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 # NOISY-DEBUG: print(f"DEBUG: key='{key}',rows()={len(rows)},value[]={type(value)} - CALLED!")
139 if not is_cache_initialized(key):
140 # NOISY-DEBUG: print(f"DEBUG: Cache for key='{key}' not initialized.")
144 # NOISY-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 # NOISY-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_hosted_on(software: str) -> str:
264 # DEBUG: print(f"DEBUG: software='{software}' - CALLED!")
266 print(f"ERROR: Bad method call, 'software' is empty")
267 raise Exception("Parameter 'software' is empty")
268 elif not "hosted on" in software:
269 print(f"WARNING: Cannot find 'hosted on' in '{software}'!")
272 end = software.find("hosted on ")
273 # DEBUG: print(f"DEBUG: end[{type(end)}]='{end}'")
275 software = software[0, start].strip()
276 # DEBUG: print(f"DEBUG: software='{software}'")
278 software = strip_until(software, " - ")
280 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
283 def strip_until(software: str, until: str) -> str:
284 # DEBUG: print(f"DEBUG: software='{software}',until='{until}' - CALLED!")
286 print(f"ERROR: Bad method call, 'software' is empty")
287 raise Exception("Parameter 'software' is empty")
289 print(f"ERROR: Bad method call, 'until' is empty")
290 raise Exception("Parameter 'until' is empty")
291 elif not until in software:
292 print(f"WARNING: Cannot find '{until}' in '{software}'!")
295 # Next, strip until part
296 end = software.find(until)
298 # DEBUG: print(f"DEBUG: end[{type(end)}]='{end}'")
300 software = software[0:end].strip()
302 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
305 def is_blacklisted(domain: str) -> bool:
307 for peer in blacklist:
313 def remove_pending_error(domain: str):
315 # Prevent updating any pending errors, nodeinfo was found
316 del pending_errors[domain]
321 def get_hash(domain: str) -> str:
322 return hashlib.sha256(domain.encode("utf-8")).hexdigest()
324 def update_last_blocked(domain: str):
325 # DEBUG: print("DEBUG: Updating last_blocked for domain", domain)
327 cursor.execute("UPDATE instances SET last_blocked = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
333 if cursor.rowcount == 0:
334 print("WARNING: Did not update any rows:", domain)
336 except BaseException as e:
337 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
340 # DEBUG: print("DEBUG: EXIT!")
342 def has_pending_nodeinfos(domain: str) -> bool:
343 # DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!")
345 for key in nodeinfos:
346 # DEBUG: print(f"DEBUG: key='{key}',domain='{domain}',nodeinfos[key]='{nodeinfos[key]}'")
347 if domain in nodeinfos[key]:
351 # DEBUG: print(f"DEBUG: has_pending='{has_pending}' - EXIT!")
354 def update_nodeinfos(domain: str):
355 # DEBUG: print("DEBUG: Updating nodeinfo for domain:", domain)
358 for key in nodeinfos:
359 # DEBUG: print("DEBUG: key:", key)
360 if domain in nodeinfos[key]:
361 # DEBUG: print(f"DEBUG: Adding '{nodeinfos[key][domain]}' for key='{key}' ...")
362 fields.append(nodeinfos[key][domain])
363 sql_string += f" {key} = ?,"
365 fields.append(domain)
366 # DEBUG: print(f"DEBUG: sql_string='{sql_string}',fields()={len(fields)}")
368 sql = "UPDATE instances SET" + sql_string + " last_status_code = NULL, last_error_details = NULL WHERE domain = ? LIMIT 1"
369 # DEBUG: print("DEBUG: sql:", sql)
372 # DEBUG: print("DEBUG: Executing SQL:", sql)
373 cursor.execute(sql, fields)
374 # DEBUG: print(f"DEBUG: Success! (rowcount={cursor.rowcount })")
376 if cursor.rowcount == 0:
377 print("WARNING: Did not update any rows:", domain)
379 except BaseException as e:
380 print(f"ERROR: failed SQL query: domain='{domain}',sql='{sql}',exception[{type(e)}]:'{str(e)}'")
383 # DEBUG: print("DEBUG: Deleting nodeinfos for domain:", domain)
384 for key in nodeinfos:
386 # DEBUG: print("DEBUG: Deleting key:", key)
387 del nodeinfos[key][domain]
391 # DEBUG: print("DEBUG: EXIT!")
393 def log_error(domain: str, res: any):
394 # DEBUG: print("DEBUG: domain,res[]:", domain, type(res))
396 # DEBUG: print("DEBUG: BEFORE res[]:", type(res))
397 if isinstance(res, BaseException) or isinstance(res, json.JSONDecodeError):
400 # DEBUG: print("DEBUG: AFTER res[]:", type(res))
402 cursor.execute("INSERT INTO error_log (domain, error_code, error_message, created) VALUES (?, 999, ?, ?)",[
408 cursor.execute("INSERT INTO error_log (domain, error_code, error_message, created) VALUES (?, ?, ?, ?)",[
415 # Cleanup old entries
416 # DEBUG: print(f"DEBUG: Purging old records (distance: {config['error_log_cleanup']})")
417 cursor.execute("DELETE FROM error_log WHERE created < ?", [time.time() - config["error_log_cleanup"]])
418 except BaseException as e:
419 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
422 # DEBUG: print("DEBUG: EXIT!")
424 def update_last_error(domain: str, res: any):
425 # DEBUG: print("DEBUG: domain,res[]:", domain, type(res))
427 # DEBUG: print("DEBUG: BEFORE res[]:", type(res))
428 if isinstance(res, BaseException) or isinstance(res, json.JSONDecodeError):
431 # DEBUG: print("DEBUG: AFTER res[]:", type(res))
433 # DEBUG: print(f"DEBUG: Setting last_error_details='{res}'");
434 cursor.execute("UPDATE instances SET last_status_code = 999, last_error_details = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
440 # DEBUG: print(f"DEBUG: Setting last_error_details='{res.reason}'");
441 cursor.execute("UPDATE instances SET last_status_code = ?, last_error_details = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
448 if cursor.rowcount == 0:
449 # DEBUG: print("DEBUG: Did not update any rows:", domain)
450 pending_errors[domain] = res
452 log_error(domain, res)
454 except BaseException as e:
455 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
458 # DEBUG: print("DEBUG: EXIT!")
460 def update_last_instance_fetch(domain: str):
461 # DEBUG: print("DEBUG: Updating last_instance_fetch for domain:", domain)
463 cursor.execute("UPDATE instances SET last_instance_fetch = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
469 if cursor.rowcount == 0:
470 print("WARNING: Did not update any rows:", domain)
472 except BaseException as e:
473 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
477 # DEBUG: print("DEBUG: EXIT!")
479 def update_last_nodeinfo(domain: str):
480 # DEBUG: print("DEBUG: Updating last_nodeinfo for domain:", domain)
482 cursor.execute("UPDATE instances SET last_nodeinfo = ?, last_updated = ? WHERE domain = ? LIMIT 1", [
488 if cursor.rowcount == 0:
489 print("WARNING: Did not update any rows:", domain)
491 except BaseException as e:
492 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
496 # DEBUG: print("DEBUG: EXIT!")
498 def get_peers(domain: str, software: str) -> list:
499 # DEBUG: print(f"DEBUG: domain='{domain}',software='{software}' - CALLED!")
502 if software == "misskey":
503 # DEBUG: print(f"DEBUG: domain='{domain}' is misskey, sending API POST request ...")
505 step = config["misskey_offset"]
507 # iterating through all "suspended" (follow-only in its terminology)
508 # instances page-by-page, since that troonware doesn't support
509 # sending them all at once
511 # DEBUG: print(f"DEBUG: Fetching offset='{offset}' from '{domain}' ...")
513 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
517 }), {"Origin": domain})
519 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
524 }), {"Origin": domain})
526 # DEBUG: print("DEBUG: fetched():", len(fetched))
527 if len(fetched) == 0:
528 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
530 elif len(fetched) != config["misskey_offset"]:
531 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
532 offset = offset + (config["misskey_offset"] - len(fetched))
534 # DEBUG: print("DEBUG: Raising offset by step:", step)
535 offset = offset + step
538 # DEBUG: print(f"DEBUG: fetched({len(fetched)})[]={type(fetched)}")
539 if isinstance(fetched, dict) and "error" in fetched and "message" in fetched["error"]:
540 print(f"WARNING: post_json_api() returned error: {fetched['error']['message']}")
541 update_last_error(domain, fetched["error"]["message"])
545 # DEBUG: print(f"DEBUG: row():{len(row)}")
546 if not "host" in row:
547 print(f"WARNING: row()={len(row)} does not contain element 'host': {row},domain='{domain}'")
549 elif is_blacklisted(row["host"]):
550 # DEBUG: print(f"DEBUG: row[host]='{row['host']}' is blacklisted. domain='{domain}'")
553 # DEBUG: print(f"DEBUG: Adding peer: '{row['host']}'")
554 peers.append(row["host"])
556 # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
557 update_last_instance_fetch(domain)
559 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
561 elif software == "lemmy":
562 # DEBUG: print(f"DEBUG: domain='{domain}' is Lemmy, fetching JSON ...")
564 res = reqto.get(f"https://{domain}/api/v3/site", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
567 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code='{res.status_code}',data[]='{type(data)}'")
568 if not res.ok or res.status_code >= 400:
569 print("WARNING: Could not reach any JSON API:", domain)
570 update_last_error(domain, res)
571 elif res.ok and isinstance(data, list):
572 # DEBUG: print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
574 elif "federated_instances" in data:
575 # DEBUG: print(f"DEBUG: Found federated_instances for domain='{domain}'")
576 peers = peers + add_peers(data["federated_instances"])
577 # DEBUG: print("DEBUG: Added instance(s) to peers")
579 print("WARNING: JSON response does not contain 'federated_instances':", domain)
580 update_last_error(domain, res)
582 except BaseException as e:
583 print(f"WARNING: Exception during fetching JSON: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
585 # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
586 update_last_instance_fetch(domain)
588 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
590 elif software == "peertube":
591 # DEBUG: print(f"DEBUG: domain='{domain}' is a PeerTube, fetching JSON ...")
594 for mode in ["followers", "following"]:
595 # DEBUG: print(f"DEBUG: domain='{domain}',mode='{mode}'")
598 res = reqto.get(f"https://{domain}/api/v1/server/{mode}?start={start}&count=100", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
601 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code='{res.status_code}',data[]='{type(data)}'")
602 if res.ok and isinstance(data, dict):
603 # DEBUG: print("DEBUG: Success, data:", len(data))
605 # DEBUG: print(f"DEBUG: Found {len(data['data'])} record(s).")
606 for record in data["data"]:
607 # DEBUG: print(f"DEBUG: record()={len(record)}")
608 if mode in record and "host" in record[mode]:
609 # DEBUG: print(f"DEBUG: Found host={record[mode]['host']}, adding ...")
610 peers.append(record[mode]["host"])
612 print(f"WARNING: record from '{domain}' has no '{mode}' or 'host' record: {record}")
614 if len(data["data"]) < 100:
615 # DEBUG: print("DEBUG: Reached end of JSON response:", domain)
618 # Continue with next row
621 except BaseException as e:
622 print(f"WARNING: Exception during fetching JSON: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
624 # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
625 update_last_instance_fetch(domain)
627 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
630 # DEBUG: print(f"DEBUG: Fetching get_peers_url='{get_peers_url}' from '{domain}' ...")
632 res = reqto.get(f"https://{domain}{get_peers_url}", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
635 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
636 if not res.ok or res.status_code >= 400:
637 # DEBUG: print(f"DEBUG: Was not able to fetch '{get_peers_url}', trying alternative ...")
638 res = reqto.get(f"https://{domain}/api/v3/site", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
641 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
642 if not res.ok or res.status_code >= 400:
643 print("WARNING: Could not reach any JSON API:", domain)
644 update_last_error(domain, res)
645 elif res.ok and isinstance(data, list):
646 # DEBUG: print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
648 elif "federated_instances" in data:
649 # DEBUG: print(f"DEBUG: Found federated_instances for domain='{domain}'")
650 peers = peers + add_peers(data["federated_instances"])
651 # DEBUG: print("DEBUG: Added instance(s) to peers")
653 print("WARNING: JSON response does not contain 'federated_instances':", domain)
654 update_last_error(domain, res)
656 # DEBUG: print("DEBUG: Querying API was successful:", domain, len(data))
659 except BaseException as e:
660 print("WARNING: Some error during get():", domain, e)
661 update_last_error(domain, e)
663 # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
664 update_last_instance_fetch(domain)
666 # DEBUG: print("DEBUG: Returning peers[]:", type(peers))
669 def post_json_api(domain: str, path: str, parameter: str, extra_headers: dict = {}) -> dict:
