X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=fba%2Fcommands.py;h=3fb4ea6869ded2a25451493b1172fd5db88889bf;hb=6dfd4d714dee64c124a249a3a379e60023ebd3ea;hp=76525c3233aa4975da25f9f47c720dbf8cc412de;hpb=6041a75bcc5eb81f9a69281ee733a6a5d23072dc;p=fba.git diff --git a/fba/commands.py b/fba/commands.py index 76525c3..3fb4ea6 100644 --- a/fba/commands.py +++ b/fba/commands.py @@ -29,18 +29,21 @@ import markdown import reqto import validators -from fba import csrf from fba import database from fba import utils from fba.helpers import blacklist +from fba.helpers import blocklists from fba.helpers import config from fba.helpers import cookies +from fba.helpers import dicts as dict_helper +from fba.helpers import domain as domain_helper from fba.helpers import locking from fba.helpers import processing from fba.helpers import software as software_helper from fba.helpers import tidyup +from fba.http import csrf from fba.http import federation from fba.http import network @@ -60,6 +63,7 @@ logger = logging.getLogger(__name__) def check_instance(args: argparse.Namespace) -> int: logger.debug("args.domain='%s' - CALLED!", args.domain) + status = 0 if not validators.domain(args.domain): logger.warning("args.domain='%s' is not valid", args.domain) @@ -121,7 +125,7 @@ def fetch_pixelfed_api(args: argparse.Namespace) -> int: return list() try: - logger.debug("Fetching JSON from pixelfed.org API, headers()=%d ...", len(headers)) + logger.info("Fetching JSON from pixelfed.org API, headers()=%d ...", len(headers)) fetched = network.get_json_api( source_domain, "/api/v1/servers/all.json?scope=All&country=all&language=all", @@ -152,8 +156,8 @@ def fetch_pixelfed_api(args: argparse.Namespace) -> int: domain = row["domain"].encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif instances.is_registered(domain): logger.debug("domain='%s' is already registered - SKIPPED!", domain) @@ -223,8 +227,8 @@ def fetch_bkali(args: argparse.Namespace) -> int: elif entry["domain"] == "": logger.debug("entry[domain] is empty - SKIPPED!") continue - elif not utils.is_domain_wanted(entry["domain"]): - logger.warning("entry[domain]='%s' is not wanted - SKIPPED!", entry["domain"]) + elif not domain_helper.is_wanted(entry["domain"]): + logger.debug("entry[domain]='%s' is not wanted - SKIPPED!", entry["domain"]) continue elif instances.is_registered(entry["domain"]): logger.debug("entry[domain]='%s' is already registered - SKIPPED!", entry["domain"]) @@ -278,69 +282,76 @@ def fetch_blocks(args: argparse.Namespace) -> int: if args.domain is not None and args.domain != "": # Re-check single domain - logger.debug("Querying database for single args.domain='%s' ...", args.domain) + logger.debug("Querying database for args.domain='%s' ...", args.domain) database.cursor.execute( - "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE domain = ?", [args.domain] + "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE domain = ? LIMIT 1", [args.domain] ) elif args.software is not None and args.software != "": # Re-check single software logger.debug("Querying database for args.software='%s' ...", args.software) database.cursor.execute( - "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE software = ? AND nodeinfo_url IS NOT NULL", [args.software] + "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE software = ? AND nodeinfo_url IS NOT NULL ORDER BY total_blocks DESC, last_updated ASC", [args.software] + ) + elif args.force: + # Re-check all + logger.debug("Re-checking all instances ...") + database.cursor.execute( + "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE software IN ('pleroma', 'mastodon', 'lemmy', 'friendica', 'misskey') AND nodeinfo_url IS NOT NULL ORDER BY total_blocks DESC, last_updated ASC" ) else: # Re-check after "timeout" (aka. minimum interval) database.cursor.execute( - "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE software IN ('pleroma', 'mastodon', 'lemmy', 'friendica', 'misskey') AND (last_blocked IS NULL OR last_blocked < ?) AND nodeinfo_url IS NOT NULL ORDER BY rowid DESC", [time.time() - config.get("recheck_block")] + "SELECT domain, software, origin, nodeinfo_url FROM instances WHERE software IN ('pleroma', 'mastodon', 'lemmy', 'friendica', 'misskey') AND (last_blocked IS NULL OR last_blocked < ?) AND nodeinfo_url IS NOT NULL ORDER BY total_blocks DESC, last_updated ASC", [time.time() - config.get("recheck_block")] ) rows = database.cursor.fetchall() logger.info("Checking %d entries ...", len(rows)) for blocker, software, origin, nodeinfo_url in rows: logger.debug("blocker='%s',software='%s',origin='%s',nodeinfo_url='%s'", blocker, software, origin, nodeinfo_url) - blocker = tidyup.domain(blocker) - logger.debug("blocker='%s' - AFTER!", blocker) - if blocker == "": - logger.warning("blocker is now empty!") - continue - elif nodeinfo_url is None or nodeinfo_url == "": - logger.debug("blocker='%s',software='%s' has empty nodeinfo_url", blocker, software) - continue - elif not utils.is_domain_wanted(blocker): + if not domain_helper.is_wanted(blocker): logger.warning("blocker='%s' is not wanted - SKIPPED!", blocker) continue - logger.debug("blocker='%s'", blocker) + logger.debug("Setting last_blocked,has_obfuscation=false for blocker='%s' ...", blocker) instances.set_last_blocked(blocker) instances.set_has_obfuscation(blocker, False) - blocking = list() - if software == "pleroma": - logger.info("blocker='%s',software='%s'", blocker, software) - blocking = pleroma.fetch_blocks(blocker, nodeinfo_url) - elif software == "mastodon": - logger.info("blocker='%s',software='%s'", blocker, software) - blocking = mastodon.fetch_blocks(blocker, nodeinfo_url) - elif software == "lemmy": - logger.info("blocker='%s',software='%s'", blocker, software) - blocking = lemmy.fetch_blocks(blocker, nodeinfo_url) - elif software == "friendica": - logger.info("blocker='%s',software='%s'", blocker, software) - blocking = friendica.fetch_blocks(blocker) - elif software == "misskey": - logger.info("blocker='%s',software='%s'", blocker, software) - blocking = misskey.fetch_blocks(blocker) - else: - logger.warning("Unknown software: blocker='%s',software='%s'", blocker, software) + # c.s isn't part of oliphant's "hidden" blocklists + if blocker == "chaos.social" or blocklists.has(blocker): + logger.debug("Skipping blocker='%s', run ./fba.py fetch_cs or fetch_oliphant instead!", blocker) + continue - logger.debug("blocker='%s'", blocker) - if blocker != "chaos.social": - logger.debug("Invoking instances.set_total_blocks(%s, %d) ...", blocker, len(blocking)) - instances.set_total_blocks(blocker, blocking) + logger.debug("Invoking federation.fetch_blocks(%s) ...", blocker) + blocking = federation.fetch_blocks(blocker) + + logger.info("blocker='%s',software='%s' has %d block entries returned.", blocker, software, len(blocking)) + if len(blocking) == 0: + logger.debug("blocker='%s',software='%s' - fetching blocklist ...", blocker, software) + if software == "pleroma": + blocking = pleroma.fetch_blocks(blocker) + logger.debug("blocker='%s' returned %d entries,software='%s'", blocker, len(blocking), software) + elif software == "mastodon": + blocking = mastodon.fetch_blocks(blocker) + logger.debug("blocker='%s' returned %d entries,software='%s'", blocker, len(blocking), software) + elif software == "lemmy": + blocking = lemmy.fetch_blocks(blocker) + logger.debug("blocker='%s' returned %d entries,software='%s'", blocker, len(blocking), software) + elif software == "friendica": + blocking = friendica.fetch_blocks(blocker) + logger.debug("blocker='%s' returned %d entries,software='%s'", blocker, len(blocking), software) + elif software == "misskey": + blocking = misskey.fetch_blocks(blocker) + logger.debug("blocker='%s' returned %d entries,software='%s'", blocker, len(blocking), software) + else: + logger.warning("Unknown software: blocker='%s',software='%s'", blocker, software) + + logger.debug("Invoking instances.set_total_blocks(%s, %d) ...", blocker, len(blocking)) + instances.set_total_blocks(blocker, blocking) - logger.info("Checking %d entries from blocker='%s',software='%s' ...", len(blocking), blocker, software) blockdict = list() + + logger.info("Checking %d entries from blocker='%s',software='%s' ...", len(blocking), blocker, software) for block in blocking: logger.debug("blocked='%s',block_level='%s',reason='%s'", block["blocked"], block["block_level"], block["reason"]) @@ -405,8 +416,8 @@ def fetch_blocks(args: argparse.Namespace) -> int: block["blocked"] = block["blocked"].lstrip(".").encode("idna").decode("utf-8") logger.debug("block[blocked]='%s' - AFTER!", block["blocked"]) - if not utils.is_domain_wanted(block["blocked"]): - logger.warning("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) + if not domain_helper.is_wanted(block["blocked"]): + logger.debug("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) continue elif block["block_level"] in ["accept", "accepted"]: logger.debug("blocked='%s' is accepted, not wanted here - SKIPPED!", block["blocked"]) @@ -430,7 +441,7 @@ def fetch_blocks(args: argparse.Namespace) -> int: logger.debug("Checking if blocker='%s' has pending updates ...", blocker) if instances.has_pending(blocker): logger.debug("Flushing updates for blocker='%s' ...", blocker) - instances.update_data(blocker) + instances.update(blocker) logger.debug("Invoking commit() ...") database.connection.commit() @@ -533,15 +544,12 @@ def fetch_observer(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif instances.is_registered(domain): logger.debug("domain='%s' is already registered - SKIPPED!", domain) continue - elif instances.is_recent(domain): - logger.debug("domain='%s' is recently being handled - SKIPPED!", domain) - continue software = software_helper.alias(software) logger.info("Fetching instances for domain='%s'", domain) @@ -569,7 +577,12 @@ def fetch_todon_wiki(args: argparse.Namespace) -> int: "reject": list(), } - raw = utils.fetch_url(f"https://{source_domain}/todon/domainblocks", network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))).text + logger.debug("Fetching domainblocks from source_domain='%s'", source_domain) + raw = utils.fetch_url( + f"https://{source_domain}/todon/domainblocks", + network.web_headers, + (config.get("connection_timeout"), config.get("read_timeout")) + ).text logger.debug("raw()=%d,raw[]='%s'", len(raw), type(raw)) doc = bs4.BeautifulSoup(raw, "html.parser") @@ -587,6 +600,7 @@ def fetch_todon_wiki(args: argparse.Namespace) -> int: blocker = "todon.eu" logger.debug("Invoking instances.set_total_blocks(%s, %d) ...", blocker, len(blocking)) + instances.set_last_blocked(blocker) instances.set_total_blocks(blocker, blocking) blockdict = list() @@ -628,7 +642,7 @@ def fetch_todon_wiki(args: argparse.Namespace) -> int: logger.debug("Checking if blocker='%s' has pending updates ...", blocker) if instances.has_pending(blocker): logger.debug("Flushing updates for blocker='%s' ...", blocker) - instances.update_data(blocker) + instances.update(blocker) logger.debug("Success! - EXIT!") return 0 @@ -672,7 +686,12 @@ def fetch_cs(args: argparse.Namespace): logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) sources.update(source_domain) - raw = utils.fetch_url(f"https://{source_domain}/chaossocial/meta/master/federation.md", network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))).text + logger.info("Fetching federation.md from source_domain='%s' ...", source_domain) + raw = utils.fetch_url( + f"https://{source_domain}/chaossocial/meta/master/federation.md", + network.web_headers, + (config.get("connection_timeout"), config.get("read_timeout")) + ).text logger.debug("raw()=%d,raw[]='%s'", len(raw), type(raw)) doc = bs4.BeautifulSoup(markdown.markdown(raw, extensions=extensions), features="html.parser") @@ -690,6 +709,7 @@ def fetch_cs(args: argparse.Namespace): blocker = "chaos.social" logger.debug("Invoking instances.set_total_blocks(%s, %d) ...", blocker, len(blocking)) + instances.set_last_blocked(blocker) instances.set_total_blocks(blocker, blocking) logger.debug("blocklist[silenced]()=%d,blocklist[reject]()=%d", len(blocklist["silenced"]), len(blocklist["reject"])) @@ -729,7 +749,7 @@ def fetch_cs(args: argparse.Namespace): logger.debug("Checking if blocker='%s' has pending updates ...", blocker) if instances.has_pending(blocker): logger.debug("Flushing updates for blocker='%s' ...", blocker) - instances.update_data(blocker) + instances.update(blocker) logger.debug("Success! - EXIT!") return 0 @@ -755,13 +775,13 @@ def fetch_fba_rss(args: argparse.Namespace) -> int: response = utils.fetch_url(args.feed, network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))) logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text)) - if response.ok and response.status_code < 300 and len(response.text) > 0: + if response.ok and response.status_code == 200 and len(response.text) > 0: logger.debug("Parsing RSS feed (%d Bytes) ...", len(response.text)) rss = atoma.parse_rss_bytes(response.content) logger.debug("rss[]='%s'", type(rss)) for item in rss.items: - logger.debug("item='%s'", item) + logger.debug("item[%s]='%s'", type(item), item) domain = tidyup.domain(item.link.split("=")[1]) logger.debug("domain='%s' - AFTER!", domain) @@ -773,8 +793,8 @@ def fetch_fba_rss(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif domain in domains: logger.debug("domain='%s' is already added - SKIPPED!", domain) @@ -812,6 +832,14 @@ def fetch_fbabot_atom(args: argparse.Namespace) -> int: locking.acquire() source_domain = "ryona.agency" + feed = f"https://{source_domain}/users/fba/feed.atom" + + logger.debug("args.feed[%s]='%s'", type(args.feed), args.feed) + if args.feed is not None and validators.url(args.feed): + logger.debug("Setting feed='%s' ...", args.feed) + feed = str(args.feed) + source_domain = urlparse(args.feed).netloc + if sources.is_recent(source_domain): logger.info("API from source_domain='%s' has recently being accessed - EXIT!", source_domain) return 0 @@ -819,15 +847,13 @@ def fetch_fbabot_atom(args: argparse.Namespace) -> int: logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) sources.update(source_domain) - feed = f"https://{source_domain}/users/fba/feed.atom" - domains = list() logger.info("Fetching ATOM feed='%s' from FBA bot account ...", feed) response = utils.fetch_url(feed, network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))) logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text)) - if response.ok and response.status_code < 300 and len(response.text) > 0: + if response.ok and response.status_code == 200 and len(response.text) > 0: logger.debug("Parsing ATOM feed (%d Bytes) ...", len(response.text)) atom = atoma.parse_atom_bytes(response.content) @@ -851,8 +877,8 @@ def fetch_fbabot_atom(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif domain in domains: logger.debug("domain='%s' is already added - SKIPPED!", domain) @@ -897,14 +923,25 @@ def fetch_instances(args: argparse.Namespace) -> int: logger.debug("Invoking locking.acquire() ...") locking.acquire() + # Initialize values + domain = tidyup.domain(args.domain) + origin = software = None + + # Fetch record + database.cursor.execute("SELECT origin, software FROM instances WHERE domain = ? LIMIT 1", [args.domain]) + row = database.cursor.fetchone() + if row is not None: + origin = row["origin"] + software = row["software"] + # Initial fetch try: - logger.info("Fetching instances from args.domain='%s' ...", args.domain) - federation.fetch_instances(args.domain, None, None, inspect.currentframe().f_code.co_name) + logger.info("Fetching instances from args.domain='%s',origin='%s',software='%s' ...", domain, origin, software) + federation.fetch_instances(domain, origin, software, inspect.currentframe().f_code.co_name) except network.exceptions as exception: logger.warning("Exception '%s' during fetching instances (fetch_instances) from args.domain='%s'", type(exception), args.domain) instances.set_last_error(args.domain, exception) - instances.update_data(args.domain) + instances.update(args.domain) return 100 if args.single: @@ -913,7 +950,7 @@ def fetch_instances(args: argparse.Namespace) -> int: # Loop through some instances database.cursor.execute( - "SELECT domain, origin, software, nodeinfo_url FROM instances WHERE software IN ('pleroma', 'mastodon', 'friendica', 'misskey', 'lemmy', 'peertube', 'takahe', 'gotosocial', 'brighteon', 'wildebeest', 'bookwyrm') AND (last_instance_fetch IS NULL OR last_instance_fetch < ?) ORDER BY rowid DESC", [time.time() - config.get("recheck_instance")] + "SELECT domain, origin, software, nodeinfo_url FROM instances WHERE software IN ('pleroma', 'mastodon', 'friendica', 'misskey', 'lemmy', 'peertube', 'takahe', 'gotosocial', 'brighteon', 'wildebeest', 'bookwyrm', 'mitra', 'areionskey', 'mammuthus', 'neodb') AND (last_instance_fetch IS NULL OR last_instance_fetch < ?) ORDER BY total_peers DESC, last_updated ASC", [time.time() - config.get("recheck_instance")] ) rows = database.cursor.fetchall() @@ -928,8 +965,8 @@ def fetch_instances(args: argparse.Namespace) -> int: domain = row["domain"].encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("Domain domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("Domain domain='%s' is not wanted - SKIPPED!", domain) continue try: @@ -959,57 +996,10 @@ def fetch_oliphant(args: argparse.Namespace) -> int: # Base URL base_url = f"https://{source_domain}/oliphant/blocklists/raw/branch/main/blocklists" - # URLs to fetch - blocklists = ( - { - "blocker": "artisan.chat", - "csv_url": "mastodon/artisan.chat.csv", - },{ - "blocker": "mastodon.art", - "csv_url": "mastodon/mastodon.art.csv", - },{ - "blocker": "pleroma.envs.net", - "csv_url": "mastodon/pleroma.envs.net.csv", - },{ - "blocker": "oliphant.social", - "csv_url": "mastodon/_unified_tier3_blocklist.csv", - },{ - "blocker": "mastodon.online", - "csv_url": "mastodon/mastodon.online.csv", - },{ - "blocker": "mastodon.social", - "csv_url": "mastodon/mastodon.social.csv", - },{ - "blocker": "mastodon.social", - "csv_url": "other/missing-tier0-mastodon.social.csv", - },{ - "blocker": "rage.love", - "csv_url": "mastodon/rage.love.csv", - },{ - "blocker": "sunny.garden", - "csv_url": "mastodon/sunny.garden.csv", - },{ - "blocker": "sunny.garden", - "csv_url": "mastodon/gardenfence.csv", - },{ - "blocker": "solarpunk.moe", - "csv_url": "mastodon/solarpunk.moe.csv", - },{ - "blocker": "toot.wales", - "csv_url": "mastodon/toot.wales.csv", - },{ - "blocker": "union.place", - "csv_url": "mastodon/union.place.csv", - },{ - "blocker": "oliphant.social", - "csv_url": "mastodon/birdsite.csv", - } - ) - domains = list() - logger.debug("Downloading %d files ...", len(blocklists)) - for block in blocklists: + logger.debug("Downloading %d files ...", len(blocklists.oliphant_blocklists)) + for block in blocklists.oliphant_blocklists: # Is domain given and not equal blocker? if isinstance(args.domain, str) and args.domain != block["blocker"]: logger.debug("Skipping blocker='%s', not matching args.domain='%s'", block["blocker"], args.domain) @@ -1018,12 +1008,14 @@ def fetch_oliphant(args: argparse.Namespace) -> int: logger.debug("args.domain='%s' already handled - SKIPPED!", args.domain) continue + instances.set_last_blocked(block["blocker"]) + # Fetch this URL logger.info("Fetching csv_url='%s' for blocker='%s' ...", block["csv_url"], block["blocker"]) response = utils.fetch_url(f"{base_url}/{block['csv_url']}", network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))) logger.debug("response.ok='%s',response.status_code=%d,response.content()=%d", response.ok, response.status_code, len(response.content)) - if not response.ok or response.status_code >= 300 or response.content == "": + if not response.ok or response.status_code > 200 or response.content == "": logger.warning("Could not fetch csv_url='%s' for blocker='%s' - SKIPPED!", block["csv_url"], block["blocker"]) continue @@ -1089,6 +1081,9 @@ def fetch_oliphant(args: argparse.Namespace) -> int: elif blacklist.is_blacklisted(domain): logger.warning("domain='%s' is blacklisted - SKIPPED!", domain) continue + elif blocks.is_instance_blocked(block["blocker"], domain, severity): + logger.debug("block[blocker]='%s' has already blocked domain='%s' with severity='%s' - SKIPPED!", block["blocker"], domain, severity) + continue logger.debug("Marking domain='%s' as handled", domain) domains.append(domain) @@ -1110,14 +1105,14 @@ def fetch_oliphant(args: argparse.Namespace) -> int: processing.block(block["blocker"], domain, None, "reject_reports") logger.debug("block[blocker]='%s'", block["blocker"]) - if block["blocker"] != "chaos.social": + if not blocklists.has(block["blocker"]): logger.debug("Invoking instances.set_total_blocks(%s, domains()=%d) ...", block["blocker"], len(domains)) instances.set_total_blocks(block["blocker"], domains) logger.debug("Checking if blocker='%s' has pending updates ...", block["blocker"]) if instances.has_pending(block["blocker"]): logger.debug("Flushing updates for block[blocker]='%s' ...", block["blocker"]) - instances.update_data(block["blocker"]) + instances.update(block["blocker"]) logger.debug("Invoking commit() ...") database.connection.commit() @@ -1148,7 +1143,7 @@ def fetch_txt(args: argparse.Namespace) -> int: response = utils.fetch_url(row["url"], network.web_headers, (config.get("connection_timeout"), config.get("read_timeout"))) logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text)) - if response.ok and response.status_code < 300 and response.text != "": + if response.ok and response.status_code == 200 and response.text != "": logger.debug("Returned %d Bytes for processing", len(response.text.strip())) domains = response.text.split("\n") @@ -1161,8 +1156,8 @@ def fetch_txt(args: argparse.Namespace) -> int: if domain == "": logger.debug("domain is empty - SKIPPED!") continue - elif not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + elif not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif instances.is_recent(domain): logger.debug("domain='%s' has been recently crawled - SKIPPED!", domain) @@ -1193,6 +1188,7 @@ def fetch_fedipact(args: argparse.Namespace) -> int: logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) sources.update(source_domain) + logger.info("Fetching / from source_domain='%s' ...", source_domain) response = utils.fetch_url( f"https://{source_domain}", network.web_headers, @@ -1200,7 +1196,7 @@ def fetch_fedipact(args: argparse.Namespace) -> int: ) logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text)) - if response.ok and response.status_code < 300 and response.text != "": + if response.ok and response.status_code == 200 and response.text != "": logger.debug("Parsing %d Bytes ...", len(response.text)) doc = bs4.BeautifulSoup(response.text, "html.parser") @@ -1221,8 +1217,8 @@ def fetch_fedipact(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif instances.is_registered(domain): logger.debug("domain='%s' is already registered - SKIPPED!", domain) @@ -1232,7 +1228,103 @@ def fetch_fedipact(args: argparse.Namespace) -> int: continue logger.info("Fetching domain='%s' ...", domain) - federation.fetch_instances(domain, None, None, inspect.currentframe().f_code.co_name) + federation.fetch_instances(domain, "beach.city", None, inspect.currentframe().f_code.co_name) + + logger.debug("Success! - EXIT!") + return 0 + +def fetch_joinmobilizon(args: argparse.Namespace) -> int: + logger.debug("args[]='%s' - CALLED!", type(args)) + + logger.debug("Invoking locking.acquire() ...") + locking.acquire() + + source_domain = "instances.joinmobilizon.org" + if sources.is_recent(source_domain): + logger.info("API from source_domain='%s' has recently being accessed - EXIT!", source_domain) + return 0 + else: + logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) + sources.update(source_domain) + + logger.info("Fetching instances from source_domain='%s' ...", source_domain) + raw = utils.fetch_url( + f"https://{source_domain}/api/v1/instances", + network.web_headers, + (config.get("connection_timeout"), config.get("read_timeout")) + ).text + logger.debug("raw()=%d,raw[]='%s'", len(raw), type(raw)) + + parsed = json.loads(raw) + logger.debug("parsed[%s]()=%d", type(parsed), len(parsed)) + + if "data" not in parsed: + logger.warning("parsed()=%d does not contain key 'data'") + return 1 + + logger.info("Checking %d instances ...", len(parsed["data"])) + for row in parsed["data"]: + logger.debug("row[]='%s'", type(row)) + if "host" not in row: + logger.warning("row='%s' does not contain key 'host' - SKIPPED!", row) + continue + elif not domain_helper.is_wanted(row["host"]): + logger.debug("row[host]='%s' is not wanted - SKIPPED!", row["host"]) + continue + elif instances.is_registered(row["host"]): + logger.debug("row[host]='%s' is already registered - SKIPPED!", row["host"]) + continue + + logger.info("Fetching row[host]='%s' ...", row["host"]) + federation.fetch_instances(row["host"], "demo.mobilizon.org", None, inspect.currentframe().f_code.co_name) + + logger.debug("Success! - EXIT!") + return 0 + +def fetch_joinmisskey(args: argparse.Namespace) -> int: + logger.debug("args[]='%s' - CALLED!", type(args)) + + logger.debug("Invoking locking.acquire() ...") + locking.acquire() + + source_domain = "instanceapp.misskey.page" + if sources.is_recent(source_domain): + logger.info("API from source_domain='%s' has recently being accessed - EXIT!", source_domain) + return 0 + else: + logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) + sources.update(source_domain) + + logger.info("Fetching instances.json from source_domain='%s' ...", source_domain) + raw = utils.fetch_url( + f"https://{source_domain}/instances.json", + network.web_headers, + (config.get("connection_timeout"), config.get("read_timeout")) + ).text + logger.debug("raw()=%d,raw[]='%s'", len(raw), type(raw)) + + parsed = json.loads(raw) + logger.debug("parsed[%s]()=%d", type(parsed), len(parsed)) + + if "instancesInfos" not in parsed: + logger.warning("parsed()=%d does not contain element 'instancesInfos'") + return 1 + + logger.info("Checking %d instane(s) ...", len(parsed["instancesInfos"])) + for row in parsed["instancesInfos"]: + logger.debug("row[%s]='%s'", type(row), row) + if "url" not in row: + logger.warning("row()=%d does not have element 'url' - SKIPPED!", len(row)) + continue + elif not domain_helper.is_wanted(row["url"]): + logger.debug("row[url]='%s' is not wanted - SKIPPED!", row["url"]) + continue + elif instances.is_registered(row["url"]): + logger.debug("row[url]='%s' is already registered - SKIPPED!", row["url"]) + continue + + logger.info("Fetching row[url]='%s' ...", row["url"]) + federation.fetch_instances(row["url"], "misskey.io", None, inspect.currentframe().f_code.co_name) logger.debug("Success! - EXIT!") return 0 @@ -1251,6 +1343,7 @@ def fetch_joinfediverse(args: argparse.Namespace) -> int: logger.debug("source_domain='%s' has not been recently used, marking ...", source_domain) sources.update(source_domain) + logger.info("Fetching /FediBlock wiki page from source_domain='%s' ...", source_domain) raw = utils.fetch_url( f"https://{source_domain}/FediBlock", network.web_headers, @@ -1364,20 +1457,21 @@ def fetch_joinfediverse(args: argparse.Namespace) -> int: if block["blocked"] == "": logger.debug("block[blocked] is empty - SKIPPED!") continue - elif not utils.is_domain_wanted(block["blocked"]): - logger.warning("block[blocked]='%s' is not wanted - SKIPPED!", block["blocked"]) + elif not domain_helper.is_wanted(block["blocked"]): + logger.debug("block[blocked]='%s' is not wanted - SKIPPED!", block["blocked"]) continue elif instances.is_recent(block["blocked"]): logger.debug("block[blocked]='%s' has been recently checked - SKIPPED!", block["blocked"]) continue - logger.info("Proccessing blocked='%s' ...", block["blocked"]) + logger.debug("Proccessing blocked='%s' ...", block["blocked"]) processing.domain(block["blocked"], "climatejustice.social", inspect.currentframe().f_code.co_name) blockdict = list() for blocker in domains: blocker = blocker[0] logger.debug("blocker[%s]='%s'", type(blocker), blocker) + instances.set_last_blocked(blocker) for block in blocking: logger.debug("block[blocked]='%s',block[block reason(s)]='%s' - BEFORE!", block["blocked"], block["block reason(s)"] if "block reason(s)" in block else None) @@ -1387,8 +1481,8 @@ def fetch_joinfediverse(args: argparse.Namespace) -> int: if block["blocked"] == "": logger.debug("block[blocked] is empty - SKIPPED!") continue - elif not utils.is_domain_wanted(block["blocked"]): - logger.warning("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) + elif not domain_helper.is_wanted(block["blocked"]): + logger.debug("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) continue logger.debug("blocked='%s',reason='%s'", block["blocked"], block["reason"]) @@ -1401,7 +1495,7 @@ def fetch_joinfediverse(args: argparse.Namespace) -> int: if instances.has_pending(blocker): logger.debug("Flushing updates for blocker='%s' ...", blocker) - instances.update_data(blocker) + instances.update(blocker) logger.debug("Invoking commit() ...") database.connection.commit() @@ -1420,7 +1514,7 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: logger.debug("Invoking locking.acquire() ...") locking.acquire() - if isinstance(args.domain, str) and args.domain != "" and utils.is_domain_wanted(args.domain): + if isinstance(args.domain, str) and args.domain != "" and domain_helper.is_wanted(args.domain): database.cursor.execute("SELECT domain, software, nodeinfo_url FROM instances WHERE has_obfuscation = 1 AND domain = ?", [args.domain]) elif isinstance(args.software, str) and args.software != "" and validators.domain(args.software) == args.software: database.cursor.execute("SELECT domain, software, nodeinfo_url