# Main packages:
'boot',
'commands',
- 'csrf',
'database',
'utils',
# Sub packages:
import reqto
import validators
-from fba import csrf
from fba import database
from fba import utils
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
for blocker, software, origin, nodeinfo_url in rows:
logger.debug("blocker='%s',software='%s',origin='%s',nodeinfo_url='%s'", blocker, software, origin, nodeinfo_url)
- if nodeinfo_url is None:
- logger.debug("blocker='%s',software='%s' has no nodeinfo_url set - SKIPPED!", blocker, software)
- continue
- elif not domain_helper.is_wanted(blocker):
+ if not domain_helper.is_wanted(blocker):
logger.warning("blocker='%s' is not wanted - SKIPPED!", blocker)
continue
instances.set_last_blocked(blocker)
instances.set_has_obfuscation(blocker, False)
- blocking = list()
-
# c.s isn't part of oliphant's "hidden" blocklists
- logger.debug("blocker='%s'", blocker)
- if blocker != "chaos.social" and not blocklists.is_excluded(blocker):
+ 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("Invoking federation.fetch_blocks(%s) ...", blocker)
+ blocking = federation.fetch_blocks(blocker)
+
+ logger.debug("blocking()=%d,nodeinfo_url='%s'", len(blocking), nodeinfo_url)
+ if len(blocking) == 0:
logger.debug("blocker='%s',software='%s'", blocker, software)
if software == "pleroma":
logger.info("blocker='%s',software='%s'", blocker, 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)
- else:
- logger.debug("Skipping blocker='%s', run ./fba.py fetch_cs or fetch_oliphant instead!", blocker)
+ 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()
processing.block(block["blocker"], domain, None, "reject_reports")
logger.debug("block[blocker]='%s'", block["blocker"])
- if not blocklists.is_excluded(block["blocker"]):
+ 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("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 software: 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"], 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 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" and not blocklists.is_excluded(row["domain"]):
+ 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)
+++ /dev/null
-# Fedi API Block - An aggregator for fetching blocking data from fediverse nodes
-# Copyright (C) 2023 Free Software Foundation
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published
-# by the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program. If not, see <https://www.gnu.org/licenses/>.
-
-import logging
-
-import bs4
-import reqto
-import requests
-
-from fba.helpers import config
-from fba.helpers import cookies
-from fba.helpers import domain as domain_helper
-
-from fba.http import network
-
-from fba.models import instances
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-def determine(domain: str, headers: dict) -> dict:
- logger.debug("domain='%s',headers()=%d - CALLED!", domain, len(headers))
- domain_helper.raise_on(domain)
-
- if not isinstance(headers, dict):
- raise ValueError(f"Parameter headers[]='{type(headers)}' is not of type 'dict'")
-
- # Default headers with no CSRF
- reqheaders = headers
-
- # Fetch / to check for meta tag indicating csrf
- logger.debug("Fetching / from domain='%s' for CSRF check ...", domain)
- response = reqto.get(
- f"https://{domain}/",
- headers=network.web_headers,
- timeout=(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 == 200 and response.text.strip() != "" and response.text.find("<html") > 0 and domain_helper.is_in_url(domain, response.url):
- # Save cookies
- logger.debug("Parsing response.text()=%d Bytes ...", len(response.text))
- cookies.store(domain, response.cookies.get_dict())
-
- # Parse text
- meta = bs4.BeautifulSoup(
- response.text,
- "html.parser"
- )
- logger.debug("meta[]='%s'", type(meta))
- tag = meta.find("meta", attrs={"name": "csrf-token"})
-
- logger.debug("tag[%s]='%s'", type(tag), tag)
- if tag is not None:
- logger.debug("Adding CSRF token='%s' for domain='%s'", tag["content"], domain)
- reqheaders["X-CSRF-Token"] = tag["content"]
- elif not domain_helper.is_in_url(domain, response.url):
- logger.warning("domain='%s' doesn't match with response.url='%s', maybe redirect to other domain?", domain, response.url)
- message = f"Redirect from domain='{domain}' to response.url='{response.url}'"
- instances.set_last_error(domain, message)
- raise requests.exceptions.TooManyRedirects(message)
-
- logger.debug("reqheaders()=%d - EXIT!", len(reqheaders))
- return reqheaders
}
)
-def is_excluded(domain: str) -> bool:
+def has(domain: str) -> bool:
logger.debug("domain='%s' - CALLED!")
domain_helper.raise_on(domain)
- # Default is not excluded
- excluded = False
+ # Default is not found
+ found = False
for row in oliphant_blocklists:
logger.debug("row[blocker]='%s',domain='%s'", row["blocker"], domain)
if row["blocker"] == domain:
- excluded = True
- logger.debug("domain='%s' is excluded from regular fetch_blocks command - BREAK!", domain)
+ found = True
+ logger.debug("domain='%s' is found and excluded from regular fetch_blocks command - BREAK!", domain)
break
- logger.debug("excluded='%s' - EXIT!")
