanted = False