1 # Fedi API Block - An aggregator for fetching blocking data from fediverse nodes
2 # Copyright (C) 2023 Free Software Foundation
4 # This program is free software: you can redistribute it and/or modify
5 # it under the terms of the GNU Affero General Public License as published
6 # by the Free Software Foundation, either version 3 of the License, or
7 # (at your option) any later version.
9 # This program is distributed in the hope that it will be useful,
10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 # GNU Affero General Public License for more details.
14 # You should have received a copy of the GNU Affero General Public License
15 # along with this program. If not, see <https://www.gnu.org/licenses/>.
27 with open("config.json") as f:
28 config = json.loads(f.read())
30 # Don't check these, known trolls/flooders/testing/developing
32 # Floods network with fake nodes as "research" project
33 "activitypub-troll.cf",
39 "social.shrimpcam.pw",
41 "mastotroll.netz.org",
42 # Testing/developing installations
45 "misskeytest.chn.moe",
48 # Array with pending errors needed to be written to database
52 # "rel" identifiers (no real URLs)
53 nodeinfo_identifier = [
54 "https://nodeinfo.diaspora.software/ns/schema/2.1",
55 "https://nodeinfo.diaspora.software/ns/schema/2.0",
56 "https://nodeinfo.diaspora.software/ns/schema/1.1",
57 "https://nodeinfo.diaspora.software/ns/schema/1.0",
58 "http://nodeinfo.diaspora.software/ns/schema/2.1",
59 "http://nodeinfo.diaspora.software/ns/schema/2.0",
60 "http://nodeinfo.diaspora.software/ns/schema/1.1",
61 "http://nodeinfo.diaspora.software/ns/schema/1.0",
64 # HTTP headers for non-API requests
66 "User-Agent": config["useragent"],
68 # HTTP headers for API requests
70 "User-Agent": config["useragent"],
71 "Content-Type": "application/json",
74 # Found info from node, such as nodeinfo URL, detection mode that needs to be
75 # written to database. Both arrays must be filled at the same time or else
76 # update_nodeinfos() will fail
78 # Detection mode: 'AUTO_DISCOVERY', 'STATIC_CHECKS' or 'GENERATOR'
79 # NULL means all detection methods have failed (maybe still reachable instance)
87 "Silenced instances" : "Silenced servers",
88 "Suspended instances" : "Suspended servers",
89 "Limited instances" : "Limited servers",
90 # Mappuing German -> English
91 "Gesperrte Server" : "Suspended servers",
92 "Gefilterte Medien" : "Filtered media",
93 "Stummgeschaltete Server" : "Silenced servers",
95 "停止済みのサーバー" : "Suspended servers",
96 "制限中のサーバー" : "Limited servers",
97 "メディアを拒否しているサーバー": "Filtered media",
98 "サイレンス済みのサーバー" : "Silenced servers",
100 "שרתים מושעים" : "Suspended servers",
101 "מדיה מסוננת" : "Filtered media",
102 "שרתים מוגבלים" : "Silenced servers",
104 "Serveurs suspendus" : "Suspended servers",
105 "Médias filtrés" : "Filtered media",
106 "Serveurs limités" : "Limited servers",
107 "Serveurs modérés" : "Limited servers",
110 # URL for fetching peers
111 get_peers_url = "/api/v1/instance/peers"
113 # Cache for redundant SQL queries
116 # Connect to database
117 connection = sqlite3.connect("blocks.db")
118 cursor = connection.cursor()
120 # Pattern instance for version numbers
122 # semantic version number (with v|V) prefix)
123 re.compile("^(?P<version>v|V{0,1})(\.{0,1})(?P<major>0|[1-9]\d*)\.(?P<minor>0+|[1-9]\d*)(\.(?P<patch>0+|[1-9]\d*)(?:-(?P<prerelease>(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+(?P<buildmetadata>[0-9a-zA-Z-]+(?:\.[0-9a-zA-Z-]+)*))?)?$"),
124 # non-sematic, e.g. 1.2.3.4
125 re.compile("^(?P<version>v|V{0,1})(\.{0,1})(?P<major>0|[1-9]\d*)\.(?P<minor>0+|[1-9]\d*)(\.(?P<patch>0+|[1-9]\d*)(\.(?P<subpatch>0|[1-9]\d*))?)$"),
126 # non-sematic, e.g. 2023-05[-dev]
127 re.compile("^(?P<year>[1-9]{1}[0-9]{3})\.(?P<month>[0-9]{2})(-dev){0,1}$"),
128 # non-semantic, e.g. abcdef0
129 re.compile("^[a-f0-9]{7}$"),
134 def is_cache_initialized(key: str) -> bool:
137 def set_all_cache_key(key: str, rows: list, value: any):
138 # DEBUG: print(f"DEBUG: key='{key}',rows()={len(rows)},value[]={type(value)} - CALLED!")
139 if not is_cache_initialized(key):
140 # DEBUG: print(f"DEBUG: Cache for key='{key}' not initialized.")
144 # DEBUG: print(f"DEBUG: Setting key='{key}',sub[{type(sub)}]='{sub}'")
146 if isinstance(sub, tuple):
147 cache[key][sub[0]] = value
149 print(f"WARNING: Unsupported type row[]='{type(row)}'")
151 # DEBUG: print("DEBUG: EXIT!")
153 def set_cache_key(key: str, sub: str, value: any):
154 if not is_cache_initialized(key):
155 print(f"WARNING: Bad method call, key='{key}' is not initialized yet.")
156 raise Exception(f"Cache for key='{key}' is not initialized, but function called")
158 cache[key][sub] = value
160 def is_cache_key_set(key: str, sub: str) -> bool:
161 if not is_cache_initialized(key):
162 print(f"WARNING: Bad method call, key='{key}' is not initialized yet.")
163 raise Exception(f"Cache for key='{key}' is not initialized, but function called")
165 return sub in cache[key]
167 def add_peers(rows: dict) -> list:
168 # DEBUG: print(f"DEBUG: rows()={len(rows)} - CALLED!")
170 for element in ["linked", "allowed", "blocked"]:
171 # DEBUG: print(f"DEBUG: Checking element='{element}'")
172 if element in rows and rows[element] != None:
173 # DEBUG: print(f"DEBUG: Adding {len(rows[element])} peer(s) to peers list ...")
174 for peer in rows[element]:
175 # DEBUG: print(f"DEBUG: peer='{peer}' - BEFORE!")
178 # DEBUG: print(f"DEBUG: peer='{peer}' - AFTER!")
179 if is_blacklisted(peer):
180 # DEBUG: print(f"DEBUG: peer='{peer}' is blacklisted, skipped!")
183 # DEBUG: print(f"DEBUG: Adding peer='{peer}' ...")
186 # DEBUG: print(f"DEBUG: peers()={len(peers)} - EXIT!")
189 def remove_version(software: str) -> str:
190 # DEBUG: print(f"DEBUG: software='{software}' - CALLED!")
191 if not "." in software and " " not in software:
192 print(f"WARNING: software='{software}' does not contain a version number.")
197 temp = software.split(";")[0]
198 elif "," in software:
199 temp = software.split(",")[0]
200 elif " - " in software:
201 temp = software.split(" - ")[0]
203 # DEBUG: print(f"DEBUG: software='{software}'")
206 version = temp.split(" ")[-1]
207 elif "/" in software:
208 version = temp.split("/")[-1]
209 elif "-" in software:
210 version = temp.split("-")[-1]
212 # DEBUG: print(f"DEBUG: Was not able to find common seperator, returning untouched software='{software}'")
217 # DEBUG: print(f"DEBUG: Checking {len(patterns)} patterns ...")
218 for pattern in patterns:
220 match = pattern.match(version)
222 # DEBUG: print(f"DEBUG: match[]={type(match)}")
223 if type(match) is re.Match:
226 # DEBUG: print(f"DEBUG: version[{type(version)}]='{version}',match='{match}'")
227 if type(match) is not re.Match:
228 print(f"WARNING: version='{version}' does not match regex, leaving software='{software}' untouched.")
231 # DEBUG: print(f"DEBUG: Found valid version number: '{version}', removing it ...")
232 end = len(temp) - len(version) - 1
234 # DEBUG: print(f"DEBUG: end[{type(end)}]={end}")
235 software = temp[0:end].strip()
236 if " version" in software:
237 # DEBUG: print(f"DEBUG: software='{software}' contains word ' version'")
238 software = strip_until(software, " version")
240 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
243 def strip_powered_by(software: str) -> str:
244 # DEBUG: print(f"DEBUG: software='{software}' - CALLED!")
246 print(f"ERROR: Bad method call, 'software' is empty")
247 raise Exception("Parameter 'software' is empty")
248 elif not "powered by" in software:
249 print(f"WARNING: Cannot find 'powered by' in '{software}'!")
252 start = software.find("powered by ")
253 # DEBUG: print(f"DEBUG: start[{type(start)}]='{start}'")
255 software = software[start + 11:].strip()
256 # DEBUG: print(f"DEBUG: software='{software}'")
258 software = strip_until(software, " - ")
260 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
263 def strip_until(software: str, until: str) -> str:
264 # DEBUG: print(f"DEBUG: software='{software}',until='{until}' - CALLED!")
266 print(f"ERROR: Bad method call, 'software' is empty")
267 raise Exception("Parameter 'software' is empty")
269 print(f"ERROR: Bad method call, 'until' is empty")
270 raise Exception("Parameter 'until' is empty")
271 elif not until in software:
272 print(f"WARNING: Cannot find 'powered by' in '{software}'!")
275 # Next, strip until part
276 end = software.find(until)
278 # DEBUG: print(f"DEBUG: end[{type(end)}]='{end}'")
280 software = software[0:end].strip()
282 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
285 def is_blacklisted(domain: str) -> bool:
287 for peer in blacklist:
293 def remove_pending_error(domain: str):
295 # Prevent updating any pending errors, nodeinfo was found
296 del pending_errors[domain]
301 def get_hash(domain: str) -> str:
302 return hashlib.sha256(domain.encode("utf-8")).hexdigest()
304 def update_last_blocked(domain: str):
305 # DEBUG: print("DEBUG: Updating last_blocked for domain", domain)
307 cursor.execute("UPDATE instances SET last_blocked = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
313 if cursor.rowcount == 0:
314 print("WARNING: Did not update any rows:", domain)
316 except BaseException as e:
317 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
320 # DEBUG: print("DEBUG: EXIT!")
322 def has_pending_nodeinfos(domain: str) -> bool:
323 # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!")
325 for key in nodeinfos:
326 # DEBUG: print(f"DEBUG: key='{key}',domain='{domain}',nodeinfos[key]='{nodeinfos[key]}'")
327 if domain in nodeinfos[key]:
331 # DEBUG: print(f"DEBUG: has_pending='{has_pending}' - EXIT!")
334 def update_nodeinfos(domain: str):
335 # DEBUG: print("DEBUG: Updating nodeinfo for domain:", domain)
338 for key in nodeinfos:
339 # DEBUG: print("DEBUG: key:", key)
340 if domain in nodeinfos[key]:
341 # DEBUG: print(f"DEBUG: Adding '{nodeinfos[key][domain]}' for key='{key}' ...")
342 fields.append(nodeinfos[key][domain])
343 sql_string += f" {key} = ?,"
345 fields.append(domain)
346 # DEBUG: print(f"DEBUG: sql_string='{sql_string}',fields()={len(fields)}")
348 sql = "UPDATE instances SET" + sql_string + " last_status_code = NULL, last_error_details = NULL WHERE domain = ? LIMIT 1"
349 # DEBUG: print("DEBUG: sql:", sql)
352 # DEBUG: print("DEBUG: Executing SQL:", sql)
353 cursor.execute(sql, fields)
354 # DEBUG: print(f"DEBUG: Success! (rowcount={cursor.rowcount })")
356 if cursor.rowcount == 0:
357 print("WARNING: Did not update any rows:", domain)
359 except BaseException as e:
360 print(f"ERROR: failed SQL query: domain='{domain}',sql='{sql}',exception[{type(e)}]:'{str(e)}'")
363 # DEBUG: print("DEBUG: Deleting nodeinfos for domain:", domain)
364 for key in nodeinfos:
366 # DEBUG: print("DEBUG: Deleting key:", key)
367 del nodeinfos[key][domain]
371 # DEBUG: print("DEBUG: EXIT!")
373 def log_error(domain: str, res: any):
374 # DEBUG: print("DEBUG: domain,res[]:", domain, type(res))
376 # DEBUG: print("DEBUG: BEFORE res[]:", type(res))
377 if isinstance(res, BaseException) or isinstance(res, json.JSONDecodeError):
380 # DEBUG: print("DEBUG: AFTER res[]:", type(res))
382 cursor.execute("INSERT INTO error_log (domain, error_code, error_message, created) VALUES (?, 999, ?, ?)",[
388 cursor.execute("INSERT INTO error_log (domain, error_code, error_message, created) VALUES (?, ?, ?, ?)",[
395 # Cleanup old entries
396 # DEBUG: print(f"DEBUG: Purging old records (distance: {config['error_log_cleanup'])")
397 cursor.execute("DELETE FROM error_log WHERE created < ?", [time.time() - config["error_log_cleanup"]])
398 except BaseException as e:
399 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
402 # DEBUG: print("DEBUG: EXIT!")
404 def update_last_error(domain: str, res: any):
405 # DEBUG: print("DEBUG: domain,res[]:", domain, type(res))
407 # DEBUG: print("DEBUG: BEFORE res[]:", type(res))
408 if isinstance(res, BaseException) or isinstance(res, json.JSONDecodeError):
411 # DEBUG: print("DEBUG: AFTER res[]:", type(res))
413 # DEBUG: print(f"DEBUG: Setting last_error_details='{res}'");
414 cursor.execute("UPDATE instances SET last_status_code = 999, last_error_details = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
420 # DEBUG: print(f"DEBUG: Setting last_error_details='{res.reason}'");
421 cursor.execute("UPDATE instances SET last_status_code = ?, last_error_details = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
428 if cursor.rowcount == 0:
429 # DEBUG: print("DEBUG: Did not update any rows:", domain)
430 pending_errors[domain] = res
432 log_error(domain, res)
434 except BaseException as e:
435 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
438 # DEBUG: print("DEBUG: EXIT!")
440 def update_last_instance_fetch(domain: str):
441 #print("DEBUG: Updating last_instance_fetch for domain:", domain)
443 cursor.execute("UPDATE instances SET last_instance_fetch = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
449 if cursor.rowcount == 0:
450 print("WARNING: Did not update any rows:", domain)
452 except BaseException as e:
453 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
457 #print("DEBUG: EXIT!")
459 def update_last_nodeinfo(domain: str):
460 # DEBUG: print("DEBUG: Updating last_nodeinfo for domain:", domain)
462 cursor.execute("UPDATE instances SET last_nodeinfo = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
468 if cursor.rowcount == 0:
469 print("WARNING: Did not update any rows:", domain)
471 except BaseException as e:
472 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
476 # DEBUG: print("DEBUG: EXIT!")
478 def get_peers(domain: str, software: str) -> list:
479 # DEBUG: print(f"DEBUG: domain='{domain}',software='{software}' - CALLED!")
482 if software == "misskey":
483 # DEBUG: print(f"DEBUG: domain='{domain}' is misskey, sending API POST request ...")
485 step = config["misskey_offset"]
487 # iterating through all "suspended" (follow-only in its terminology)
488 # instances page-by-page, since that troonware doesn't support
489 # sending them all at once
491 # DEBUG: print(f"DEBUG: Fetching offset='{offset}' from '{domain}' ...")
493 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
497 }), {"Origin": domain})
499 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
504 }), {"Origin": domain})
506 # DEBUG: print("DEBUG: fetched():", len(fetched))
507 if len(fetched) == 0:
508 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
510 elif len(fetched) != config["misskey_offset"]:
511 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
512 offset = offset + (config["misskey_offset"] - len(fetched))
514 # DEBUG: print("DEBUG: Raising offset by step:", step)
515 offset = offset + step
518 # DEBUG: print(f"DEBUG: fetched({len(fetched)})[]={type(fetched)}")
519 if isinstance(fetched, dict) and "error" in fetched and "message" in fetched["error"]:
520 print(f"WARNING: post_json_api() returned error: {fetched['error']['message']}")
521 update_last_error(domain, fetched["error"]["message"])
525 # DEBUG: print(f"DEBUG: row():{len(row)}")
526 if not "host" in row:
527 print(f"WARNING: row()={len(row)} does not contain element 'host': {row},domain='{domain}'")
529 elif is_blacklisted(row["host"]):
530 # DEBUG: print(f"DEBUG: row[host]='{row['host']}' is blacklisted. domain='{domain}'")
533 # DEBUG: print(f"DEBUG: Adding peer: '{row['host']}'")
534 peers.append(row["host"])
536 #print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
537 update_last_instance_fetch(domain)
539 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
541 elif software == "lemmy":
542 # DEBUG: print(f"DEBUG: domain='{domain}' is Lemmy, fetching JSON ...")
544 res = reqto.get(f"https://{domain}/api/v3/site", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
547 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code='{res.status_code}',data[]='{type(data)}'")
548 if not res.ok or res.status_code >= 400:
549 print("WARNING: Could not reach any JSON API:", domain)
550 update_last_error(domain, res)
551 elif res.ok and isinstance(data, list):
552 # DEBUG: print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
554 elif "federated_instances" in data:
555 # DEBUG: print(f"DEBUG: Found federated_instances for domain='{domain}'")
556 peers = peers + add_peers(data["federated_instances"])
557 # DEBUG: print("DEBUG: Added instance(s) to peers")
559 print("WARNING: JSON response does not contain 'federated_instances':", domain)
560 update_last_error(domain, res)
562 except BaseException as e:
563 print(f"WARNING: Exception during fetching JSON: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
565 #print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
566 update_last_instance_fetch(domain)
568 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
570 elif software == "peertube":
571 # DEBUG: print(f"DEBUG: domain='{domain}' is a PeerTube, fetching JSON ...")
574 for mode in ["followers", "following"]:
575 # DEBUG: print(f"DEBUG: domain='{domain}',mode='{mode}'")
578 res = reqto.get(f"https://{domain}/api/v1/server/{mode}?start={start}&count=100", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
581 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code='{res.status_code}',data[]='{type(data)}'")
582 if res.ok and isinstance(data, dict):
583 # DEBUG: print("DEBUG: Success, data:", len(data))
585 # DEBUG: print(f"DEBUG: Found {len(data['data'])} record(s).")
586 for record in data["data"]:
587 # DEBUG: print(f"DEBUG: record()={len(record)}")
588 if mode in record and "host" in record[mode]:
589 # DEBUG: print(f"DEBUG: Found host={record[mode]['host']}, adding ...")
590 peers.append(record[mode]["host"])
592 print(f"WARNING: record from '{domain}' has no '{mode}' or 'host' record: {record}")
594 if len(data["data"]) < 100:
595 # DEBUG: print("DEBUG: Reached end of JSON response:", domain)
598 # Continue with next row
601 except BaseException as e:
602 print(f"WARNING: Exception during fetching JSON: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
604 #print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
605 update_last_instance_fetch(domain)
607 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
610 # DEBUG: print(f"DEBUG: Fetching get_peers_url='{get_peers_url}' from '{domain}' ...")
612 res = reqto.get(f"https://{domain}{get_peers_url}", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
615 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
616 if not res.ok or res.status_code >= 400:
617 # DEBUG: print(f"DEBUG: Was not able to fetch '{get_peers_url}', trying alternative ...")