670 # DEBUG: print("DEBUG: Sending POST to domain,path,parameter:", domain, path, parameter, extra_headers)
673 res = reqto.post(f"https://{domain}{path}", data=parameter, headers={**api_headers, **extra_headers}, timeout=(config["connection_timeout"], config["read_timeout"]))
676 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
677 if not res.ok or res.status_code >= 400:
678 print(f"WARNING: Cannot query JSON API: domain='{domain}',path='{path}',parameter()={len(parameter)},res.status_code='{res.status_code}',data[]='{type(data)}'")
679 update_last_error(domain, res)
681 except BaseException as e:
682 print(f"WARNING: Some error during post(): domain='{domain}',path='{path}',parameter()={len(parameter)},exception[{type(e)}]:'{str(e)}'")
684 # DEBUG: print(f"DEBUG: Returning data({len(data)})=[]:{type(data)}")
687 def fetch_nodeinfo(domain: str, path: str = None) -> list:
688 # DEBUG: print("DEBUG: Fetching nodeinfo from domain,path:", domain, path)
690 nodeinfo = fetch_wellknown_nodeinfo(domain)
691 # DEBUG: print("DEBUG: nodeinfo:", nodeinfo)
693 if len(nodeinfo) > 0:
694 # DEBUG: print("DEBUG: Returning auto-discovered nodeinfo:", len(nodeinfo))
698 f"https://{domain}/nodeinfo/2.1.json",
699 f"https://{domain}/nodeinfo/2.1",
700 f"https://{domain}/nodeinfo/2.0.json",
701 f"https://{domain}/nodeinfo/2.0",
702 f"https://{domain}/nodeinfo/1.0",
703 f"https://{domain}/api/v1/instance"
707 for request in requests:
708 if path != None and path != "" and request != path:
709 # DEBUG: print(f"DEBUG: path='{path}' does not match request='{request}' - SKIPPED!")
713 # DEBUG: print("DEBUG: Fetching request:", request)
714 res = reqto.get(request, headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
717 # DEBUG: print(f"DEBUG: res.ok={res.ok},res.status_code={res.status_code},data[]='{type(data)}'")
718 if res.ok and isinstance(data, dict):
719 # DEBUG: print("DEBUG: Success:", request)
720 nodeinfos["detection_mode"][domain] = "STATIC_CHECK"
721 nodeinfos["nodeinfo_url"][domain] = request
723 elif res.ok and isinstance(data, list):
724 # DEBUG: print(f"DEBUG: domain='{domain}' returned a list: '{data}'")
726 elif not res.ok or res.status_code >= 400:
727 print("WARNING: Failed fetching nodeinfo from domain:", domain)
728 update_last_error(domain, res)
731 except BaseException as e:
732 # DEBUG: print("DEBUG: Cannot fetch API request:", request)
733 update_last_error(domain, e)
736 # DEBUG: print("DEBUG: Returning data[]:", type(data))
739 def fetch_wellknown_nodeinfo(domain: str) -> list:
740 # DEBUG: print("DEBUG: Fetching .well-known info for domain:", domain)
744 res = reqto.get(f"https://{domain}/.well-known/nodeinfo", headers=api_headers, timeout=(config["connection_timeout"], config["read_timeout"]))
747 # DEBUG: print("DEBUG: domain,res.ok,data[]:", domain, res.ok, type(data))
748 if res.ok and isinstance(data, dict):
750 # DEBUG: print("DEBUG: Found entries:", len(nodeinfo), domain)
751 if "links" in nodeinfo:
752 # DEBUG: print("DEBUG: Found links in nodeinfo():", len(nodeinfo["links"]))
753 for link in nodeinfo["links"]:
754 # DEBUG: print("DEBUG: rel,href:", link["rel"], link["href"])
755 if link["rel"] in nodeinfo_identifier:
756 # DEBUG: print("DEBUG: Fetching nodeinfo from:", link["href"])
757 res = reqto.get(link["href"])
760 # DEBUG: print("DEBUG: href,res.ok,res.status_code:", link["href"], res.ok, res.status_code)
761 if res.ok and isinstance(data, dict):
762 # DEBUG: print("DEBUG: Found JSON nodeinfo():", len(data))
763 nodeinfos["detection_mode"][domain] = "AUTO_DISCOVERY"
764 nodeinfos["nodeinfo_url"][domain] = link["href"]
767 print("WARNING: Unknown 'rel' value:", domain, link["rel"])
769 print("WARNING: nodeinfo does not contain 'links':", domain)
771 except BaseException as e:
772 print("WARNING: Failed fetching .well-known info:", domain)
773 update_last_error(domain, e)
776 # DEBUG: print("DEBUG: Returning data[]:", type(data))
779 def fetch_generator_from_path(domain: str, path: str = "/") -> str:
780 # DEBUG: print(f"DEBUG: domain='{domain}',path='{path}' - CALLED!")
784 # DEBUG: print(f"DEBUG: Fetching path='{path}' from '{domain}' ...")