FROM instances WHERE has_obfuscation = 1 AND software = ?", [args.software]) @@ -1431,32 +1525,38 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: logger.info("Checking %d domains ...", len(rows)) for row in rows: logger.debug("Fetching peers from domain='%s',software='%s',nodeinfo_url='%s' ...", row["domain"], row["software"], row["nodeinfo_url"]) - if (args.all is None or not args.all) and instances.is_recent(row["domain"]) and args.domain is None and args.software is None: - logger.debug("row[domain]='%s' has been recently checked, args.all[]='%s' - SKIPPED!", row["domain"], type(args.all)) + if (args.force is None or not args.force) and args.domain is None and args.software is None and instances.is_recent(row["domain"], "last_blocked"): + logger.debug("row[domain]='%s' has been recently checked, args.force[]='%s' - SKIPPED!", row["domain"], type(args.force)) continue - blocking = list() - if row["software"] == "pleroma": - logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) - blocking = pleroma.fetch_blocks(row["domain"], row["nodeinfo_url"]) - elif row["software"] == "mastodon": - logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) - blocking = mastodon.fetch_blocks(row["domain"], row["nodeinfo_url"]) - elif row["software"] == "lemmy": - logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) - blocking = lemmy.fetch_blocks(row["domain"], row["nodeinfo_url"]) - elif row["software"] == "friendica": - logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) - blocking = friendica.fetch_blocks(row["domain"]) - elif row["software"] == "misskey": - logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) - blocking = misskey.fetch_blocks(row["domain"]) - else: - logger.warning("Unknown sofware: domain='%s',software='%s'", row["domain"], row["software"]) + logger.debug("Invoking federation.fetch_blocks(%s) ...", row["domain"]) + blocking = federation.fetch_blocks(row["domain"]) + + logger.debug("blocking()=%d", len(blocking)) + if len(blocking) == 0: + if row["software"] == "pleroma": + logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) + blocking = pleroma.fetch_blocks(row["domain"]) + elif row["software"] == "mastodon": + logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) + blocking = mastodon.fetch_blocks(row["domain"]) + elif row["software"] == "lemmy": + logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) + blocking = lemmy.fetch_blocks(row["domain"]) + elif row["software"] == "friendica": + logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) + blocking = friendica.fetch_blocks(row["domain"]) + elif row["software"] == "misskey": + logger.debug("domain='%s',software='%s'", row["domain"], row["software"]) + blocking = misskey.fetch_blocks(row["domain"]) + else: + logger.warning("Unknown software: domain='%s',software='%s'", row["domain"], row["software"]) + # c.s isn't part of oliphant's "hidden" blocklists logger.debug("row[domain]='%s'", row["domain"]) - if row["domain"] != "chaos.social": + if row["domain"] != "chaos.social" and not blocklists.has(row["domain"]): logger.debug("Invoking instances.set_total_blocks(%s, %d) ...", row["domain"], len(blocking)) + instances.set_last_blocked(row["domain"]) instances.set_total_blocks(row["domain"], blocking) obfuscated = 0 @@ -1483,8 +1583,8 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: logger.debug("block='%s' is obfuscated.", block["blocked"]) obfuscated = obfuscated + 1 blocked = utils.deobfuscate(block["blocked"], row["domain"], block["hash"] if "hash" in block else None) - elif not utils.is_domain_wanted(block["blocked"]): - logger.warning("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) + elif not domain_helper.is_wanted(block["blocked"]): + logger.debug("blocked='%s' is not wanted - SKIPPED!", block["blocked"]) continue elif blocks.is_instance_blocked(row["domain"], block["blocked"]): logger.debug("blocked='%s' is already blocked - SKIPPED!", block["blocked"]) @@ -1494,9 +1594,13 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: if blocked is not None and blocked != block["blocked"]: logger.debug("blocked='%s' was deobfuscated to blocked='%s'", block["blocked"], blocked) obfuscated = obfuscated - 1 + if blocks.is_instance_blocked(row["domain"], blocked): logger.debug("blocked='%s' is already blocked by domain='%s' - SKIPPED!", blocked, row["domain"]) continue + elif blacklist.is_blacklisted(blocked): + logger.debug("blocked='%s' is blacklisted - SKIPPED!", blocked) + continue block["block_level"] = blocks.alias_block_level(block["block_level"]) @@ -1508,6 +1612,9 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: "reason" : block["reason"], }) + logger.debug("Settings obfuscated=%d for row[domain]='%s' ...", obfuscated, row["domain"]) + instances.set_obfuscated_blocks(row["domain"], obfuscated) + logger.info("domain='%s' has %d obfuscated domain(s)", row["domain"], obfuscated) if obfuscated == 0 and len(blocking) > 0: logger.info("Block list from domain='%s' has been fully deobfuscated.", row["domain"]) @@ -1515,7 +1622,7 @@ def recheck_obfuscation(args: argparse.Namespace) -> int: if instances.has_pending(row["domain"]): logger.debug("Flushing updates for blocker='%s' ...", row["domain"]) - instances.update_data(row["domain"]) + instances.update(row["domain"]) logger.debug("Invoking commit() ...") database.connection.commit() @@ -1556,14 +1663,21 @@ def fetch_fedilist(args: argparse.Namespace) -> int: ) logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text)) - if not response.ok or response.status_code >= 300 or len(response.content) == 0: + if not response.ok or response.status_code > 200 or len(response.content) == 0: logger.warning("Failed fetching url='%s': response.ok='%s',response.status_code=%d,response.content()=%d - EXIT!", url, response.ok, response.status_code, len(response.text)) return 1 reader = csv.DictReader(response.content.decode("utf-8").splitlines(), dialect="unix") logger.debug("reader[]='%s'", type(reader)) - for