]> git.mxchange.org Git - fba.git/blobdiff - fba/http/federation.py
Continued:
[fba.git] / fba / http / federation.py
index 054fc3f163bf21645f825155e1fa932b2037ee1f..5f6616d0b0777baa6d561d63fece9cedada6e6c0 100644 (file)
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
+import logging
+
 from urllib.parse import urlparse
 
 import bs4
 import validators
 
 from fba import csrf
+from fba import utils
 
 from fba.helpers import blacklist
 from fba.helpers import config
@@ -33,6 +36,9 @@ from fba.networks import lemmy
 from fba.networks import misskey
 from fba.networks import peertube
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 # "rel" identifiers (no real URLs)
 nodeinfo_identifier = [
     "https://nodeinfo.diaspora.software/ns/schema/2.1",
@@ -46,11 +52,13 @@ nodeinfo_identifier = [
 ]
 
 def fetch_instances(domain: str, origin: str, software: str, command: str, path: str = None):
-    # DEBUG: print(f"DEBUG: domain='{domain}',origin='{origin}',software='{software}',path='{path}' - CALLED!")
+    logger.debug(f"domain='{domain}',origin='{origin}',software='{software}',path='{path}' - CALLED!")
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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"):
@@ -60,18 +68,18 @@ def fetch_instances(domain: str, origin: str, software: str, command: str, path:
     elif not isinstance(origin, str) and origin is not None:
         raise ValueError(f"Parameter origin[]='{type(origin)}' is not 'str'")
     elif software is None:
-        # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
+        logger.debug(f"Updating last_instance_fetch for domain='{domain}' ...")
         instances.set_last_instance_fetch(domain)
 
-        # DEBUG: print(f"DEBUG: software for domain='{domain}' is not set, determining ...")
+        logger.debug(f"software for domain='{domain}' is not set, determining ...")
         software = None
         try:
             software = determine_software(domain, path)
         except network.exceptions as exception:
-            # DEBUG: print(f"DEBUG: Exception '{type(exception)}' during determining software type")
+            logger.debug(f"Exception '{type(exception)}' during determining software type")
             pass
 
-        # DEBUG: print(f"DEBUG: Determined software='{software}' for domain='{domain}'")
+        logger.debug(f"Determined software='{software}' for domain='{domain}'")
     elif not isinstance(software, str):
         raise ValueError(f"Parameter software[]='{type(software)}' is not 'str'")
     elif not isinstance(command, str):
@@ -86,63 +94,56 @@ def fetch_instances(domain: str, origin: str, software: str, command: str, path:
         raise ValueError(f"domain='{domain}' is a fake domain")
 
     if not instances.is_registered(domain):
-        # DEBUG: print(f"DEBUG: Adding new domain='{domain}',origin='{origin}',command='{command}',path='{path}',software='{software}'")
+        logger.debug(f"Adding new domain='{domain}',origin='{origin}',command='{command}',path='{path}',software='{software}'")
         instances.add(domain, origin, command, path, software)
 
-    # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
+    logger.debug(f"Updating last_instance_fetch for domain='{domain}' ...")
     instances.set_last_instance_fetch(domain)
 
-    # DEBUG: print("DEBUG: Fetching instances for domain:", domain, software)
+    logger.debug("Fetching instances for domain:", domain, software)
     peerlist = fetch_peers(domain, software)
 
     if peerlist is None:
-        print("ERROR: Cannot fetch peers:", domain)
+        logger.warning("Cannot fetch peers:", domain)
         return
     elif instances.has_pending(domain):
-        # DEBUG: print(f"DEBUG: domain='{domain}' has pending nodeinfo data, flushing ...")
+        logger.debug(f"domain='{domain}' has pending nodeinfo data, flushing ...")
         instances.update_data(domain)
 
-    print(f"INFO: Checking {len(peerlist)} instances from domain='{domain}' ...")
+    logger.info("Checking %d instances from domain='%s' ...", len(peerlist), domain)
     for instance in peerlist:
-        # DEBUG: print(f"DEBUG: instance='{instance}'")
+        logger.debug(f"instance='{instance}'")
         if instance is None:
             # Skip "None" types as tidup.domain() cannot parse them
             continue
 