618 res = reqto.get(f"https://{domain}/api/v3/site", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
621 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
622 if not res.ok or res.status_code >= 400:
623 print("WARNING: Could not reach any JSON API:", domain)
624 update_last_error(domain, res)
625 elif res.ok and isinstance(data, list):
626 print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
628 elif "federated_instances" in data:
629 # DEBUG: print(f"DEBUG: Found federated_instances for domain='{domain}'")
630 peers = peers + add_peers(data["federated_instances"])
631 # DEBUG: print("DEBUG: Added instance(s) to peers")
633 print("WARNING: JSON response does not contain 'federated_instances':", domain)
634 update_last_error(domain, res)
636 # DEBUG: print("DEBUG: Querying API was successful:", domain, len(data))
639 except BaseException as e:
640 print("WARNING: Some error during get():", domain, e)
641 update_last_error(domain, e)
643 #print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
644 update_last_instance_fetch(domain)
646 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
649 def post_json_api(domain: str, path: str, parameter: str, extra_headers: dict = {}) -> dict:
650 # DEBUG: print("DEBUG: Sending POST to domain,path,parameter:", domain, path, parameter, extra_headers)
653 res = reqto.post(f"https://{domain}{path}", data=parameter, headers={**api_headers, **extra_headers}, timeout=(config["connection_timeout"], config["read_timeout"]))
656 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
657 if not res.ok or res.status_code >= 400:
658 print(f"WARNING: Cannot query JSON API: domain='{domain}',path='{path}',parameter()={len(parameter)},res.status_code='{res.status_code}',data[]='{type(data)}'")
659 update_last_error(domain, res)
661 except BaseException as e:
662 print(f"WARNING: Some error during post(): domain='{domain}',path='{path}',parameter()={len(parameter)},exception[{type(e)}]:'{str(e)}'")
664 # DEBUG: print(f"DEBUG: Returning data({len(data)})=[]:{type(data)}")
667 def fetch_nodeinfo(domain: str, path: str = None) -> list:
668 # DEBUG: print("DEBUG: Fetching nodeinfo from domain,path:", domain, path)
670 nodeinfo = fetch_wellknown_nodeinfo(domain)
671 # DEBUG: print("DEBUG: nodeinfo:", len(nodeinfo))
673 if len(nodeinfo) > 0:
674 # DEBUG: print("DEBUG: Returning auto-discovered nodeinfo:", len(nodeinfo))
678 f"https://{domain}/nodeinfo/2.1.json",
679 f"https://{domain}/nodeinfo/2.1",
680 f"https://{domain}/nodeinfo/2.0.json",
681 f"https://{domain}/nodeinfo/2.0",
682 f"https://{domain}/nodeinfo/1.0",
683 f"https://{domain}/api/v1/instance"
687 for request in requests:
688 if path != None and path != "" and request != path:
689 print(f"DEBUG: path='{path}' does not match request='{request}' - SKIPPED!")
693 # DEBUG: print("DEBUG: Fetching request:", request)
694 res = reqto.get(request, headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
697 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
698 if res.ok and isinstance(data, dict):
699 # DEBUG: print("DEBUG: Success:", request)
700 nodeinfos["detection_mode"][domain] = "STATIC_CHECK"
701 nodeinfos["nodeinfo_url"][domain] = request
703 elif res.ok and isinstance(data, list):
704 # DEBUG: print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
706 elif not res.ok or res.status_code >= 400:
707 print("WARNING: Failed fetching nodeinfo from domain:", domain)
708 update_last_error(domain, res)
711 except BaseException as e:
712 # DEBUG: print("DEBUG: Cannot fetch API request:", request)
713 update_last_error(domain, e)
716 # DEBUG: print("DEBUG: Returning data[]:", type(data))
719 def fetch_wellknown_nodeinfo(domain: str) -> list:
720 # DEBUG: print("DEBUG: Fetching .well-known info for domain:", domain)
724 res = reqto.get(f"https://{domain}/.well-known/nodeinfo", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
727 # DEBUG: print("DEBUG: domain,res.ok,data[]:", domain, res.ok, type(data))
728 if res.ok and isinstance(data, dict):
730 # DEBUG: print("DEBUG: Found entries:", len(nodeinfo), domain)
731 if "links" in nodeinfo:
732 # DEBUG: print("DEBUG: Found links in nodeinfo():", len(nodeinfo["links"]))
733 for link in nodeinfo["links"]:
734 # DEBUG: print("DEBUG: rel,href:", link["rel"], link["href"])
735 if link["rel"] in nodeinfo_identifier:
736 # DEBUG: print("DEBUG: Fetching nodeinfo from:", link["href"])
737 res = reqto.get(link["href"])
740 # DEBUG: print("DEBUG: href,res.ok,res.status_code:", link["href"], res.ok, res.status_code)
741 if res.ok and isinstance(data, dict):
742 # DEBUG: print("DEBUG: Found JSON nodeinfo():", len(data))
743 nodeinfos["detection_mode"][domain] = "AUTO_DISCOVERY"
744 nodeinfos["nodeinfo_url"][domain] = link["href"]
747 print("WARNING: Unknown 'rel' value:", domain, link["rel"])
749 print("WARNING: nodeinfo does not contain 'links':", domain)
751 except BaseException as e:
752 print("WARNING: Failed fetching .well-known info:", domain)
753 update_last_error(domain, e)
756 # DEBUG: print("DEBUG: Returning data[]:", type(data))
759 def fetch_generator_from_path(domain: str, path: str = "/") -> str:
760 # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' - CALLED!")
764 # DEBUG: print(f"DEBUG: Fetching path='{path}' from '{domain}' ...")