785 res = reqto.get(f"https://{domain}{path}", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"]))
787 # DEBUG: print("DEBUG: domain,res.ok,res.status_code,res.text[]:", domain, res.ok, res.status_code, type(res.text))
788 if res.ok and res.status_code < 300 and len(res.text) > 0:
789 # DEBUG: print("DEBUG: Search for <meta name='generator'>:", domain)
790 doc = bs4.BeautifulSoup(res.text, "html.parser")
792 # DEBUG: print("DEBUG: doc[]:", type(doc))
793 generator = doc.find("meta", {"name": "generator"})
794 site_name = doc.find("meta", {"property": "og:site_name"})
796 # DEBUG: print(f"DEBUG: generator='{generator}',site_name='{site_name}'")
797 if isinstance(generator, bs4.element.Tag):
798 # DEBUG: print("DEBUG: Found generator meta tag:", domain)
799 software = tidyup(generator.get("content"))
800 print(f"INFO: domain='{domain}' is generated by '{software}'")
801 nodeinfos["detection_mode"][domain] = "GENERATOR"
802 remove_pending_error(domain)
803 elif isinstance(site_name, bs4.element.Tag):
804 # DEBUG: print("DEBUG: Found property=og:site_name:", domain)
805 sofware = tidyup(site_name.get("content"))
806 print(f"INFO: domain='{domain}' has og:site_name='{software}'")
807 nodeinfos["detection_mode"][domain] = "SITE_NAME"
808 remove_pending_error(domain)
810 except BaseException as e:
811 # DEBUG: print(f"DEBUG: Cannot fetch / from '{domain}':", e)
812 update_last_error(domain, e)
815 # DEBUG: print(f"DEBUG: software[]={type(software)}")
816 if type(software) is str and software == "":
817 # DEBUG: print(f"DEBUG: Corrected empty string to None for software of domain='{domain}'")
819 elif type(software) is str and ("." in software or " " in software):
820 # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
821 software = remove_version(software)
823 # DEBUG: print(f"DEBUG: software[]={type(software)}")
824 if type(software) is str and " powered by " in software:
825 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
826 software = remove_version(strip_powered_by(software))
827 elif type(software) is str and " hosted on " in software:
828 # DEBUG: print(f"DEBUG: software='{software}' has 'hosted on' in it")
829 software = remove_version(strip_hosted_on(software))
830 elif type(software) is str and " by " in software:
831 # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
832 software = strip_until(software, " by ")
833 elif type(software) is str and " see " in software:
834 # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
835 software = strip_until(software, " see ")
837 # DEBUG: print(f"DEBUG: software='{software}' - EXIT!")
840 def determine_software(domain: str, path: str = None) -> str:
841 # DEBUG: print("DEBUG: Determining software for domain,path:", domain, path)
844 # DEBUG: print(f"DEBUG: Fetching nodeinfo from '{domain}' ...")
845 data = fetch_nodeinfo(domain, path)
847 # DEBUG: print("DEBUG: data[]:", type(data))
848 if not isinstance(data, dict) or len(data) == 0:
849 # DEBUG: print("DEBUG: Could not determine software type:", domain)
850 return fetch_generator_from_path(domain)
852 # DEBUG: print("DEBUG: data():", len(data), data)
853 if "status" in data and data["status"] == "error" and "message" in data:
854 print("WARNING: JSON response is an error:", data["message"])
855 update_last_error(domain, data["message"])
856 return fetch_generator_from_path(domain)
857 elif "message" in data:
858 print("WARNING: JSON response contains only a message:", data["message"])
859 update_last_error(domain, data["message"])
860 return fetch_generator_from_path(domain)
861 elif "software" not in data or "name" not in data["software"]:
862 # DEBUG: print(f"DEBUG: JSON response from domain='{domain}' does not include [software][name], fetching / ...")
863 software = fetch_generator_from_path(domain)
865 # DEBUG: print(f"DEBUG: Generator for domain='{domain}' is: {software}, EXIT!")