-        # DEBUG: print(f"DEBUG: instance='{instance}' - BEFORE")
+        logger.debug(f"instance='{instance}' - BEFORE")
         instance = tidyup.domain(instance)
-        # DEBUG: print(f"DEBUG: instance='{instance}' - AFTER")
+        logger.debug(f"instance='{instance}' - AFTER")
 
         if instance == "":
-            print(f"WARNING: Empty instance after tidyup.domain(), domain='{domain}'")
-            continue
-        elif not validators.domain(instance.split("/")[0]):
-            print(f"WARNING: Bad instance='{instance}' from domain='{domain}',origin='{origin}'")
+            logger.warning(f"Empty instance after tidyup.domain(), domain='{domain}'")
             continue
-        elif instance.endswith(".arpa"):
-            print(f"WARNING: instance='{instance}' is a reversed .arpa domain and should not be used generally.")
-            continue
-        elif blacklist.is_blacklisted(instance):
-            # DEBUG: print("DEBUG: instance is blacklisted:", instance)
+        elif not utils.is_domain_wanted((instance):
+            logger.debug("instance='%s' is not wanted - SKIPPED!", instance)
             continue
         elif instance.find("/profile/") > 0 or instance.find("/users/") > 0:
-            # DEBUG: print(f"DEBUG: instance='{instance}' is a link to a single user profile - SKIPPED!")
-            continue
-        elif instance.endswith(".tld"):
-            # DEBUG: print(f"DEBUG: instance='{instance}' is a fake domain - SKIPPED!")
+            logger.debug("instance='%s' is a link to a single user profile - SKIPPED!", instance)
             continue
         elif not instances.is_registered(instance):
-            # DEBUG: print("DEBUG: Adding new instance:", instance, domain)
+            logger.debug("Adding new instance:", instance, domain)
             instances.add(instance, domain, command)
 
-    # DEBUG: print("DEBUG: EXIT!")
+    logger.debug("EXIT!")
 
 def fetch_peers(domain: str, software: str) -> list:
-    # DEBUG: print(f"DEBUG: domain({len(domain)})='{domain}',software='{software}' - CALLED!")
+    logger.debug(f"domain({len(domain)})='{domain}',software='{software}' - CALLED!")
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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"):
@@ -153,13 +154,13 @@ def fetch_peers(domain: str, software: str) -> list:
         raise ValueError(f"software[]='{type(software)}' is not 'str'")
 
     if software == "misskey":
-        # DEBUG: print(f"DEBUG: Invoking misskey.fetch_peers({domain}) ...")
+        logger.debug(f"Invoking misskey.fetch_peers({domain}) ...")
         return misskey.fetch_peers(domain)
     elif software == "lemmy":
-        # DEBUG: print(f"DEBUG: Invoking lemmy.fetch_peers({domain}) ...")
+        logger.debug(f"Invoking lemmy.fetch_peers({domain}) ...")
         return lemmy.fetch_peers(domain)
     elif software == "peertube":
-        # DEBUG: print(f"DEBUG: Invoking peertube.fetch_peers({domain}) ...")
+        logger.debug(f"Invoking peertube.fetch_peers({domain}) ...")
         return peertube.fetch_peers(domain)
 
     # Init peers variable
@@ -169,14 +170,14 @@ def fetch_peers(domain: str, software: str) -> list:
     headers = tuple()
 
     try:
-        # DEBUG: print(f"DEBUG: Checking CSRF for domain='{domain}'")
+        logger.debug("Checking CSRF for domain='%s'", domain)
         headers = csrf.determine(domain, dict())
     except network.exceptions as exception:
-        print(f"WARNING: Exception '{type(exception)}' during checking CSRF (fetch_peers,{__name__}) - EXIT!")
+        logger.warning(f"Exception '{type(exception)}' during checking CSRF (fetch_peers,{__name__}) - EXIT!")
         instances.set_last_error(domain, exception)
         return peers
 
-    # DEBUG: print(f"DEBUG: Fetching peers from '{domain}',software='{software}' ...")
+    logger.debug(f"Fetching peers from '{domain}',software='{software}' ...")
     data = network.get_json_api(
         domain,
         "/api/v1/instance/peers",
@@ -184,9 +185,9 @@ def fetch_peers(domain: str, software: str) -> list:
         (config.get("connection_timeout"), config.get("read_timeout"))
     )
 
-    # DEBUG: print(f"DEBUG: data[]='{type(data)}'")
+    logger.debug("data[]='%s'", type(data))
     if "error_message" in data:
-        # DEBUG: print("DEBUG: Was not able to fetch peers, trying alternative ...")
+        logger.debug("Was not able to fetch peers, trying alternative ...")
         data = network.get_json_api(
             domain,
             "/api/v3/site",
@@ -194,35 +195,37 @@ def fetch_peers(domain: str, software: str) -> list:
             (config.get("connection_timeout"), config.get("read_timeout"))
         )
 