row in reader: + if reader is None: + logger.warning("Failed parsing response.content()=%d as CSV content", len(response.content)) + return 2 + + rows = list(reader) + + logger.info("Checking %d rows ...", len(rows)) + for row in rows: logger.debug("row[]='%s'", type(row)) if "hostname" not in row: logger.warning("row()=%d has no element 'hostname' - SKIPPED!", len(row)) @@ -1581,11 +1695,11 @@ def fetch_fedilist(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue - elif (args.all is None or not args.all) and instances.is_registered(domain): - logger.debug("domain='%s' is already registered, --all not specified: args.all[]='%s'", domain, type(args.all)) + elif (args.force is None or not args.force) and instances.is_registered(domain): + logger.debug("domain='%s' is already registered, --force not specified: args.force[]='%s'", domain, type(args.force)) continue elif instances.is_recent(domain): logger.debug("domain='%s' has been recently crawled - SKIPPED!", domain) @@ -1608,7 +1722,13 @@ def update_nodeinfo(args: argparse.Namespace) -> int: database.cursor.execute("SELECT domain, software FROM instances WHERE domain = ?", [args.domain]) elif args.software is not None and args.software != "": logger.info("Fetching domains for args.software='%s'", args.software) - database.cursor.execute("SELECT domain, software FROM instances WHERE software = ?", [args.software]) + database.cursor.execute("SELECT domain, software FROM instances WHERE software = ? AND (last_nodeinfo < ? OR last_nodeinfo IS NULL)", [args.software.lower(), time.time() - config.get("recheck_nodeinfo")]) + elif args.mode is not None and args.mode != "": + logger.info("Fetching domains for args.mode='%s'", args.mode.upper()) + database.cursor.execute("SELECT domain, software FROM instances WHERE detection_mode = ? AND (last_nodeinfo < ? OR last_nodeinfo IS NULL)", [args.mode.upper(), time.time() - config.get("recheck_nodeinfo")]) + elif args.no_software: + logger.info("Fetching domains with no software type detected ...") + database.cursor.execute("SELECT domain, software FROM instances WHERE software IS NULL AND (last_nodeinfo < ? OR last_nodeinfo IS NULL)", [time.time() - config.get("recheck_nodeinfo")]) else: logger.info("Fetching domains for recently updated ...") database.cursor.execute("SELECT domain, software FROM instances WHERE last_nodeinfo < ? OR last_nodeinfo IS NULL", [time.time() - config.get("recheck_nodeinfo")]) @@ -1619,22 +1739,33 @@ def update_nodeinfo(args: argparse.Namespace) -> int: cnt = 0 for row in domains: logger.debug("row[]='%s'", type(row)) + if not args.force and instances.is_recent(row["domain"], "last_nodeinfo"): + logger.debug("row[domain]='%s' has been recently checked - SKIPPED!", row["domain"]) + continue + try: logger.info("Checking nodeinfo for row[domain]='%s',row[software]='%s' (%s%%) ...", row["domain"], row["software"], "{:5.1f}".format(cnt / len(domains) * 100)) software = federation.determine_software(row["domain"]) logger.debug("Determined software='%s'", software) if (software != row["software"] and software is not None) or args.force is True: + logger.debug("software='%s'", software) + if software is None: + logger.debug("Setting nodeinfo_url to 'None' for row[domain]='%s' ...", row["domain"]) + instances.set_nodeinfo_url(row["domain"], None) + logger.warning("Software type for row[domain]='%s' has changed from '%s' to '%s'!", row["domain"], row["software"], software) instances.set_software(row["domain"], software) - instances.set_success(row["domain"]) + if software is not None: + logger.debug("Setting row[domain]='%s' as successfully determined ...", row["domain"]) + instances.set_success(row["domain"]) except network.exceptions as exception: logger.warning("Exception '%s' during updating nodeinfo for row[domain]='%s'", type(exception), row["domain"]) instances.set_last_error(row["domain"], exception) instances.set_last_nodeinfo(row["domain"]) - instances.update_data(row["domain"]) + instances.update(row["domain"]) cnt = cnt + 1 logger.debug("Success! - EXIT!") @@ -1662,6 +1793,7 @@ def fetch_instances_social(args: argparse.Namespace) -> int: "Authorization": f"Bearer {config.get('instances_social_api_key')}", } + logger.info("Fetching list from source_domain='%s' ...", source_domain) fetched = network.get_json_api( source_domain, "/api/1.0/instances/list?count=0&sort_by=name", @@ -1700,8 +1832,8 @@ def fetch_instances_social(args: argparse.Namespace) -> int: domain = domain.encode("idna").decode("utf-8") logger.debug("domain='%s' - AFTER!", domain) - if not utils.is_domain_wanted(domain): - logger.warning("domain='%s' is not wanted - SKIPPED!", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) continue elif domain in domains: logger.debug("domain='%s' is already added - SKIPPED!", domain) @@ -1719,6 +1851,162 @@ def fetch_instances_social(args: argparse.Namespace) -> int: logger.debug("Success! - EXIT!") return 0 +def fetch_relays(args: argparse.Namespace) -> int: + logger.debug("args[]='%s' - CALLED!", type(args)) + + logger.debug("Invoking locking.acquire() ...") + locking.acquire() + + if args.domain is not None and args.domain != "": + database.cursor.execute("SELECT domain, software FROM instances WHERE software IN ('activityrelay', 'aoderelay', 'selective-relay') AND domain = ? LIMIT 1", [args.domain]) + else: + database.cursor.execute("SELECT domain, software FROM instances WHERE software IN ('activityrelay', 'aoderelay', 'selective-relay')") + + domains = list() + rows = database.cursor.fetchall() + + logger.info("Checking %d relays ...", len(rows)) + for row in rows: + logger.debug("row[domain]='%s',row[software]='%s' ...", row["domain"], row["software"]) + peers = list() + if not args.force and instances.is_recent(row["domain"]): + logger.debug("row[domain]='%s' has been recently fetched - SKIPPED!", row["domain"]) + continue + + try: + logger.info("Fetching / from relay