868 software = tidyup(data["software"]["name"])
870 # DEBUG: print("DEBUG: sofware after tidyup():", software)
871 if software in ["akkoma", "rebased"]:
872 # DEBUG: print("DEBUG: Setting pleroma:", domain, software)
874 elif software in ["hometown", "ecko"]:
875 # DEBUG: print("DEBUG: Setting mastodon:", domain, software)
876 software = "mastodon"
877 elif software in ["calckey", "groundpolis", "foundkey", "cherrypick", "meisskey"]:
878 # DEBUG: print("DEBUG: Setting misskey:", domain, software)
880 elif software.find("/") > 0:
881 print("WARNING: Spliting of slash:", software)
882 software = software.split("/")[-1];
883 elif software.find("|") > 0:
884 print("WARNING: Spliting of pipe:", software)
885 software = tidyup(software.split("|")[0]);
886 elif "powered by" in software:
887 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
888 software = strip_powered_by(software)
889 elif type(software) is str and " by " in software:
890 # DEBUG: print(f"DEBUG: software='{software}' has ' by ' in it")
891 software = strip_until(software, " by ")
892 elif type(software) is str and " see " in software:
893 # DEBUG: print(f"DEBUG: software='{software}' has ' see ' in it")
894 software = strip_until(software, " see ")
896 # DEBUG: print(f"DEBUG: software[]={type(software)}")
898 print("WARNING: tidyup() left no software name behind:", domain)
901 # DEBUG: print(f"DEBUG: software[]={type(software)}")
902 if str(software) == "":
903 # DEBUG: print(f"DEBUG: software for '{domain}' was not detected, trying generator ...")
904 software = fetch_generator_from_path(domain)
905 elif len(str(software)) > 0 and ("." in software or " " in software):
906 # DEBUG: print(f"DEBUG: software='{software}' may contain a version number, domain='{domain}', removing it ...")
907 software = remove_version(software)
909 # DEBUG: print(f"DEBUG: software[]={type(software)}")
910 if type(software) is str and "powered by" in software:
911 # DEBUG: print(f"DEBUG: software='{software}' has 'powered by' in it")
912 software = remove_version(strip_powered_by(software))
914 # DEBUG: print("DEBUG: Returning domain,software:", domain, software)
917 def update_block_reason(reason: str, blocker: str, blocked: str, block_level: str):
918 # DEBUG: print("DEBUG: Updating block reason:", reason, blocker, blocked, block_level)
921 "UPDATE blocks SET reason = ?, last_seen = ? WHERE blocker = ? AND blocked = ? AND block_level = ? AND reason = ''",
931 # DEBUG: print(f"DEBUG: cursor.rowcount={cursor.rowcount}")
932 if cursor.rowcount == 0:
933 print("WARNING: Did not update any rows:", domain)
935 except BaseException as e:
936 print(f"ERROR: failed SQL query: reason='{reason}',blocker='{blocker}',blocked='{blocked}',block_level='{block_level}',sql='{sql}',exception[{type(e)}]:'{str(e)}'")
939 # DEBUG: print("DEBUG: EXIT!")
941 def update_last_seen(blocker: str, blocked: str, block_level: str):
942 # DEBUG: print("DEBUG: Updating last_seen for:", blocker, blocked, block_level)
945 "UPDATE blocks SET last_seen = ? WHERE blocker = ? AND blocked = ? AND block_level = ?",
954 if cursor.rowcount == 0:
955 print("WARNING: Did not update any rows:", domain)
957 except BaseException as e:
958 print(f"ERROR: failed SQL query: last_seen='{last_seen}',blocker='{blocker}',blocked='{blocked}',block_level='{block_level}',exception[{type(e)}]:'{str(e)}'")
961 # DEBUG: print("DEBUG: EXIT!")
963 def block_instance(blocker: str, blocked: str, reason: str, block_level: str):
964 # DEBUG: print("DEBUG: blocker,blocked,reason,block_level:", blocker, blocked, reason, block_level)
965 if not validators.domain(blocker.split("/")[0]):
966 print("WARNING: Bad blocker:", blocker)
968 elif not validators.domain(blocked.split("/")[0]):
969 print("WARNING: Bad blocked:", blocked)
972 print("INFO: New block:", blocker, blocked, reason, block_level, first_seen, last_seen)
975 "INSERT INTO blocks (blocker, blocked, reason, block_level, first_seen, last_seen) VALUES(?, ?, ?, ?, ?, ?)",
986 except BaseException as e:
987 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)}'")
990 # DEBUG: print("DEBUG: EXIT!")
992 def is_instance_registered(domain: str) -> bool:
993 # NOISY-DEBUG: print(f"DEBUG: domain='{domain}' - CALLED!")
994 if not is_cache_initialized("is_registered"):
995 # NOISY-DEBUG: print(f"DEBUG: Cache for 'is_registered' not initialized, fetching all rows ...")
