X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=fba%2Ffba.py;h=a34690f8c07905611913dc64833d6ec2d8b55b72;hb=434855d0ceb92dad9b00aba14247ed71afc12f6c;hp=1eddf5d5aae7af0919831df1b59a5d9ed5164635;hpb=5af800628de088e864497096d78c8bc035d67aa3;p=fba.git diff --git a/fba/fba.py b/fba/fba.py index 1eddf5d..a34690f 100644 --- a/fba/fba.py +++ b/fba/fba.py @@ -1,4 +1,3 @@ -# Fedi API Block - An aggregator for fetching blocking data from fediverse nodes # Copyright (C) 2023 Free Software Foundation # # This program is free software: you can redistribute it and/or modify @@ -14,23 +13,23 @@ # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . -import bs4 import hashlib import re -import reqto -import requests import json import sqlite3 import sys import time -import validators from urllib.parse import urlparse +import bs4 +import requests +import validators + from fba import blacklist -from fba import cache from fba import config from fba import instances +from fba import network from fba.federation import lemmy from fba.federation import misskey @@ -52,17 +51,6 @@ nodeinfo_identifier = [ "http://nodeinfo.diaspora.software/ns/schema/1.0", ] -# HTTP headers for non-API requests -headers = { - "User-Agent": config.get("useragent"), -} - -# HTTP headers for API requests -api_headers = { - "User-Agent": config.get("useragent"), - "Content-Type": "application/json", -} - # Connect to database connection = sqlite3.connect("blocks.db") cursor = connection.cursor() @@ -83,20 +71,26 @@ patterns = [ def is_primitive(var: any) -> bool: # DEBUG: print(f"DEBUG: var[]='{type(var)}' - CALLED!") - return type(var) in {int, str, float, bool} or var == None + return type(var) in {int, str, float, bool} or var is None def fetch_instances(domain: str, origin: str, software: str, script: str, path: str = None): # DEBUG: print(f"DEBUG: domain='{domain}',origin='{origin}',software='{software}',path='{path}' - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(origin) != str and origin != None: + raise ValueError("Parameter 'domain' is empty") + elif not isinstance(origin, str) and origin is not None: raise ValueError(f"Parameter origin[]={type(origin)} is not 'str'") - elif type(script) != str: + elif software is None: + # DEBUG: print(f"DEBUG: software for domain='{domain}' is not set, determining ...") + software = determine_software(domain, path) + # DEBUG: print(f"DEBUG: Determined software='{software}' for domain='{domain}'") + elif not isinstance(software, str): + raise ValueError(f"Parameter software[]={type(software)} is not 'str'") + elif not isinstance(script, str): raise ValueError(f"Parameter script[]={type(script)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'domain' is empty") if not instances.is_registered(domain): # DEBUG: print("DEBUG: Adding new domain:", domain, origin) @@ -105,7 +99,7 @@ def fetch_instances(domain: str, origin: str, software: str, script: str, path: # DEBUG: print("DEBUG: Fetching instances for domain:", domain, software) peerlist = fetch_peers(domain, software) - if (peerlist is None): + if peerlist is None: print("ERROR: Cannot fetch peers:", domain) return elif instances.has_pending_instance_data(domain): @@ -114,7 +108,7 @@ def fetch_instances(domain: str, origin: str, software: str, script: str, path: print(f"INFO: Checking {len(peerlist)} instances from {domain} ...") for instance in peerlist: - if instance == None: + if instance is None: # Skip "None" types as tidup() cannot parse them continue @@ -137,8 +131,8 @@ def fetch_instances(domain: str, origin: str, software: str, script: str, path: if not instances.is_registered(instance): # DEBUG: print("DEBUG: Adding new instance:", instance, domain) instances.add(instance, domain, script) - except BaseException as e: - print(f"ERROR: instance='{instance}',exception[{type(e)}]:'{str(e)}'") + except BaseException as exc: + print(f"ERROR: instance='{instance}',exc[{type(exc)}]:'{str(exc)}'") continue # DEBUG: print("DEBUG: EXIT!") @@ -148,7 +142,7 @@ def add_peers(rows: dict) -> list: peers = list() for key in ["linked", "allowed", "blocked"]: # DEBUG: print(f"DEBUG: Checking key='{key}'") - if key in rows and rows[key] != None: + 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!") @@ -191,7 +185,6 @@ def remove_version(software: str) -> str: # DEBUG: print(f"DEBUG: Was not able to find common seperator, returning untouched software='{software}'") return software - matches = None match = None # DEBUG: print(f"DEBUG: Checking {len(patterns)} patterns ...") for pattern in patterns: @@ -199,11 +192,12 @@ def remove_version(software: str) -> str: match = pattern.match(version) # DEBUG: print(f"DEBUG: match[]={type(match)}") - if type(match) is re.Match: + if isinstance(match, re.Match): + # DEBUG: print(f"DEBUG: version='{version}' is matching pattern='{pattern}'") break # DEBUG: print(f"DEBUG: version[{type(version)}]='{version}',match='{match}'") - if type(match) is not re.Match: + if not isinstance(match, re.Match): print(f"WARNING: version='{version}' does not match regex, leaving software='{software}' untouched.") return software @@ -221,11 +215,12 @@ def remove_version(software: str) -> str: def strip_powered_by(software: str) -> str: # DEBUG: print(f"DEBUG: software='{software}' - CALLED!") - if software == "": - print(f"ERROR: Bad method call, 'software' is empty") - raise Exception("Parameter 'software' is empty") + if not isinstance(software, str): + raise ValueError(f"Parameter software[]='{type(software)}' is not 'str'") + elif software == "": + raise ValueError("Parameter 'software' is empty") elif not "powered by" in software: - print(f"WARNING: Cannot find 'powered by' in '{software}'!") + print(f"WARNING: Cannot find 'powered by' in software='{software}'!") return software start = software.find("powered by ") @@ -241,9 +236,10 @@ def strip_powered_by(software: str) -> str: def strip_hosted_on(software: str) -> str: # DEBUG: print(f"DEBUG: software='{software}' - CALLED!") - if software == "": - print(f"ERROR: Bad method call, 'software' is empty") - raise Exception("Parameter 'software' is empty") + if not isinstance(software, str): + raise ValueError(f"Parameter software[]='{type(software)}' is not 'str'") + elif software == "": + raise ValueError("Parameter 'software' is empty") elif not "hosted on" in software: print(f"WARNING: Cannot find 'hosted on' in '{software}'!") return software @@ -251,7 +247,7 @@ def strip_hosted_on(software: str) -> str: end = software.find("hosted on ") # DEBUG: print(f"DEBUG: end[{type(end)}]='{end}'") - software = software[0, start].strip() + software = software[0, end].strip() # DEBUG: print(f"DEBUG: software='{software}'") software = strip_until(software, " - ") @@ -261,12 +257,14 @@ def strip_hosted_on(software: str) -> str: def strip_until(software: str, until: str) -> str: # DEBUG: print(f"DEBUG: software='{software}',until='{until}' - CALLED!") - if software == "": - print(f"ERROR: Bad method call, 'software' is empty") - raise Exception("Parameter 'software' is empty") + if not isinstance(software, str): + raise ValueError(f"Parameter software[]='{type(software)}' is not 'str'") + elif software == "": + raise ValueError("Parameter 'software' is empty") + elif not isinstance(until, str): + raise ValueError(f"Parameter until[]='{type(until)}' is not 'str'") elif until == "": - print(f"ERROR: Bad method call, 'until' is empty") - raise Exception("Parameter 'until' is empty") + raise ValueError("Parameter 'until' is empty") elif not until in software: print(f"WARNING: Cannot find '{until}' in '{software}'!") return software @@ -282,10 +280,10 @@ def strip_until(software: str, until: str) -> str: return software def remove_pending_error(domain: str): - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'domain' is empty") try: # Prevent updating any pending