-        # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'")
+        logger.debug("data[]='%s'", type(data))
         if "error_message" in data:
-            print(f"WARNING: Could not reach any JSON API at domain='{domain}',status_code='{data['status_code']}',error_message='{data['error_message']}'")
+            logger.warning(f"Could not reach any JSON API at domain='{domain}',status_code='{data['status_code']}',error_message='{data['error_message']}'")
         elif "federated_instances" in data["json"]:
-            # DEBUG: print(f"DEBUG: Found federated_instances for domain='{domain}'")
+            logger.debug(f"Found federated_instances for domain='{domain}'")
             peers = peers + add_peers(data["json"]["federated_instances"])
-            # DEBUG: print("DEBUG: Added instance(s) to peers")
+            logger.debug("Added instance(s) to peers")
         else:
             message = "JSON response does not contain 'federated_instances' or 'error_message'"
-            print(f"WARNING: {message},domain='{domain}'")
+            logger.warning("message='%s',domain='%s'", message, domain)
             instances.set_last_error(domain, message)
     elif isinstance(data["json"], list):
-        # DEBUG print("DEBUG: Querying API was successful:", domain, len(data['json']))
+        logger.debug("Querying API was successful: domain='%s',data[json]()=%d", domain, len(data['json']))
         peers = data["json"]
     else:
-        print(f"WARNING: Cannot parse data[json][]='{type(data['json'])}'")
+        logger.warning("Cannot parse data[json][]='%s'", type(data['json']))
 
-    # DEBUG: print(f"DEBUG: Adding '{len(peers)}' for domain='{domain}'")
+    logger.debug(f"Adding '{len(peers)}' for domain='{domain}'")
     instances.set_total_peers(domain, peers)
 
-    # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
+    logger.debug("Returning peers[]:", type(peers))
     return peers
 
 def fetch_nodeinfo(domain: str, path: str = None) -> dict:
-    # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' - CALLED!")
+    logger.debug(f"domain='{domain}',path='{path}' - CALLED!")
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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"):
@@ -232,12 +235,12 @@ def fetch_nodeinfo(domain: str, path: str = None) -> dict:
     elif not isinstance(path, str) and path is not None:
         raise ValueError(f"Parameter path[]='{type(path)}' is not 'str'")
 
-    # DEBUG: print(f"DEBUG: Fetching nodeinfo from domain='{domain}' ...")
+    logger.debug(f"Fetching nodeinfo from domain='{domain}' ...")
     nodeinfo = fetch_wellknown_nodeinfo(domain)
 
-    # DEBUG: print(f"DEBUG: nodeinfo[{type(nodeinfo)}]({len(nodeinfo)}='{nodeinfo}'")
+    logger.debug(f"nodeinfo[{type(nodeinfo)}]({len(nodeinfo)}='{nodeinfo}'")
     if "error_message" not in nodeinfo and "json" in nodeinfo and len(nodeinfo["json"]) > 0:
-        # DEBUG: print(f"DEBUG: Found nodeinfo[json]()={len(nodeinfo['json'])} - EXIT!")
+        logger.debug(f"Found nodeinfo[json]()={len(nodeinfo['json'])} - EXIT!")
         return nodeinfo["json"]
 
     # No CSRF by default, you don't have to add network.api_headers by yourself here
@@ -245,10 +248,10 @@ def fetch_nodeinfo(domain: str, path: str = None) -> dict:
     data = dict()
 
     try:
-        # DEBUG: print(f"DEBUG: Checking CSRF for domain='{domain}'")
+        logger.debug("Checking CSRF for domain='%s'", domain)
         headers = csrf.determine(domain, dict())
     except network.exceptions as exception:
-        print(f"WARNING: Exception '{type(exception)}' during checking CSRF (nodeinfo,{__name__}) - EXIT!")
+        logger.warning(f"Exception '{type(exception)}' during checking CSRF (nodeinfo,{__name__}) - EXIT!")
         instances.set_last_error(domain, exception)
         return {
             "status_code"  : 500,
@@ -266,11 +269,11 @@ def fetch_nodeinfo(domain: str, path: str = None) -> dict:
     ]
 
     for request in request_paths:
-        # DEBUG: print(f"DEBUG: path[{type(path)}]='{path}',request='{request}'")
+        logger.debug(f"path[{type(path)}]='{path}',request='{request}'")
         if path is None or path == request or path == f"http://{domain}{path}" or path == f"https://{domain}{path}":
-            # DEBUG: print(f"DEBUG: Fetching request='{request}' from domain='{domain}' ...")
+            logger.debug(f"Fetching request='{request}' from domain='{domain}' ...")
             if path == f"http://{domain}{path}" or path == f"https://{domain}{path}":
-                # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' has protocol in path, splitting ...")
+                logger.debug(f"domain='{domain}',path='{path}' has protocol in path, splitting ...")
                 components = urlparse(path)
                 path = components.path
 