997 cursor.execute("SELECT domain FROM instances")
1000 set_all_cache_key("is_registered", cursor.fetchall(), True)
1001 except BaseException as e:
1002 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
1006 registered = is_cache_key_set("is_registered", domain)
1008 # NOISY-DEBUG: print(f"DEBUG: registered='{registered}' - EXIT!")
1011 def add_instance(domain: str, origin: str, originator: str, path: str = None):
1012 # DEBUG: print("DEBUG: domain,origin,originator,path:", domain, origin, originator, path)
1013 if not validators.domain(domain.split("/")[0]):
1014 print("WARNING: Bad domain name:", domain)
1016 elif origin is not None and not validators.domain(origin.split("/")[0]):
1017 print("WARNING: Bad origin name:", origin)
1020 software = determine_software(domain, path)
1021 # DEBUG: print("DEBUG: Determined software:", software)
1023 print(f"INFO: Adding instance domain='{domain}' (origin='{origin}',software='{software}')")
1026 "INSERT INTO instances (domain, origin, originator, hash, software, first_seen) VALUES (?, ?, ?, ?, ?, ?)",
1037 set_cache_key("is_registered", domain, True)
1039 if has_pending_nodeinfos(domain):
1040 # DEBUG: print(f"DEBUG: domain='{domain}' has pending nodeinfo being updated ...")
1041 update_nodeinfos(domain)
1042 remove_pending_error(domain)
1044 if domain in pending_errors:
1045 # DEBUG: print("DEBUG: domain has pending error being updated:", domain)
1046 update_last_error(domain, pending_errors[domain])
1047 remove_pending_error(domain)
1049 except BaseException as e:
1050 print(f"ERROR: failed SQL query: domain='{domain}',exception[{type(e)}]:'{str(e)}'")
1053 # DEBUG: print("DEBUG: Updating nodeinfo for domain:", domain)
1054 update_last_nodeinfo(domain)
1056 # DEBUG: print("DEBUG: EXIT!")
1058 def send_bot_post(instance: str, blocks: dict):
1059 message = instance + " has blocked the following instances:\n\n"
1062 if len(blocks) > 20:
1064 blocks = blocks[0 : 19]
1066 for block in blocks:
1067 if block["reason"] == None or block["reason"] == '':
1068 message = message + block["blocked"] + " with unspecified reason\n"
1070 if len(block["reason"]) > 420:
1071 block["reason"] = block["reason"][0:419] + "[…]"
1073 message = message + block["blocked"] + ' for "' + block["reason"].replace("@", "@\u200b") + '"\n'
1076 message = message + "(the list has been truncated to the first 20 entries)"
1078 botheaders = {**api_headers, **{"Authorization": "Bearer " + config["bot_token"]}}
1081 f"{config['bot_instance']}/api/v1/statuses",
1084 "visibility" : config['bot_visibility'],
1085 "content_type": "text/plain"
1093 def get_mastodon_blocks(domain: str) -> dict:
1094 # DEBUG: print("DEBUG: Fetching mastodon blocks from domain:", domain)
1096 "Suspended servers": [],
1097 "Filtered media" : [],
1098 "Limited servers" : [],
1099 "Silenced servers" : [],
1103 doc = bs4.BeautifulSoup(
1104 reqto.get(f"https://{domain}/about/more", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"])).text,
1107 except BaseException as e:
1108 print("ERROR: Cannot fetch from domain:", domain, e)
1109 update_last_error(domain, e)
1112 for header in doc.find_all("h3"):
1113 header_text = tidyup(header.text)
1115 if header_text in language_mapping:
1116 # DEBUG: print(f"DEBUG: header_text='{header_text}'")
1117 header_text = language_mapping[header_text]
1119 if header_text in blocks or header_text.lower() in blocks:
1120 # replaced find_next_siblings with find_all_next to account for instances that e.g. hide lists in dropdown menu
1121 for line in header.find_all_next("table")[0].find_all("tr")[1:]:
1122 blocks[header_text].append(
1124 "domain": tidyup(line.find("span").text),
1125 "hash" : tidyup(line.find("span")["title"][9:]),
1126 "reason": tidyup(line.find_all("td")[1].text),
1130 # DEBUG: print("DEBUG: Returning blocks for domain:", domain)
1132 "reject" : blocks["Suspended servers"],
1133 "media_removal" : blocks["Filtered media"],
1134 "followers_only": blocks["Limited servers"] + blocks["Silenced servers"],
1137 def get_friendica_blocks(domain: str) -> dict:
1138 # DEBUG: print("DEBUG: Fetching friendica blocks from domain:", domain)
1142 doc = bs4.BeautifulSoup(
1143 reqto.get(f"https://{domain}/friendica", headers=headers, timeout=(config["connection_timeout"], config["read_timeout"])).text,
1146 except BaseException as e:
1147 print("WARNING: Failed to fetch /friendica from domain:", domain, e)
1148 update_last_error(domain, e)
1151 blocklist = doc.find(id="about_blocklist")
1153 # Prevents exceptions:
1154 if blocklist is None:
1155 # DEBUG: print("DEBUG:Instance has no block list:", domain)
1158 for line in blocklist.find("table").find_all("tr")[1:]:
1159 # DEBUG: print(f"DEBUG: line='{line}'")
1161 "domain": tidyup(line.find_all("td")[0].text),
1162 "reason": tidyup(line.find_all("td")[1].text)
1165 # DEBUG: print("DEBUG: Returning blocks() for domain:", domain, len(blocks))
1170 def get_misskey_blocks(domain: str) -> dict:
1171 # DEBUG: print("DEBUG: Fetching misskey blocks from domain:", domain)
1178 step = config["misskey_offset"]
1180 # iterating through all "suspended" (follow-only in its terminology)
1181 # instances page-by-page, since that troonware doesn't support
1182 # sending them all at once
1184 # DEBUG: print(f"DEBUG: Fetching offset='{offset}' from '{domain}' ...")