errors, nodeinfo was found @@ -297,27 +295,30 @@ def remove_pending_error(domain: str): # DEBUG: print("DEBUG: EXIT!") def get_hash(domain: str) -> str: - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'domain' is empty") return hashlib.sha256(domain.encode("utf-8")).hexdigest() def log_error(domain: str, response: requests.models.Response): # DEBUG: print("DEBUG: domain,response[]:", domain, type(response)) - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'domain' is empty") + elif config.get("write_error_log").lower() != "true": + # DEBUG: print(f"DEBUG: Writing to error_log is disabled in configuruation file - EXIT!") + return try: # DEBUG: print("DEBUG: BEFORE response[]:", type(response)) if isinstance(response, BaseException) or isinstance(response, json.decoder.JSONDecodeError): - response = str(response) + response = f"response[{type(response)}]='{str(response)}'" # DEBUG: print("DEBUG: AFTER response[]:", type(response)) - if type(response) is str: + if isinstance(response, str): cursor.execute("INSERT INTO error_log (domain, error_code, error_message, created) VALUES (?, 999, ?, ?)",[ domain, response, @@ -334,19 +335,19 @@ def log_error(domain: str, response: requests.models.Response): # Cleanup old entries # DEBUG: print(f"DEBUG: Purging old records (distance: {config.get('error_log_cleanup')})") cursor.execute("DELETE FROM error_log WHERE created < ?", [time.time() - config.get("error_log_cleanup")]) - except BaseException as e: - print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'") + except BaseException as exc: + print(f"ERROR: failed SQL query: domain='{domain}',exc[{type(exc)}]:'{str(exc)}'") sys.exit(255) # DEBUG: print("DEBUG: EXIT!") def fetch_peers(domain: str, software: str) -> list: # DEBUG: print(f"DEBUG: domain({len(domain)})={domain},software={software} - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(software) != str and software != None: + raise ValueError("Parameter 'domain' is empty") + elif not isinstance(software, str) and software is not None: raise ValueError(f"software[]={type(software)} is not 'str'") if software == "misskey": @@ -362,14 +363,15 @@ def fetch_peers(domain: str, software: str) -> list: # DEBUG: print(f"DEBUG: Fetching peers from '{domain}',software='{software}' ...") peers = list() try: - response = get_response(domain, "/api/v1/instance/peers", api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) + response = network.fetch_response(domain, "/api/v1/instance/peers", network.api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) + # DEBUG: print(f"DEBUG: response[]='{type(response)}'") data = json_from_response(response) - # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'") + if not response.ok or response.status_code >= 400: - # DEBUG: print(f"DEBUG: Was not able to fetch peers, trying alternative ...") - response = get_response(domain, "/api/v3/site", api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) + # DEBUG: print("DEBUG: Was not able to fetch peers, trying alternative ...") + response = network.fetch_response(domain, "/api/v3/site", network.api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) data = json_from_response(response) # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'") @@ -390,12 +392,12 @@ def fetch_peers(domain: str, software: str) -> list: # DEBUG: print("DEBUG: Querying API was successful:", domain, len(data)) peers = data - except BaseException as e: - print("WARNING: Some error during get():", domain, e) - instances.update_last_error(domain, e) + except BaseException as exc: + print("WARNING: Some error during fetch_peers():", domain, exc) + instances.update_last_error(domain, exc) # DEBUG: print(f"DEBUG: Adding '{len(peers)}' for domain='{domain}'") - instances.set("total_peers", domain, len(peers)) + instances.set_data("total_peers", domain, len(peers)) # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...") instances.update_last_instance_fetch(domain) @@ -403,48 +405,13 @@ def fetch_peers(domain: str, software: str) -> list: # DEBUG: print("DEBUG: Returning peers[]:", type(peers)) return peers -def post_json_api(domain: str, path: str, parameter: str, extra_headers: dict = {}) -> dict: - # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}',parameter='{parameter}',extra_headers()={len(extra_headers)} - CALLED!") - if type(domain) != str: - raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") - elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(path) != str: - raise ValueError(f"path[]={type(path)} is not 'str'") - elif path == "": - raise ValueError("Parameter 'path' cannot be empty") - elif type(parameter) != str: - raise ValueError(f"parameter[]={type(parameter)} is not 'str'") - - # DEBUG: print("DEBUG: Sending POST to domain,path,parameter:", domain, path, parameter, extra_headers) - data = {} - try: - response = reqto.post( - f"https://{domain}{path}", - data=parameter, - headers={**api_headers, **extra_headers}, - timeout=(config.get("connection_timeout"), config.get("read_timeout")) - ) - - data = json_from_response(response) - # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'") - if not response.ok or response.status_code >= 400: - print(f"WARNING: Cannot query JSON API: domain='{domain}',path='{path}',parameter()={len(parameter)},response.status_code='{response.status_code}',data[]='{type(data)}'") - instances.update_last_error(domain, response) - - except BaseException as e: - print(f"WARNING: Some error during post(): domain='{domain}',path='{path}',parameter()={len(parameter)},exception[{type(e)}]:'{str(e)}'") - - # DEBUG: print(f"DEBUG: Returning data({len(data)})=[]:{type(data)}") - return data - def fetch_nodeinfo(domain: str, path: str = None) -> list: # DEBUG: print(f"DEBUG: domain='{domain}',path={path} - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(path) != str and path != None: + raise ValueError("Parameter 'domain' is empty") + 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}' ...") @@ -466,20 +433,20 @@ def fetch_nodeinfo(domain: str, path: str = None) -> list: data = {} for request in request_paths: - if path != None and path != "" and path != f"https://{domain}{path}": + if path is not None and path != "" and path != f"https://{domain}{path}": # DEBUG: print(f"DEBUG: path='{path}' does not match request='{request}' - SKIPPED!") continue try: # DEBUG: print(f"DEBUG: Fetching request='{request}' from domain='{domain}' ...") - response = get_response(domain, request, api_headers, (config.get("nodeinfo_connection_timeout"), config.get("nodeinfo_read_timeout"))) + response = network.fetch_response(domain, request, network.api_headers, (config.get("nodeinfo_connection_timeout"), config.get("nodeinfo_read_timeout"))) data = json_from_response(response) # DEBUG: print(f"DEBUG: response.ok={response.ok},response.status_code={response.status_code},data[]='{type(data)}'") if response.ok and isinstance(data, dict): # DEBUG: print("DEBUG: Success:", request) - instances.set("detection_mode", domain, "STATIC_CHECK") - instances.set("nodeinfo_url" , domain, request) + instances.set_data("detection_mode", domain, "STATIC_CHECK") + instances.set_data("nodeinfo_url" , domain, request) break elif response.ok and isinstance(data, list): print(f"UNSUPPORTED: domain='{domain}' returned a list: '{data}'") @@ -489,9 +456,9 @@ def fetch_nodeinfo(domain: str, path: str = None) -> list: instances.update_last_error(domain, response) continue - except BaseException as e: + except BaseException as exc: # DEBUG: print("DEBUG: Cannot fetch API request:", request) - instances.update_last_error(domain, e) + instances.update_last_error(domain, exc) pass # DEBUG: print(f"DEBUG: data()={len(data)} - EXIT!") @@ -499,16 +466,16 @@ def fetch_nodeinfo(domain: str, path: str = None) -> list: def fetch_wellknown_nodeinfo(domain: str) -> list: # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'domain' is empty") # DEBUG: print("DEBUG: Fetching .well-known info for domain:", domain) data = {} try: - response = get_response(domain, "/.well-known/nodeinfo", api_headers, (config.get("nodeinfo_connection_timeout"), config.get("nodeinfo_read_timeout"))) + response = network.fetch_response(domain, "/.well-known/nodeinfo", network.api_headers, (config.get("nodeinfo_connection_timeout"), config.get("nodeinfo_read_timeout"))) data = json_from_response(response) # DEBUG: print("DEBUG: domain,response.ok,data[]:", domain, response.ok, type(data)) @@ -521,23 +488,23 @@ def fetch_wellknown_nodeinfo(domain: str) -> list: # DEBUG: print("DEBUG: rel,href:", link["rel"], link["href"]) if link["rel"] in nodeinfo_identifier: # DEBUG: print("DEBUG: Fetching nodeinfo from:", link["href"]) - response = get_url(link["href"], api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) + response = fetch_url(link["href"], network.api_headers, (config.get("connection_timeout"), config.get("read_timeout"))) data = json_from_response(response) # DEBUG: print("DEBUG: href,response.ok,response.status_code:", link["href"], response.ok, response.status_code) if response.ok and isinstance(data, dict): # DEBUG: print("DEBUG: Found JSON nodeinfo():", len(data)) - instances.set("detection_mode", domain, "AUTO_DISCOVERY") - instances.set("nodeinfo_url" , domain, link["href"]) + instances.set_data("detection_mode", domain, "AUTO_DISCOVERY") + instances.set_data("nodeinfo_url" , domain, link["href"]) break else: print("WARNING: Unknown 'rel' value:", domain, link["rel"]) else: print("WARNING: nodeinfo does not contain 'links':", domain) - except BaseException as e: + except BaseException as exc: print("WARNING: Failed fetching .well-known info:", domain) - instances.update_last_error(domain, e) + instances.update_last_error(domain, exc) pass # DEBUG: print("DEBUG: Returning data[]:", type(data)) @@ -545,21 +512,21 @@ def fetch_wellknown_nodeinfo(domain: str) -> list: def fetch_generator_from_path(domain: str, path: str = "/") -> str: # DEBUG: print(f"DEBUG: domain({len(domain)})={domain},path={path} - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(path) != str: + raise ValueError("Parameter 'domain' is empty") + elif not isinstance(path, str): raise ValueError(f"path[]={type(path)} is not 'str'") elif path == "": - raise ValueError(f"Parameter 'domain' is empty") + raise ValueError("Parameter 'path' is empty") # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' - CALLED!") software = None try: # DEBUG: print(f"DEBUG: Fetching path='{path}' from '{domain}' ...") - response = get_response(domain, path, headers, (config.get("connection_timeout"), config.get("read_timeout"))) + 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: @@ -575,39 +542,39 @@ def fetch_generator_from_path(domain: str, path: str = "/") -> str: # DEBUG: print("DEBUG: Found generator meta tag:", domain) software = tidyup_domain(generator.get("content")) print(f"INFO: domain='{domain}' is generated by '{software}'") - instances.set("detection_mode", domain, "GENERATOR") + instances.set_data("detection_mode", domain, "GENERATOR") remove_pending_error(domain) elif isinstance(site_name, bs4.element.Tag): # DEBUG: print("DEBUG: Found property=og:site_name:", domain) sofware = tidyup_domain(site_name.get("content")) print(f"INFO: domain='{domain}' has og:site_name='{software}'") - instances.set("detection_mode", domain, "SITE_NAME") + instances.set_data("detection_mode", domain, "SITE_NAME") remove_pending_error(domain) - except BaseException as e: - # DEBUG: print(f"DEBUG: Cannot fetch / from '{domain}':", e) - instances.update_last_error(domain, e) + except BaseException as exc: + # DEBUG: print(f"DEBUG: Cannot fetch / from '{domain}':", exc) + instances.update_last_error(domain, exc) pass # DEBUG: print(f"DEBUG: software[]={type(software)}") - if