@@ -281,24 +284,26 @@ def fetch_nodeinfo(domain: str, path: str = None) -> dict:
                 (config.get("nodeinfo_connection_timeout"), config.get("nodeinfo_read_timeout"))
             )
 
-            # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'")
+            logger.debug("data[]='%s'", type(data))
             if "error_message" not in data:
-                # DEBUG: print("DEBUG: Success:", request)
+                logger.debug("Success:", request)
                 instances.set_detection_mode(domain, "STATIC_CHECK")
                 instances.set_nodeinfo_url(domain, request)
                 break
 
-            print(f"WARNING: Failed fetching nodeinfo from domain='{domain}',status_code='{data['status_code']}',error_message='{data['error_message']}'")
+            logger.warning(f"Failed fetching nodeinfo from domain='{domain}',status_code='{data['status_code']}',error_message='{data['error_message']}'")
 
-    # DEBUG: print(f"DEBUG: data()={len(data)} - EXIT!")
+    logger.debug("data()=%d - EXIT!", len(data))
     return data
 
 def fetch_wellknown_nodeinfo(domain: str) -> dict:
-    # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!")
+    logger.debug("domain(%d)='%s' - CALLED!", len(domain), domain)
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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"):
@@ -310,10 +315,10 @@ def fetch_wellknown_nodeinfo(domain: str) -> dict:
     headers = tuple()
 
     try:
-        # DEBUG: print(f"DEBUG: Checking CSRF for domain='{domain}'")
+        logger.debug("Checking CSRF for domain='%s'", domain)
         headers = csrf.determine(domain, dict())
     except network.exceptions as exception:
-        print(f"WARNING: Exception '{type(exception)}' during checking CSRF (fetch_wellknown_nodeinfo,{__name__}) - EXIT!")
+        logger.warning(f"Exception '{type(exception)}' during checking CSRF (fetch_wellknown_nodeinfo,{__name__}) - EXIT!")
         instances.set_last_error(domain, exception)
         return {
             "status_code"  : 500,
@@ -321,7 +326,7 @@ def fetch_wellknown_nodeinfo(domain: str) -> dict:
             "exception"    : exception,
         }
 
-    # DEBUG: print("DEBUG: Fetching .well-known info for domain:", domain)
+    logger.debug("Fetching .well-known info for domain:", domain)
     data = network.get_json_api(
         domain,
         "/.well-known/nodeinfo",
@@ -331,59 +336,58 @@ def fetch_wellknown_nodeinfo(domain: str) -> dict:
 
     if "error_message" not in data:
         nodeinfo = data["json"]
-        # DEBUG: print("DEBUG: Found entries:", len(nodeinfo), domain)
+        logger.debug("Found entries:", len(nodeinfo), domain)
         if "links" in nodeinfo:
-            # DEBUG: print("DEBUG: Found links in nodeinfo():", len(nodeinfo["links"]))
+            logger.debug("Found links in nodeinfo():", len(nodeinfo["links"]))
             for link in nodeinfo["links"]:
-                # DEBUG: print(f"DEBUG: link[{type(link)}]='{link}'")
+                logger.debug(f"link[{type(link)}]='{link}'")
                 if not isinstance(link, dict) or not "rel" in link:
-                    print(f"WARNING: link[]='{type(link)}' is not 'dict' or no element 'rel' found")
+                    logger.warning(f"link[]='{type(link)}' is not 'dict' or no element 'rel' found")
                 elif link["rel"] in nodeinfo_identifier:
                     # Default is that 'href' has a complete URL, but some hosts don't send that
                     url = link["href"]
                     components = urlparse(link["href"])
 
-                    # DEBUG: print(f"DEBUG: components[{type(components)}]='{components}'")
+                    logger.debug(f"components[{type(components)}]='{components}'")
                     if components.scheme == "" and components.netloc == "":
-                        # DEBUG: print(f"DEBUG: link[href]='{link['href']}' has no scheme and host name in it, prepending from domain='{domain}'")
+                        logger.debug(f"link[href]='{link['href']}' has no scheme and host name in it, prepending from domain='{domain}'")
                         url = f"https://{domain}{url}"
                         components = urlparse(url)
 