765 res = reqto.get(f"https://{domain}{path}", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"]))
767 # DEBUG: print("DEBUG: domain,res.ok,res.status_code,res.text[]:", domain, res.ok, res.status_code, type(res.text))
768 if res.ok and res.status_code < 300 and len(res.text) > 0:
769 # DEBUG: print("DEBUG: Search for <meta name='generator'>:", domain)
770 doc = bs4.BeautifulSoup(res.text, "html.parser")
772 # DEBUG: print("DEBUG: doc[]:", type(doc))
773 tag = doc.find("meta", {"name": "generator"})
775 # DEBUG: print(f"DEBUG: tag[{type(tag)}: {tag}")
776 if isinstance(tag, bs4.element.Tag):
777 # DEBUG: print("DEBUG: Found generator meta tag: ", domain)
778 software = tidyup(tag.get("content"))
779 print(f"INFO: domain='{domain}' is generated by '{software}'")
780 nodeinfos["detection_mode"][domain] = "GENERATOR"
781 remove_pending_error(domain)
783 except BaseException as e:
784 # DEBUG: print(f"DEBUG: Cannot fetch / from '{domain}':", e)
785 update_last_error(domain, e)
788 # DEBUG: print(f"DEBUG: software[]={type(software)}")
789 if type(software) is str and software == "":
790 # DEBUG: print(f"DEBUG: Corrected empty string to None for software of domain='{domain}'")
792 elif type(software) is str and ("." in software or " " in software):
793 # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
794 software = remove_version(software)
796 # DEBUG: print(f"DEBUG: software[]={type(software)}")
797 if type(software) is str and "powered by" in software:
798 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
799 software = remove_version(strip_powered_by(software))
800 elif type(software) is str and " by " in software:
801 # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
802 software = strip_until(software, " by ")
803 elif type(software) is str and " see " in software:
804 # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
805 software = strip_until(software, " see ")
807 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
810 def determine_software(domain: str, path: str = None) -> str:
811 # DEBUG: print("DEBUG: Determining software for domain,path:", domain, path)
814 # DEBUG: print(f"DEBUG: Fetching nodeinfo from '{domain}' ...")
815 data = fetch_nodeinfo(domain, path)
817 # DEBUG: print("DEBUG: data[]:", type(data))
818 if not isinstance(data, dict) or len(data) == 0:
819 # DEBUG: print("DEBUG: Could not determine software type:", domain)
820 return fetch_generator_from_path(domain)
822 # DEBUG: print("DEBUG: data():", len(data), data)
823 if "status" in data and data["status"] == "error" and "message" in data:
824 print("WARNING: JSON response is an error:", data["message"])
825 update_last_error(domain, data["message"])
826 return fetch_generator_from_path(domain)
827 elif "software" not in data or "name" not in data["software"]:
828 # DEBUG: print(f"DEBUG: JSON response from {domain} does not include [software][name], fetching / ...")
829 software = fetch_generator_from_path(domain)
831 # DEBUG: print(f"DEBUG: Generator for domain='{domain}' is: {software}, EXIT!")
834 software = tidyup(data["software"]["name"])
836 # DEBUG: print("DEBUG: sofware after tidyup():", software)
837 if software in ["akkoma", "rebased"]:
838 # DEBUG: print("DEBUG: Setting pleroma:", domain, software)
840 elif software in ["hometown", "ecko"]:
841 # DEBUG: print("DEBUG: Setting mastodon:", domain, software)
842 software = "mastodon"
843 elif software in ["calckey", "groundpolis", "foundkey", "cherrypick", "meisskey"]:
844 # DEBUG: print("DEBUG: Setting misskey:", domain, software)
846 elif software.find("/") > 0:
847 print("WARNING: Spliting of slash:", software)
848 software = software.split("/")[-1];
849 elif software.find("|") > 0:
850 print("WARNING: Spliting of pipe:", software)
851 software = tidyup(software.split("|")[0]);
852 elif "powered by" in software:
853 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
854 software = strip_powered_by(software)
855 elif type(software) is str and " by " in software:
856 # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
857 software = strip_until(software, " by ")
858 elif type(software) is str and " see " in software:
859 # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
860 software = strip_until(software, " see ")
862 # DEBUG: print(f"DEBUG: software[]={type(software)}")
864 print("WARNING: tidyup() left no software name behind:", domain)
867 # DEBUG: print(f"DEBUG: software[]={type(software)}")
868 if str(software) == "":
869 # DEBUG: print(f"DEBUG: software for '{domain}' was not detected, trying generator ...")
870 software = fetch_generator_from_path(domain)
871 elif len(str(software)) > 0 and ("." in software or " " in software):
872 # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
873 software = remove_version(software)
875 # DEBUG: print(f"DEBUG: software[]={type(software)}")
876 if type(software) is str and "powered by" in software:
877 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
878 software = remove_version(strip_powered_by(software))
880 # DEBUG: print("DEBUG: Returning domain,software:", domain, software)
883 def update_block_reason(reason: str, blocker: str, blocked: str, block_level: str):
884 # DEBUG: print("DEBUG: Updating block reason:", reason, blocker, blocked, block_level)
887 "UPDATE blocks SET reason = ?, last_seen = ? WHERE blocker = ? AND blocked = ? AND block_level = ? AND reason = ''",
897 # DEBUG: print(f"DEBUG: cursor.rowcount={cursor.rowcount}")
898 if cursor.rowcount == 0:
899 print("WARNING: Did not update any rows:", domain)
901 except BaseException as e:
902 print(f"ERROR: failed SQL query: reason='{reason}',blocker='{blocker}',blocked='{blocked}',block_level='{block_level}',sql='{sql}',exception[{type(e)}]:'{str(e)}'")
905 # DEBUG: print("DEBUG: EXIT!")