type(software) is str and software == "": + if isinstance(software, str) and software == "": # DEBUG: print(f"DEBUG: Corrected empty string to None for software of domain='{domain}'") software = None - elif type(software) is str and ("." in software or " " in software): + 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 ...") software = remove_version(software) # DEBUG: print(f"DEBUG: software[]={type(software)}") - if type(software) is str and " powered by " in software: + if isinstance(software, str) and " powered by " in software: # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it") software = remove_version(strip_powered_by(software)) - elif type(software) is str and " hosted on " in software: + elif isinstance(software, str) and " hosted on " in software: # DEBUG: print(f"DEBUG: software='{software}' has 'hosted on' in it") software = remove_version(strip_hosted_on(software)) - elif type(software) is str and " by " in software: + elif isinstance(software, str) and " by " in software: # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it") software = strip_until(software, " by ") - elif type(software) is str and " see " in software: + elif isinstance(software, str) and " see " in software: # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it") software = strip_until(software, " see ") @@ -616,11 +583,11 @@ def fetch_generator_from_path(domain: str, path: str = "/") -> str: def determine_software(domain: str, path: str = None) -> str: # DEBUG: print(f"DEBUG: domain({len(domain)})={domain},path={path} - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - elif type(path) != str and path != None: + raise ValueError("Parameter 'domain' is empty") + 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) @@ -664,17 +631,17 @@ def determine_software(domain: str, path: str = None) -> str: software = "misskey" elif software.find("/") > 0: print("WARNING: Spliting of slash:", software) - software = tidup_domain(software.split("/")[-1]); + software = tidyup_domain(software.split("/")[-1]) elif software.find("|") > 0: print("WARNING: Spliting of pipe:", software) - software = tidyup_domain(software.split("|")[0]); + software = tidyup_domain(software.split("|")[0]) elif "powered by" in software: # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it") software = strip_powered_by(software) - elif type(software) is str and " by " in software: + elif isinstance(software, str) and " by " in software: # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it") software = strip_until(software, " by ") - elif type(software) is str and " see " in software: + elif isinstance(software, str) and " see " in software: # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it") software = strip_until(software, " see ") @@ -692,110 +659,16 @@ def determine_software(domain: str, path: str = None) -> str: software = remove_version(software) # DEBUG: print(f"DEBUG: software[]={type(software)}") - if type(software) is str and "powered by" in software: + if isinstance(software, str) and "powered by" in software: # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it") software = remove_version(strip_powered_by(software)) # DEBUG: print("DEBUG: Returning domain,software:", domain, software) return software -def send_bot_post(instance: str, blocklist: dict): - # DEBUG: print(f"DEBUG: instance={instance},blocklist()={len(blocklist)} - CALLED!") - if type(domain) != str: - raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'") - elif domain == "": - raise ValueError("Parameter 'domain' is empty") - elif type(blocklist) != dict: - raise ValueError(f"Parameter blocklist[]='{type(blocklist)}' is not 'dict'") - - message = instance + " has blocked the following instances:\n\n" - truncated = False - - if len(blocklist) > 20: - truncated = True - blocklist = blocklist[0 : 19] - - # DEBUG: print(f"DEBUG: blocklist()={len(blocklist)}") - for block in blocklist: - # DEBUG: print(f"DEBUG: block['{type(block)}']={block}") - if block["reason"] == None or block["reason"] == '': - message = message + block["blocked"] + " with unspecified reason\n" - else: - if len(block["reason"]) > 420: - block["reason"] = block["reason"][0:419] + "[…]" - - message = message + block["blocked"] + ' for "' + block["reason"].replace("@", "@\u200b") + '"\n' - - if truncated: - message = message + "(the list has been truncated to the first 20 entries)" - - botheaders = {**api_headers, **{"Authorization": "Bearer " + config.get("bot_token")}} - - req = reqto.post( - f"{config.get('bot_instance')}/api/v1/statuses", - data={ - "status" : message, - "visibility" : config.get('bot_visibility'), - "content_type": "text/plain" - }, - headers=botheaders, - timeout=10 - ).json() - - return True - -def fetch_friendica_blocks(domain: str) -> dict: - # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!") - if type(domain) != str: - raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") - elif domain == "": - raise ValueError(f"Parameter 'domain' is empty") - - # DEBUG: print("DEBUG: Fetching friendica blocks from domain:", domain) - blocked = list() - - try: - doc = bs4.BeautifulSoup( - get_response(domain, "/friendica", headers, (config.get("connection_timeout"), config.get("read_timeout"))).text, - "html.parser", - ) - except BaseException as e: - print("WARNING: Failed to fetch /friendica from domain:", domain, e) - instances.update_last_error(domain, e) - return {} - - blocklist = doc.find(id="about_blocklist") - - # Prevents exceptions: - if blocklist is None: - # DEBUG: print("DEBUG: Instance has no block list:", domain) - return {} - - table = blocklist.find("table") - - # DEBUG: print(f"DEBUG: table[]='{type(table)}'") - if table.find("tbody"): - rows = table.find("tbody").find_all("tr") - else: - rows = table.find_all("tr") - - # DEBUG: print(f"DEBUG: Found rows()={len(rows)}") - for line in rows: - # DEBUG: print(f"DEBUG: line='{line}'") - blocked.append({ - "domain": tidyup_domain(line.find_all("td")[0].text), - "reason": tidyup_reason(line.find_all("td")[1].text) - }) - # DEBUG: print("DEBUG: Next!") - - # DEBUG: print("DEBUG: Returning blocklist() for domain:", domain, len(blocklist)) - return { - "reject": blocked - } - def tidyup_reason(reason: str) -> str: # DEBUG: print(f"DEBUG: reason='{reason}' - CALLED!") - if type(reason) != str: + if not isinstance(reason, str): raise ValueError(f"Parameter reason[]={type(reason)} is not 'str'") # Strip string @@ -809,7 +682,7 @@ def tidyup_reason(reason: str) -> str: def tidyup_domain(domain: str) -> str: # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!") - if type(domain) != str: + if not isinstance(domain, str): raise ValueError(f"Parameter domain[]={type(domain)} is not 'str'") # All lower-case and strip spaces out + last dot @@ -853,50 +726,24 @@ def json_from_response(response: requests.models.Response) -> list: # DEBUG: print(f"DEBUG: data[]={type(data)} - EXIT!") return data -def get_response(domain: str, path: str, headers: dict, timeout: list) -> requests.models.Response: - # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}',headers()={len(headers)},timeout={timeout} - CALLED!") - if type(domain) != str: - raise ValueError(f"Parameter domain[]='{type(domain)}' is not 'str'") - elif domain == "": - raise ValueError("Parameter 'domain' is empty") - elif type(path) != str: - raise ValueError(f"Parameter path[]='{type(path)}' is not 'str'") - elif path == "": - raise ValueError("Parameter 'path' is empty") - - try: - # DEBUG: print(f"DEBUG: Sending request to '{domain}{path}' ...") - response = reqto.get( - f"https://{domain}{path}", - headers=headers, - timeout=timeout - ); - except requests.exceptions.ConnectionError as e: - # DEBUG: print(f"DEBUG: Fetching '{path}' from '{domain}' failed. exception[{type(e)}]='{str(e)}'") - instances.update_last_error(domain, e) - raise