-                    if blacklist.is_blacklisted(components.netloc):
-                        print(f"WARNING: components.netloc='{components.netloc}' is blacklisted - SKIPPED!")
-                        continue
-                    elif not validators.domain(components.netloc):
-                        print(f"WARNING: components.netloc='{components.netloc}' is not a valid domain - SKIPPED!")
+                    if not utils.is_domain_wanted((components.netloc):
+                        logger.debug("components.netloc='%s' is not wanted - SKIPPED!", components.netloc)
                         continue
 
-                    # DEBUG: print("DEBUG: Fetching nodeinfo from:", url)
+                    logger.debug("Fetching nodeinfo from:", url)
                     data = network.fetch_api_url(
                         url,
                         (config.get("connection_timeout"), config.get("read_timeout"))
                      )
 
-                    # DEBUG: print("DEBUG: href,data[]:", link["href"], type(data))
+                    logger.debug("href,data[]:", link["href"], type(data))
                     if "error_message" not in data and "json" in data:
-                        # DEBUG: print("DEBUG: Found JSON nodeinfo():", len(data))
+                        logger.debug("Found JSON nodeinfo():", len(data))
                         instances.set_detection_mode(domain, "AUTO_DISCOVERY")
                         instances.set_nodeinfo_url(domain, link["href"])
                         break
                     else:
                         instances.set_last_error(domain, data)
                 else:
-                    print("WARNING: Unknown 'rel' value:", domain, link["rel"])
+                    logger.warning("Unknown 'rel' value:", domain, link["rel"])
         else:
-            print("WARNING: nodeinfo does not contain 'links':", domain)
+            logger.warning("nodeinfo does not contain 'links':", domain)
 
-    # DEBUG: print("DEBUG: Returning data[]:", type(data))
+    logger.debug("Returning data[]:", type(data))
     return data
 
 def fetch_generator_from_path(domain: str, path: str = "/") -> str:
-    # DEBUG: print(f"DEBUG: domain({len(domain)})='{domain}',path='{path}' - CALLED!")
+    logger.debug(f"domain({len(domain)})='{domain}',path='{path}' - CALLED!")
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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"):
@@ -395,161 +399,172 @@ def fetch_generator_from_path(domain: str, path: str = "/") -> str:
     elif path == "":
         raise ValueError("Parameter 'path' is empty")
 
-    # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' - CALLED!")
+    logger.debug(f"domain='{domain}',path='{path}' - CALLED!")
     software = None
 
-    # DEBUG: print(f"DEBUG: Fetching path='{path}' from '{domain}' ...")
+    logger.debug(f"Fetching path='{path}' from '{domain}' ...")
     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))
+    logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text))
     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 ...")
+        logger.debug(f"Parsing response.text()={len(response.text)} Bytes ...")
+
         doc = bs4.BeautifulSoup(response.text, "html.parser")
+        logger.debug("doc[]='%s'", type(doc))
 
-        # DEBUG: print("DEBUG: doc[]:", type(doc))
         generator = doc.find("meta", {"name"    : "generator"})
         site_name = doc.find("meta", {"property": "og:site_name"})
 
-        # DEBUG: print(f"DEBUG: generator='{generator}',site_name='{site_name}'")
+        logger.debug("generator[]='%s',site_name[]='%s'", type(generator), type(site_name))
         if isinstance(generator, bs4.element.Tag) and isinstance(generator.get("content"), str):
-            # DEBUG: print("DEBUG: Found generator meta tag:", domain)
+            logger.debug("Found generator meta tag:", domain)
             software = tidyup.domain(generator.get("content"))
-            # DEBUG: print(f"DEBUG: software[{type(software)}]='{software}'")
+
+            logger.debug("software[%s]='%s'", type(software), software)
             if software is not None and software != "":
-                print(f"INFO: domain='{domain}' is generated by '{software}'")
+                logger.info("domain='%s' is generated by '%s'", domain, software)
                 instances.set_detection_mode(domain, "GENERATOR")
         elif isinstance(site_name, bs4.element.Tag) and isinstance(site_name.get("content"), str):
-            # DEBUG: print("DEBUG: Found property=og:site_name:", domain)
+            logger.debug("Found property=og:site_name:", domain)
             software = tidyup.domain(site_name.get("content"))
-            # DEBUG: print(f"DEBUG: software[{type(software)}]='{software}'")
+
+            logger.debug("software[%s]='%s'", type(software), software)
             if software is not None and software != "":
-                print(f"INFO: domain='{domain}' has og:site_name='{software}'")
+                logger.info("domain='%s' has og:site_name='%s'", domain, software)
                 instances.set_detection_mode(domain, "SITE_NAME")
 