907 def update_last_seen(blocker: str, blocked: str, block_level: str):
908 # DEBUG: print("DEBUG: Updating last_seen for:", blocker, blocked, block_level)
911 "UPDATE blocks SET last_seen = ? WHERE blocker = ? AND blocked = ? AND block_level = ?",
920 if cursor.rowcount == 0:
921 print("WARNING: Did not update any rows:", domain)
923 except BaseException as e:
924 print(f"ERROR: failed SQL query: last_seen='{last_seen}',blocker='{blocker}',blocked='{blocked}',block_level='{block_level}',exception[{type(e)}]:'{str(e)}'")
927 # DEBUG: print("DEBUG: EXIT!")
929 def block_instance(blocker: str, blocked: str, reason: str, block_level: str):
930 # DEBUG: print("DEBUG: blocker,blocked,reason,block_level:", blocker, blocked, reason, block_level)
931 if not validators.domain(blocker.split("/")[0]):
932 print("WARNING: Bad blocker:", blocker)
934 elif not validators.domain(blocked.split("/")[0]):
935 print("WARNING: Bad blocked:", blocked)
938 print("INFO: New block:", blocker, blocked, reason, block_level, first_seen, last_seen)
941 "INSERT INTO blocks (blocker, blocked, reason, block_level, first_seen, last_seen) VALUES(?, ?, ?, ?, ?, ?)",
952 except BaseException as e:
953 print(f"ERROR: failed SQL query: blocker='{blocker}',blocked='{blocked}',reason='{reason}',block_level='{block_level}',first_seen='{first_seen}',last_seen='{last_seen}',exception[{type(e)}]:'{str(e)}'")
956 # DEBUG: print("DEBUG: EXIT!")
958 def is_instance_registered(domain: str) -> bool:
959 # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!")
960 if not is_cache_initialized("is_registered"):
961 # DEBUG: print(f"DEBUG: Cache for 'is_registered' not initialized, fetching all rows ...")
963 cursor.execute("SELECT domain FROM instances")
966 set_all_cache_key("is_registered", cursor.fetchall(), True)
967 except BaseException as e:
968 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
972 registered = is_cache_key_set("is_registered", domain)
974 # DEBUG: print(f"DEBUG: registered='{registered}' - EXIT!")
977 def add_instance(domain: str, origin: str, originator: str, path: str = None):
978 # DEBUG: print("DEBUG: domain,origin,originator,path:", domain, origin, originator, path)
979 if not validators.domain(domain.split("/")[0]):
980 print("WARNING: Bad domain name:", domain)
982 elif origin is not None and not validators.domain(origin.split("/")[0]):
983 print("WARNING: Bad origin name:", origin)
986 software = determine_software(domain, path)
987 # DEBUG: print("DEBUG: Determined software:", software)
989 print(f"INFO: Adding instance {domain} (origin: {origin})")
992 "INSERT INTO instances (domain, origin, originator, hash, software, first_seen) VALUES (?, ?, ?, ?, ?, ?)",
1003 set_cache_key("is_registered", domain, True)
1005 if has_pending_nodeinfos(domain):
1006 # DEBUG: print(f"DEBUG: domain='{domain}' has pending nodeinfo being updated ...")
1007 update_nodeinfos(domain)
1008 remove_pending_error(domain)
1010 if domain in pending_errors:
1011 # DEBUG: print("DEBUG: domain has pending error being updated:", domain)
1012 update_last_error(domain, pending_errors[domain])
1013 remove_pending_error(domain)
1015 except BaseException as e:
1016 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
1019 # DEBUG: print("DEBUG: Updating nodeinfo for domain:", domain)
1020 update_last_nodeinfo(domain)
1022 # DEBUG: print("DEBUG: EXIT!")