1186 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1187 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
1192 }), {"Origin": domain})
1194 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1195 fetched = post_json_api(domain, "/api/federation/instances", json.dumps({
1200 "offset" : offset - 1
1201 }), {"Origin": domain})
1203 # DEBUG: print("DEBUG: fetched():", len(fetched))
1204 if len(fetched) == 0:
1205 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
1207 elif len(fetched) != config["misskey_offset"]:
1208 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
1209 offset = offset + (config["misskey_offset"] - len(fetched))
1211 # DEBUG: print("DEBUG: Raising offset by step:", step)
1212 offset = offset + step
1214 for instance in fetched:
1216 if instance["isSuspended"]:
1217 blocks["suspended"].append(
1219 "domain": tidyup(instance["host"]),
1220 # no reason field, nothing
1225 except BaseException as e:
1226 print("WARNING: Caught error, exiting loop:", domain, e)
1227 update_last_error(domain, e)
1232 # same shit, different asshole ("blocked" aka full suspend)
1235 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1236 fetched = post_json_api(domain,"/api/federation/instances", json.dumps({
1241 }), {"Origin": domain})
1243 # DEBUG: print("DEBUG: Sending JSON API request to domain,step,offset:", domain, step, offset)
1244 fetched = post_json_api(domain,"/api/federation/instances", json.dumps({
1250 }), {"Origin": domain})
1252 # DEBUG: print("DEBUG: fetched():", len(fetched))
1253 if len(fetched) == 0:
1254 # DEBUG: print("DEBUG: Returned zero bytes, exiting loop:", domain)
1256 elif len(fetched) != config["misskey_offset"]:
1257 # DEBUG: print(f"DEBUG: Fetched '{len(fetched)}' row(s) but expected: '{config['misskey_offset']}'")
1258 offset = offset + (config["misskey_offset"] - len(fetched))
1260 # DEBUG: print("DEBUG: Raising offset by step:", step)
1261 offset = offset + step
1263 for instance in fetched:
1264 if instance["isBlocked"]:
1265 blocks["blocked"].append({
1266 "domain": tidyup(instance["host"]),
1270 except BaseException as e:
1271 print("ERROR: Exception during POST:", domain, e)
1272 update_last_error(domain, e)
1276 # DEBUG: print(f"DEBUG: Updating last_instance_fetch for domain='{domain}' ...")
1277 update_last_instance_fetch(domain)
1279 # DEBUG: print("DEBUG: Returning for domain,blocked(),suspended():", domain, len(blocks["blocked"]), len(blocks["suspended"]))
1281 "reject" : blocks["blocked"],
1282 "followers_only": blocks["suspended"]
1285 def tidyup(string: str) -> str:
1286 # some retards put their blocks in variable case
1287 string = string.lower().strip()
1289 # other retards put the port
1290 string = re.sub("\:\d+$", "", string)
1292 # bigger retards put the schema in their blocklist, sometimes even without slashes
1293 string = re.sub("^https?\:(\/*)", "", string)
1295 # and trailing slash
1296 string = re.sub("\/$", "", string)
1299 string = re.sub("^\@", "", string)
1301 # the biggest retards of them all try to block individual users
1302 string = re.sub("(.+)\@", "", string)