- return excluded
+ logger.debug("found='%s' - EXIT!", found)
+ return found
# along with this program. If not, see <https://www.gnu.org/licenses/>.
__all__ = [
+ 'csrf',
'federation',
'network',
'nodeinfo',
--- /dev/null
+# Fedi API Block - An aggregator for fetching blocking data from fediverse nodes
+# Copyright (C) 2023 Free Software Foundation
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+
+import logging
+
+import bs4
+import reqto
+import requests
+
+from fba.helpers import config
+from fba.helpers import cookies
+from fba.helpers import domain as domain_helper
+
+from fba.http import network
+
+from fba.models import instances
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def determine(domain: str, headers: dict) -> dict:
+ logger.debug("domain='%s',headers()=%d - CALLED!", domain, len(headers))
+ domain_helper.raise_on(domain)
+
+ if not isinstance(headers, dict):
+ raise ValueError(f"Parameter headers[]='{type(headers)}' is not of type 'dict'")
+
+ # Default headers with no CSRF
+ reqheaders = headers
+
+ # Fetch / to check for meta tag indicating csrf
+ logger.debug("Fetching / from domain='%s' for CSRF check ...", domain)
+ response = reqto.get(
+ f"https://{domain}/",
+ headers=network.web_headers,
+ timeout=(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 == 200 and response.text.strip() != "" and response.text.find("<html") > 0 and domain_helper.is_in_url(domain, response.url):
+ # Save cookies
+ logger.debug("Parsing response.text()=%d Bytes ...", len(response.text))
+ cookies.store(domain, response.cookies.get_dict())
+
+ # Parse text
+ meta = bs4.BeautifulSoup(
+ response.text,
+ "html.parser"
+ )
+ logger.debug("meta[]='%s'", type(meta))
+ tag = meta.find("meta", attrs={"name": "csrf-token"})
+
+ logger.debug("tag[%s]='%s'", type(tag), tag)
+ if tag is not None:
+ logger.debug("Adding CSRF token='%s' for domain='%s'", tag["content"], domain)
+ reqheaders["X-CSRF-Token"] = tag["content"]
+ elif not domain_helper.is_in_url(domain, response.url):
+ logger.warning("domain='%s' doesn't match with response.url='%s', maybe redirect to other domain?", domain, response.url)
+ message = f"Redirect from domain='{domain}' to response.url='{response.url}'"
+ instances.set_last_error(domain, message)
+ raise requests.exceptions.TooManyRedirects(message)
+
+ logger.debug("reqheaders()=%d - EXIT!", len(reqheaders))
+ return reqheaders
import requests
import validators
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import cookies
from fba.helpers import domain as domain_helper
from fba.helpers import tidyup
from fba.helpers import version
+from fba.http import csrf
from fba.http import network
from fba.http import nodeinfo
+from fba.models import blocks
from fba.models import instances
from fba.networks import lemmy
logger.debug("peers()=%d - EXIT!", len(peers))
return peers
+
+def fetch_blocks(domain: str) -> list:
+ logger.debug("domain='%s' - CALLED!", domain)
+ domain_helper.raise_on(domain)
+
+ # Init block list
+ blocklist = list()
+
+ # No CSRF by default, you don't have to add network.api_headers by yourself here
+ headers = tuple()
+
+ try:
+ logger.debug("Checking CSRF for domain='%s'", domain)
+ headers = csrf.determine(domain, dict())
+ except network.exceptions as exception:
+ logger.warning("Exception '%s' during checking CSRF (fetch_blocks,%s)", type(exception), __name__)
+ instances.set_last_error(domain, exception)
+
+ logger.debug("Returning empty list ... - EXIT!")