row[domain]='%s',row[software]='%s' ...", row["domain"], row["software"]) + raw = utils.fetch_url( + f"https://{row['domain']}", + network.web_headers, + (config.get("connection_timeout"), config.get("read_timeout")) + ).text + logger.debug("raw[%s]()=%d", type(raw), len(raw)) + except network.exceptions as exception: + logger.warning("Exception '%s' during fetching from relay '%s': '%s'", type(exception), row["domain"], str(exception)) + instances.set_last_error(row["domain"], exception) + instances.set_last_instance_fetch(row["domain"]) + instances.update(row["domain"]) + continue + + doc = bs4.BeautifulSoup(raw, features="html.parser") + logger.debug("doc[]='%s'", type(doc)) + + logger.debug("row[software]='%s'", row["software"]) + if row["software"] == "activityrelay": + logger.debug("Checking row[domain]='%s' ...", row["domain"]) + tags = doc.findAll("p") + + logger.debug("Checking %d paragraphs ...", len(tags)) + for tag in tags: + logger.debug("tag[]='%s'", type(tag)) + if len(tag.contents) == 0: + logger.debug("tag='%s' is an empty tag - SKIPPED!", tag) + continue + elif "registered instances" not in tag.contents[0]: + logger.debug("Skipping paragraph, text not found.") + continue + + logger.debug("Found tag.contents[0][]='%s'", tag.contents[0]) + for domain in tag.contents: + logger.debug("domain[%s]='%s'", type(domain), domain) + if not isinstance(domain, bs4.element.NavigableString) or "registered instances" in domain: + continue + + domain = str(domain) + logger.debug("domain='%s'", domain) + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) + continue + + logger.debug("domain='%s' - BEFORE!", domain) + domain = tidyup.domain(domain) + logger.debug("domain='%s' - AFTER!", domain) + + if domain == "": + logger.debug("Empty domain after tidyup.domain() from origin='%s' - SKIPPED!", row["domain"]) + continue + elif domain not in peers: + logger.debug("Appending domain='%s' to peers list for relay='%s' ...", domain, row["domain"]) + peers.append(domain) + + if dict_helper.has_key(domains, "domain", domain): + logger.debug("domain='%s' already added", domain) + continue + + logger.debug("Appending domain='%s',origin='%s',software='%s' ...", domain, row["domain"], row["software"]) + domains.append({ + "domain": domain, + "origin": row["domain"], + }) + elif row["software"] in ["aoderelay", "selective-relay"]: + logger.debug("Checking row[domain]='%s' ...", row["domain"]) + if row["software"] == "aoderelay": + tags = doc.findAll("section", {"class": "instance"}) + else: + tags = doc.find("div", {"id": "instances"}).findAll("li") + + logger.debug("Checking %d tags ...", len(tags)) + for tag in tags: + logger.debug("tag[]='%s'", type(tag)) + + link = tag.find("a") + logger.debug("link[%s]='%s'", type(link), link) + if link is None: + logger.warning("tag='%s' has no a-tag ...", tag) + continue + + components = urlparse(link["href"]) + domain = components.netloc.lower() + + if not domain_helper.is_wanted(domain): + logger.debug("domain='%s' is not wanted - SKIPPED!", domain) + continue + + logger.debug("domain='%s' - BEFORE!", domain) + domain = tidyup.domain(domain) + logger.debug("domain='%s' - AFTER!", domain) + + if domain == "": + logger.debug("Empty domain after tidyup.domain() from origin='%s' - SKIPPED!", row["domain"]) + continue + elif domain not in peers: + logger.debug("Appending domain='%s' to peers list for relay='%s' ...", domain, row["domain"]) + peers.append(domain) + + if dict_helper.has_key(domains, "domain", domain): + logger.debug("domain='%s' already added", domain) + continue + + logger.debug("Appending domain='%s',origin='%s',software='%s'", domain, row["domain"], row["software"]) + domains.append({ + "domain": domain, + "origin": row["domain"], + }) + else: + logger.warning("row[domain]='%s',row[software]='%s' is not supported", row["domain"], row["software"]) + + logger.debug("Updating last_instance_fetch for row[domain]='%s' ...", row["domain"]) + instances.set_last_instance_fetch(row["domain"]) + + logger.info("Relay '%s' has %d peer(s) registered.", row["domain"], len(peers)) + instances.set_total_peers(row["domain"], peers) + + logger.debug("Flushing data for row[domain]='%s'", row["domain"]) + instances.update(row["domain"]) + + logger.info("Checking %d domains ...", len(domains)) + for row in domains: + logger.debug("row[domain]='%s',row[origin]='%s'", row["domain"], row["origin"]) + if instances.is_registered(row["domain"]): + logger.debug("row[domain]='%s' is already registered - SKIPPED!", row["domain"]) + continue + + logger.info("Fetching row[domain]='%s',row[origin]='%s' ...", row["domain"], row["origin"]) + federation.fetch_instances(row["domain"], row["origin"], None, inspect.currentframe().f_code.co_name) + + logger.debug("Success! - EXIT!") + return 0 + def convert_idna(args: argparse.Namespace) -> int: logger.debug("args[]='%s' - CALLED!", type(args)) @@ -1748,3 +2036,29 @@ def convert_idna(args: argparse.Namespace) -> int: logger.debug("Success! - EXIT!") return 0 + +def remove_invalid(args: argparse.Namespace) -> int: + logger.debug("args[]='%s' - CALLED!", type(args)) + + logger.debug("Invoking locking.acquire() ...") + locking.acquire() + + database.cursor.execute("SELECT domain FROM instances ORDER BY domain ASC") + rows = database.cursor.fetchall() + + logger.info("Checking %d domains ...", len(rows)) + for row in rows: + logger.debug("row[domain]='%s'", row["domain"]) + if not validators.domain(row["domain"].split("/")[0]): + logger.info("Invalid row[domain]='%s' found, removing ...", row["domain"]) + database.cursor.execute("DELETE FROM blocks WHERE blocker = ? OR blocked = ?", [row["domain"], row["domain"]]) + database.cursor.execute("DELETE FROM instances WHERE domain = ? LIMIT 1", [row["domain"]]) + + logger.debug("Invoking commit() ...") + database.connection.commit() + + logger.info("Vaccum cleaning database ...") + database.cursor.execute("VACUUM") + + logger.debug("Success! - EXIT!") + return 0