-    # DEBUG: print(f"DEBUG: software[]='{type(software)}'")
+    logger.debug("software[]='%s'", type(software))
     if isinstance(software, str) and software == "":
-        # DEBUG: print(f"DEBUG: Corrected empty string to None for software of domain='{domain}'")
+        logger.debug("Corrected empty string to None for software of domain='%s'", domain)
         software = None
     elif isinstance(software, str) and ("." in software or " " in software):
-        # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
+        logger.debug(f"software='{software}' may contain a version number, domain='{domain}', removing it ...")
         software = version.remove(software)
 
-    # DEBUG: print(f"DEBUG: software[]='{type(software)}'")
+    logger.debug("software[]='%s'", type(software))
     if isinstance(software, str) and "powered by " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
+        logger.debug(f"software='{software}' has 'powered by' in it")
         software = version.remove(version.strip_powered_by(software))
     elif isinstance(software, str) and " hosted on " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has 'hosted on' in it")
+        logger.debug(f"software='{software}' has 'hosted on' in it")
         software = version.remove(version.strip_hosted_on(software))
     elif isinstance(software, str) and " by " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
+        logger.debug(f"software='{software}' has ' by ' in it")
         software = version.strip_until(software, " by ")
     elif isinstance(software, str) and " see " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
+        logger.debug(f"software='{software}' has ' see ' in it")
         software = version.strip_until(software, " see ")
 
-    # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
+    logger.debug(f"software='{software}' - EXIT!")
     return software
 
 def determine_software(domain: str, path: str = None) -> str:
-    # DEBUG: print(f"DEBUG: domain({len(domain)})='{domain}',path='{path}' - CALLED!")
+    logger.debug(f"domain({len(domain)})='{domain}',path='{path}' - CALLED!")
     if not isinstance(domain, str):
         raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'")
     elif domain == "":
         raise ValueError("Parameter 'domain' is empty")
+    elif domain.lower() != domain:
+        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(".tld"):
+        raise ValueError(f"domain='{domain}' is a fake domain, please don't crawl them!")
     elif not isinstance(path, str) and path is not None:
         raise ValueError(f"Parameter path[]='{type(path)}' is not 'str'")
 
-    # DEBUG: print("DEBUG: Determining software for domain,path:", domain, path)
+    logger.debug("Determining software for domain,path:", domain, path)
     software = None
 
-    # DEBUG: print(f"DEBUG: Fetching nodeinfo from '{domain}' ...")
+    logger.debug(f"Fetching nodeinfo from '{domain}' ...")
     data = fetch_nodeinfo(domain, path)
 
-    # DEBUG: print(f"DEBUG: data[{type(data)}]='{data}'")
+    logger.debug(f"data[{type(data)}]='{data}'")
     if "exception" in data:
         # Continue raising it
         raise data["exception"]
     elif "error_message" in data:
-        # DEBUG: print(f"DEBUG: Returned error_message during fetching nodeinfo: '{data['error_message']}',status_code='{data['status_code']}'")
+        logger.debug(f"Returned error_message during fetching nodeinfo: '{data['error_message']}',status_code='{data['status_code']}'")
         return fetch_generator_from_path(domain)
     elif "status" in data and data["status"] == "error" and "message" in data:
-        print("WARNING: JSON response is an error:", data["message"])
+        logger.warning("JSON response is an error:", data["message"])
         instances.set_last_error(domain, data["message"])
         return fetch_generator_from_path(domain)
     elif "message" in data:
-        print("WARNING: JSON response contains only a message:", data["message"])
+        logger.warning("JSON response contains only a message:", data["message"])
         instances.set_last_error(domain, data["message"])
         return fetch_generator_from_path(domain)
     elif "software" not in data or "name" not in data["software"]:
-        # DEBUG: print(f"DEBUG: JSON response from domain='{domain}' does not include [software][name], fetching / ...")
+        logger.debug(f"JSON response from domain='{domain}' does not include [software][name], fetching / ...")
         software = fetch_generator_from_path(domain)
-        # DEBUG: print(f"DEBUG: Generator for domain='{domain}' is: '{software}'")
+        logger.debug(f"Generator for domain='{domain}' is: '{software}'")
     elif "software" in data and "name" in data["software"]:
-        # DEBUG: print("DEBUG: Found data[software][name] in JSON response")
+        logger.debug("Found data[software][name] in JSON response")
         software = data["software"]["name"]
 