+ return list()
+
+ try:
+ # json endpoint for newer mastodongs
+ logger.debug("Querying API domain_blocks: domain='%s'", domain)
+ data = network.get_json_api(
+ domain,
+ "/api/v1/instance/domain_blocks",
+ headers,
+ (config.get("connection_timeout"), config.get("read_timeout"))
+ )
+ rows = list()
+
+ logger.debug("data[]='%s'", type(data))
+ if "error_message" in data:
+ logger.debug("Was not able to fetch domain_blocks from domain='%s': status_code=%d,error_message='%s'", domain, data['status_code'], data['error_message'])
+ instances.set_last_error(domain, data)
+ return blocklist
+ elif "json" in data and "error" in data["json"]:
+ logger.warning("JSON API returned error message: '%s'", data["json"]["error"])
+ instances.set_last_error(domain, data)
+ return blocklist
+ else:
+ # Getting blocklist
+ rows = data["json"]
+
+ logger.debug("Marking domain='%s' as successfully handled ...", domain)
+ instances.set_success(domain)
+
+ logger.debug("rows[%s]()=%d", type(rows), len(rows))
+ if len(rows) > 0:
+ logger.debug("Checking %d entries from domain='%s' ...", len(rows), domain)
+ for block in rows:
+ # Check type
+ logger.debug("block[]='%s'", type(block))
+ if not isinstance(block, dict):
+ logger.debug("block[]='%s' is of type 'dict' - SKIPPED!", type(block))
+ continue
+ elif "domain" not in block:
+ logger.warning("block()=%d does not contain element 'domain' - SKIPPED!", len(block))
+ continue
+ elif "severity" not in block:
+ logger.warning("block()=%d does not contain element 'severity' - SKIPPED!", len(block))
+ continue
+ elif block["severity"] in ["accept", "accepted"]:
+ logger.debug("block[domain]='%s' has unwanted severity level '%s' - SKIPPED!", block["domain"], block["severity"])
+ continue
+ elif "digest" in block and not validators.hashes.sha256(block["digest"]):
+ logger.warning("block[domain]='%s' has invalid block[digest]='%s' - SKIPPED!", block["domain"], block["digest"])
+ continue
+
+ reason = tidyup.reason(block["comment"]) if "comment" in block and block["comment"] is not None and block["comment"] != "" else None
+
+ logger.debug("Appending blocker='%s',blocked='%s',reason='%s',block_level='%s'", domain, block["domain"], reason, block["severity"])
+ blocklist.append({
+ "blocker" : domain,
+ "blocked" : block["domain"],
+ "hash" : block["digest"] if "digest" in block else None,
+ "reason" : reason,
+ "block_level": blocks.alias_block_level(block["severity"]),
+ })
+ else:
+ logger.debug("domain='%s' has no block list", domain)
+
+ except network.exceptions as exception:
+ logger.warning("domain='%s',exception[%s]='%s'", domain, type(exception), str(exception))
+ instances.set_last_error(domain, exception)
+
+ logger.debug("blocklist()=%d - EXIT!", len(blocklist))
+ return blocklist
from urllib.parse import urlparse
import validators
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import domain as domain_helper
+from fba.http import csrf
from fba.http import network
from fba.models import instances
import bs4
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import domain as domain_helper
from fba.helpers import tidyup
+from fba.http import csrf
from fba.http import federation
from fba.http import network
import bs4
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import domain as domain_helper
from fba.helpers import tidyup
+from fba.http import federation
from fba.http import network
from fba.models import blocks
elif nodeinfo_url == "":
raise ValueError("Parameter 'nodeinfo_url' is empty")
- # Init block list
blocklist = list()
- # No CSRF by default, you don't have to add network.api_headers by yourself here
- headers = tuple()
-
- try:
- logger.debug("Checking CSRF for domain='%s'", domain)
- headers = csrf.determine(domain, dict())
- except network.exceptions as exception:
- logger.warning("Exception '%s' during checking CSRF (fetch_blocks,%s)", type(exception), __name__)
- instances.set_last_error(domain, exception)
-
- logger.debug("Returning empty list ... - EXIT!")