1024 def send_bot_post(instance: str, blocks: dict):
1025 message = instance + " has blocked the following instances:\n\n"
1028 if len(blocks) > 20:
1030 blocks = blocks[0 : 19]
1032 for block in blocks:
1033 if block["reason"] == None or block["reason"] == '':
1034 message = message + block["blocked"] + " with unspecified reason\n"
1036 if len(block["reason"]) > 420:
1037 block["reason"] = block["reason"][0:419] + "[…]"
1039 message = message + block["blocked"] + ' for "' + block["reason"].replace("@", "@\u200b") + '"\n'
1042 message = message + "(the list has been truncated to the first 20 entries)"
1044 botheaders = {**api_headers, **{"Authorization": "Bearer " + config["bot_token"]}}
1047 f"{config['bot_instance']}/api/v1/statuses",
1050 "visibility" : config['bot_visibility'],
1051 "content_type": "text/plain"
1059 def get_mastodon_blocks(domain: str) -> dict:
1060 # DEBUG: print("DEBUG: Fetching mastodon blocks from domain:", domain)
1062 "Suspended servers": [],
1063 "Filtered media" : [],
1064 "Limited servers" : [],
1065 "Silenced servers" : [],
1069 doc = bs4.BeautifulSoup(
1070 reqto.get(f"https://{domain}/about/more", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"])).text,
1073 except BaseException as e:
1074 print("ERROR: Cannot fetch from domain:", domain, e)
1075 update_last_error(domain, e)
1078 for header in doc.find_all("h3"):
1079 header_text = tidyup(header.text)
1081 if header_text in language_mapping:
1082 # DEBUG: print(f"DEBUG: header_text='{header_text}'")
1083 header_text = language_mapping[header_text]
1085 if header_text in blocks or header_text.lower() in blocks:
1086 # replaced find_next_siblings with find_all_next to account for instances that e.g. hide lists in dropdown menu
1087 for line in header.find_all_next("table")[0].find_all("tr")[1:]:
1088 blocks[header_text].append(
1090 "domain": tidyup(line.find("span").text),
1091 "hash" : tidyup(line.find("span")["title"][9:]),
1092 "reason": tidyup(line.find_all("td")[1].text),
1096 # DEBUG: print("DEBUG: Returning blocks for domain:", domain)
1098 "reject" : blocks["Suspended servers"],
1099 "media_removal" : blocks["Filtered media"],
1100 "followers_only": blocks["Limited servers"] + blocks["Silenced servers"],
1103 def get_friendica_blocks(domain: str) -> dict:
1104 # DEBUG: print("DEBUG: Fetching friendica blocks from domain:", domain)
1108 doc = bs4.BeautifulSoup(
1109 reqto.get(f"https://{domain}/friendica", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"])).text,
1112 except BaseException as e:
1113 print("WARNING: Failed to fetch /friendica from domain:", domain, e)
1114 update_last_error(domain, e)
1117 blocklist = doc.find(id="about_blocklist")
1119 # Prevents exceptions:
1120 if blocklist is None:
1121 # DEBUG: print("DEBUG:Instance has no block list:", domain)
1124 for line in blocklist.find("table").find_all("tr")[1:]:
1125 # DEBUG: print(f"DEBUG: line='{line}'")
1127 "domain": tidyup(line.find_all("td")[0].text),
1128 "reason": tidyup(line.find_all("td")[1].text)
1131 # DEBUG: print("DEBUG: Returning blocks() for domain:", domain, len(blocks))
1136 def get_misskey_blocks(domain: str) -> dict:
1137 # DEBUG: print("DEBUG: Fetching misskey blocks from domain:", domain)
1144 step = config["misskey_offset"]
1146 # iterating through all "suspended" (follow-only in its terminology)
1147 # instances page-by-page, since that troonware doesn't support
1148 # sending them all at once
1150 # DEBUG: print(f"DEBUG: Fetching offset='{offset}' from '{domain}' ...")
1152 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1153 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
1158 }), {"Origin": domain})
1160 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1161 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
1166 "offset" : offset - 1
1167 }), {"Origin": domain})
1169 # DEBUG: print("DEBUG: fetched():", len(fetched))
1170 if len(fetched) == 0:
1171 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
1173 elif len(fetched) != config["misskey_offset"]:
1174 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
1175 offset = offset + (config["misskey_offset"] - len(fetched))
1177 # DEBUG: print("DEBUG: Raising offset by step:", step)
1178 offset = offset + step
1180 for instance in fetched:
1182 if instance["isSuspended"]:
1183 blocks["suspended"].append(
1185 "domain": tidyup(instance["host"]),
1186 # no reason field, nothing
1191 except BaseException as e:
1192 print("WARNING: Caught error, exiting loop:", domain, e)
1193 update_last_error(domain, e)
1198 # same shit, different asshole ("blocked" aka full suspend)
1201 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1202 fetched = post_json_api(domain,"/api/federation/instances", json.dumps({
1207 }), {"Origin": domain})
1209 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1210 fetched = post_json_api(domain,"/api/federation/instances", json.dumps({
1216 }), {"Origin": domain})
1218 # DEBUG: print("DEBUG: fetched():", len(fetched))
1219 if len(fetched) == 0:
1220 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
1222 elif len(fetched) != config["misskey_offset"]:
1223 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
1224 offset = offset + (config["misskey_offset"] - len(fetched))
1226 # DEBUG: print("DEBUG: Raising offset by step:", step)
1227 offset = offset + step
1229 for instance in fetched:
1230 if instance["isBlocked"]:
1231 blocks["blocked"].append({
1232 "domain": tidyup(instance["host"]),
1236 except BaseException as e:
1237 print("ERROR: Exception during POST:", domain, e)
1238 update_last_error(domain, e)
1242 #print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
1243 update_last_instance_fetch(domain)
1245 # DEBUG: print("DEBUG: Returning for domain,blocked(),suspended():", domain, len(blocks["blocked"]), len(blocks["suspended"]))
1247 "reject" : blocks["blocked"],
1248 "followers_only": blocks["suspended"]
1251 def tidyup(string: str) -> str:
1252 # some retards put their blocks in variable case
1253 string = string.lower().strip()
1255 # other retards put the port
1256 string = re.sub("\:\d+$", "", string)
1258 # bigger retards put the schema in their blocklist, sometimes even without slashes
1259 string = re.sub("^https?\:(\/*)", "", string)
1261 # and trailing slash
1262 string = re.sub("\/$", "", string)
1265 string = re.sub("^\@", "", string)
1267 # the biggest retards of them all try to block individual users
1268 string = re.sub("(.+)\@", "", string)