     if software is None:
-        # DEBUG: print("DEBUG: Returning None - EXIT!")
+        logger.debug("Returning None - EXIT!")
         return None
 
     sofware = tidyup.domain(software)
-    # DEBUG: print("DEBUG: sofware after tidyup.domain():", software)
+    logger.debug("sofware after tidyup.domain():", software)
 
     if software in ["akkoma", "rebased", "akkounfucked", "ched"]:
-        # DEBUG: print("DEBUG: Setting pleroma:", domain, software)
+        logger.debug("Setting pleroma:", domain, software)
         software = "pleroma"
     elif software in ["hometown", "ecko"]:
-        # DEBUG: print("DEBUG: Setting mastodon:", domain, software)
+        logger.debug("Setting mastodon:", domain, software)
         software = "mastodon"
     elif software in ["slipfox calckey", "calckey", "groundpolis", "foundkey", "cherrypick", "meisskey", "magnetar", "keybump"]:
-        # DEBUG: print("DEBUG: Setting misskey:", domain, software)
+        logger.debug("Setting misskey:", domain, software)
         software = "misskey"
     elif software == "runtube.re":
-        # DEBUG: print("DEBUG: Setting peertube:", domain, software)
+        logger.debug("Setting peertube:", domain, software)
         software = "peertube"
     elif software == "nextcloud social":
-        # DEBUG: print("DEBUG: Setting nextcloud:", domain, software)
+        logger.debug("Setting nextcloud:", domain, software)
         software = "nextcloud"
     elif software.find("/") > 0:
-        print("WARNING: Spliting of slash:", software)
+        logger.warning("Spliting of slash:", software)
         software = tidyup.domain(software.split("/")[-1])
     elif software.find("|") > 0:
-        print("WARNING: Spliting of pipe:", software)
+        logger.warning("Spliting of pipe:", software)
         software = tidyup.domain(software.split("|")[0])
     elif "powered by" in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
+        logger.debug(f"software='{software}' has 'powered by' in it")
         software = version.strip_powered_by(software)
     elif isinstance(software, str) and " by " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
+        logger.debug(f"software='{software}' has ' by ' in it")
         software = version.strip_until(software, " by ")
     elif isinstance(software, str) and " see " in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
+        logger.debug(f"software='{software}' has ' see ' in it")
         software = version.strip_until(software, " see ")
 
-    # DEBUG: print(f"DEBUG: software[]='{type(software)}'")
+    logger.debug("software[]='%s'", type(software))
     if software == "":
-        print("WARNING: tidyup.domain() left no software name behind:", domain)
+        logger.warning("tidyup.domain() left no software name behind:", domain)
         software = None
 
-    # DEBUG: print(f"DEBUG: software[]='{type(software)}'")
+    logger.debug("software[]='%s'", type(software))
     if str(software) == "":
-        # DEBUG: print(f"DEBUG: software for '{domain}' was not detected, trying generator ...")
+        logger.debug(f"software for '{domain}' was not detected, trying generator ...")
         software = fetch_generator_from_path(domain)
     elif len(str(software)) > 0 and ("." in software or " " in software):
-        # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
+        logger.debug(f"software='{software}' may contain a version number, domain='{domain}', removing it ...")
         software = version.remove(software)
 
-    # DEBUG: print(f"DEBUG: software[]='{type(software)}'")
+    logger.debug("software[]='%s'", type(software))
     if isinstance(software, str) and "powered by" in software:
-        # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
+        logger.debug(f"software='{software}' has 'powered by' in it")
         software = version.remove(version.strip_powered_by(software))
 
-    # DEBUG: print("DEBUG: Returning domain,software:", domain, software)
+    logger.debug("Returning domain,software:", domain, software)
     return software
 
 def find_domains(tag: bs4.element.Tag) -> list:
-    # DEBUG: print(f"DEBUG: tag[]='{type(tag)}' - CALLED!")
+    logger.debug(f"tag[]='{type(tag)}' - CALLED!")
     if not isinstance(tag, bs4.element.Tag):
         raise ValueError(f"Parameter tag[]='{type(tag)}' is not type of bs4.element.Tag")
     elif len(tag.select("tr")) == 0:
@@ -557,21 +572,21 @@ def find_domains(tag: bs4.element.Tag) -> list:
 
     domains = list()
     for element in tag.select("tr"):
-        # DEBUG: print(f"DEBUG: element[]='{type(element)}'")
+        logger.debug(f"element[]='{type(element)}'")
         if not element.find("td"):
-            # DEBUG: print("DEBUG: Skipping element, no <td> found")
+            logger.debug("Skipping element, no <td> found")
             continue
 
         domain = tidyup.domain(element.find("td").text)
         reason = tidyup.reason(element.findAll("td")[1].text)
 