- return list()
-
- try:
- # json endpoint for newer mastodongs
- logger.debug("Querying API domain_blocks: domain='%s'", domain)
- data = network.get_json_api(
- domain,
- "/api/v1/instance/domain_blocks",
- headers,
- (config.get("connection_timeout"), config.get("read_timeout"))
- )
- rows = list()
-
- logger.debug("data[]='%s'", type(data))
- if "error_message" in data:
- logger.debug("Was not able to fetch domain_blocks from domain='%s': status_code=%d,error_message='%s'", domain, data['status_code'], data['error_message'])
- instances.set_last_error(domain, data)
- return blocklist
- elif "json" in data and "error" in data["json"]:
- logger.warning("JSON API returned error message: '%s'", data["json"]["error"])
- instances.set_last_error(domain, data)
- return blocklist
- else:
- # Getting blocklist
- rows = data["json"]
-
- logger.debug("Marking domain='%s' as successfully handled ...", domain)
- instances.set_success(domain)
-
- logger.debug("rows[%s]()=%d", type(rows), len(rows))
- if len(rows) == 0:
- logger.debug("domain='%s' has returned zero rows, trying /about/more page ...", domain)
- rows = fetch_blocks_from_about(domain)
-
- logger.debug("rows[%s]()=%d", type(rows), len(rows))
- if len(rows) > 0:
- logger.debug("Checking %d entries from domain='%s' ...", len(rows), domain)
- for block in rows:
- # Check type
- logger.debug("block[]='%s'", type(block))
- if not isinstance(block, dict):
- logger.debug("block[]='%s' is of type 'dict' - SKIPPED!", type(block))
- continue
- elif "domain" not in block:
- logger.warning("block()=%d does not contain element 'domain' - SKIPPED!", len(block))
- continue
- elif "severity" not in block:
- logger.warning("block()=%d does not contain element 'severity' - SKIPPED!", len(block))
- continue
- elif block["severity"] in ["accept", "accepted"]:
- logger.debug("block[domain]='%s' has unwanted severity level '%s' - SKIPPED!", block["domain"], block["severity"])
- continue
- elif "digest" in block and not validators.hashes.sha256(block["digest"]):
- logger.warning("block[domain]='%s' has invalid block[digest]='%s' - SKIPPED!", block["domain"], block["digest"])
- continue
-
- reason = tidyup.reason(block["comment"]) if "comment" in block and block["comment"] is not None and block["comment"] != "" else None
-
- logger.debug("Appending blocker='%s',blocked='%s',reason='%s',block_level='%s'", domain, block["domain"], reason, block["severity"])
- blocklist.append({
- "blocker" : domain,
- "blocked" : block["domain"],
- "hash" : block["digest"] if "digest" in block else None,
- "reason" : reason,
- "block_level": blocks.alias_block_level(block["severity"]),
- })
- else:
- logger.debug("domain='%s' has no block list", domain)
-
- except network.exceptions as exception:
- logger.warning("domain='%s',exception[%s]='%s'", domain, type(exception), str(exception))
- instances.set_last_error(domain, exception)
+ logger.debug("Invoking federation.fetch_blocks(%s) ...", domain)
+ rows = federation.fetch_blocks(domain)
+
+ logger.debug("rows[%s]()=%d", type(rows), len(rows))
+ if len(rows) == 0:
+ logger.debug("domain='%s' has returned zero rows, trying /about/more page ...", domain)
+ rows = fetch_blocks_from_about(domain)
+
+ logger.debug("rows[%s]()=%d", type(rows), len(rows))
+ if len(rows) > 0:
+ logger.debug("Checking %d entries from domain='%s' ...", len(rows), domain)
+ for block in rows:
+ # Check type
+ logger.debug("block[]='%s'", type(block))
+ if not isinstance(block, dict):
+ logger.debug("block[]='%s' is of type 'dict' - SKIPPED!", type(block))
+ continue
+ elif "domain" not in block:
+ logger.warning("block()=%d does not contain element 'domain' - SKIPPED!", len(block))
+ continue
+ elif "severity" not in block:
+ logger.warning("block()=%d does not contain element 'severity' - SKIPPED!", len(block))
+ continue
+ elif block["severity"] in ["accept", "accepted"]:
+ logger.debug("block[domain]='%s' has unwanted severity level '%s' - SKIPPED!", block["domain"], block["severity"])
+ continue
+ elif "digest" in block and not validators.hashes.sha256(block["digest"]):
+ logger.warning("block[domain]='%s' has invalid block[digest]='%s' - SKIPPED!", block["domain"], block["digest"])
+ continue
+
+ reason = tidyup.reason(block["comment"]) if "comment" in block and block["comment"] is not None and block["comment"] != "" else None
+
+ logger.debug("Appending blocker='%s',blocked='%s',reason='%s',block_level='%s'", domain, block["domain"], reason, block["severity"])
+ blocklist.append({
+ "blocker" : domain,
+ "blocked" : block["domain"],
+ "hash" : block["digest"] if "digest" in block else None,
+ "reason" : reason,
+ "block_level": blocks.alias_block_level(block["severity"]),
+ })
+ else:
+ logger.debug("domain='%s' has no block list", domain)
logger.debug("blocklist()=%d - EXIT!", len(blocklist))
return blocklist
import json
import logging
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import dicts as dict_helper
from fba.helpers import domain as domain_helper
from fba.helpers import tidyup
+from fba.http import csrf
from fba.http import network
from fba.models import instances
import logging
-from fba import csrf
-
from fba.helpers import config
from fba.helpers import domain as domain_helper
+from fba.http import csrf
from fba.http import network
from fba.models import instances
projects / fba.git / commitdiff