e - - # DEBUG: print(f"DEBUG: response[]='{type(response)}' - EXXIT!") - return response - -def has_key(keys: list, search: str, value: any) -> bool: - # DEBUG: print(f"DEBUG: keys()={len(keys)},search='{search}',value[]='{type(value)}' - CALLED!") - if type(keys) != list: - raise ValueError(f"Parameter keys[]='{type(keys)}' is not 'list'") - elif type(search) != str: - raise ValueError(f"Parameter search[]='{type(search)}' is not 'str'") - elif search == "": - raise ValueError("Parameter 'search' is empty") +def has_key(lists: list, key: str, value: any) -> bool: + # DEBUG: print(f"DEBUG: lists()={len(lists)},key='{key}',value[]='{type(value)}' - CALLED!") + if not isinstance(lists, list): + raise ValueError(f"Parameter lists[]='{type(lists)}' is not 'list'") + elif not isinstance(key, str): + raise ValueError(f"Parameter key[]='{type(key)}' is not 'str'") + elif key == "": + raise ValueError("Parameter 'key' is empty") has = False - # DEBUG: print(f"DEBUG: Checking keys()={len(keys)} ...") - for key in keys: - # DEBUG: print(f"DEBUG: key['{type(key)}']={key}") - if type(key) != dict: - raise ValueError(f"key[]='{type(key)}' is not 'dict'") - elif not search in key: - raise KeyError(f"Cannot find search='{search}'") - elif key[search] == value: + # DEBUG: print(f"DEBUG: Checking lists()={len(lists)} ...") + for row in lists: + # DEBUG: print(f"DEBUG: row['{type(row)}']={row}") + if not isinstance(row, dict): + raise ValueError(f"row[]='{type(row)}' is not 'dict'") + elif not key in row: + raise KeyError(f"Cannot find key='{key}'") + elif row[key] == value: has = True break @@ -907,8 +754,6 @@ def find_domains(tag: bs4.element.Tag) -> list: # DEBUG: print(f"DEBUG: 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 not isinstance(tag, bs4.element.Tag): - raise KeyError("Cannot find table with instances!") elif len(tag.select("tr")) == 0: raise KeyError("No table rows found in table!") @@ -928,7 +773,7 @@ def find_domains(tag: bs4.element.Tag) -> list: print(f"WARNING: domain='{domain}' is blacklisted - skipped!") continue elif domain == "gab.com/.ai, develop.gab.com": - # DEBUG: print(f"DEBUG: Multiple domains detected in one row") + # DEBUG: print("DEBUG: Multiple domains detected in one row") domains.append({ "domain": "gab.com", "reason": reason, @@ -955,12 +800,16 @@ def find_domains(tag: bs4.element.Tag) -> list: # DEBUG: print(f"DEBUG: domains()={len(domains)} - EXIT!") return domains -def get_url(url: str, headers: dict, timeout: list) -> requests.models.Response: +def fetch_url(url: str, headers: dict, timeout: tuple) -> requests.models.Response: # DEBUG: print(f"DEBUG: url='{url}',headers()={len(headers)},timeout={timeout} - CALLED!") - if type(url) != str: + if not isinstance(url, str): raise ValueError(f"Parameter url[]='{type(url)}' is not 'str'") elif url == "": raise ValueError("Parameter 'url' is empty") + elif not isinstance(headers, dict): + raise ValueError(f"Parameter headers[]='{type(headers)}' is not 'dict'") + elif not isinstance(timeout, tuple): + raise ValueError(f"Parameter timeout[]='{type(timeout)}' is not 'tuple'") # DEBUG: print(f"DEBUG: Parsing url='{url}'") components = urlparse(url) @@ -968,9 +817,9 @@ def get_url(url: str, headers: dict, timeout: list) -> requests.models.Response: # Invoke other function, avoid trailing ? # DEBUG: print(f"DEBUG: components[{type(components)}]={components}") if components.query != "": - response = get_response(components.hostname, f"{components.path}?{components.query}", headers, timeout) + response = network.fetch_response(components.hostname, f"{components.path}?{components.query}", headers, timeout) else: - response = get_response(components.hostname, f"{components.path}", headers, timeout) + response = network.fetch_response(components.hostname, f"{components.path}", headers, timeout) # DEBUG: print(f"DEBUG: response[]='{type(response)}' - EXXIT!") return response