-        # DEBUG: print(f"DEBUG: domain='{domain}',reason='{reason}'")
+        logger.debug("domain='%s',reason='%s'", domain, reason)
 
-        if blacklist.is_blacklisted(domain):
-            print(f"WARNING: domain='{domain}' is blacklisted - SKIPPED!")
+        if not utils.is_domain_wanted((domain):
+            logger.debug("domain='%s' is blacklisted - SKIPPED!", domain)
             continue
         elif domain == "gab.com/.ai, develop.gab.com":
-            # DEBUG: print("DEBUG: Multiple domains detected in one row")
+            logger.debug("Multiple domains detected in one row")
             domains.append({
                 "domain": "gab.com",
                 "reason": reason,
@@ -586,36 +601,49 @@ def find_domains(tag: bs4.element.Tag) -> list:
             })
             continue
         elif not validators.domain(domain.split("/")[0]):
-            print(f"WARNING: domain='{domain}' is not a valid domain - SKIPPED!")
+            logger.warning("domain='%s' is not a valid domain - SKIPPED!", domain)
             continue
 
-        # DEBUG: print(f"DEBUG: Adding domain='{domain}',reason='{reason}' ...")
+        logger.debug(f"Adding domain='{domain}',reason='{reason}' ...")
         domains.append({
             "domain": domain,
             "reason": reason,
         })
 
-    # DEBUG: print(f"DEBUG: domains()={len(domains)} - EXIT!")
+    logger.debug(f"domains()={len(domains)} - EXIT!")
     return domains
 
 def add_peers(rows: dict) -> list:
-    # DEBUG: print(f"DEBUG: rows()={len(rows)} - CALLED!")
+    logger.debug(f"rows[]={type(rows)} - CALLED!")
+    if not isinstance(rows, dict):
+        raise ValueError(f"Parameter rows[]='{type(rows)}' is not 'dict'")
+
     peers = list()
     for key in ["linked", "allowed", "blocked"]:
-        # DEBUG: print(f"DEBUG: Checking key='{key}'")
-        if key in rows and rows[key] is not None:
-            # DEBUG: print(f"DEBUG: Adding {len(rows[key])} peer(s) to peers list ...")
-            for peer in rows[key]:
-                # DEBUG: print(f"DEBUG: peer='{peer}' - BEFORE!")
+        logger.debug(f"Checking key='{key}'")
+        if key not in rows or rows[key] is None:
+            logger.debug(f"Cannot find key='{key}' or it is NoneType - SKIPPED!")
+            continue
+
+        logger.debug(f"Adding {len(rows[key])} peer(s) to peers list ...")
+        for peer in rows[key]:
+            logger.debug(f"peer='{peer}' - BEFORE!")
+            if isinstance(peer, dict) and "domain" in peer:
+                logger.debug(f"peer[domain]='{peer['domain']}'")
+                peer = tidyup.domain(peer["domain"])
+            elif isinstance(peer, str):
+                logger.debug(f"peer='{peer}'")
                 peer = tidyup.domain(peer)
+            else:
+                raise ValueError(f"peer[]='{type(peer)}' is not supported,key='{key}'")
 
-                # DEBUG: print(f"DEBUG: peer='{peer}' - AFTER!")
-                if blacklist.is_blacklisted(peer):
-                    # DEBUG: print(f"DEBUG: peer='{peer}' is blacklisted, skipped!")
-                    continue
+            logger.debug(f"peer='{peer}' - AFTER!")
+            if not utils.is_domain_wanted((peer):
+                logger.debug("peer='%s' is not wanted - SKIPPED!", peer)
+                continue
 
-                # DEBUG: print(f"DEBUG: Adding peer='{peer}' ...")
-                peers.append(peer)
+            logger.debug(f"Adding peer='{peer}' ...")
+            peers.append(peer)
 
-    # DEBUG: print(f"DEBUG: peers()={len(peers)} - EXIT!")
+    logger.debug(f"peers()={len(peers)} - EXIT!")
     return peers