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/>.
19 from urllib.parse import urlparse
23 from fba.helpers import blacklist
24 from fba.helpers import config
26 from fba.models import instances
28 logging.basicConfig(level=logging.INFO)
29 logger = logging.getLogger(__name__)
34 def raise_on(domain: str):
35 logger.debug("domain='%s' - CALLED!", domain)
37 if not isinstance(domain, str):
38 raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
40 raise ValueError("Parameter 'domain' is empty")
41 elif domain.lower() != domain:
42 raise ValueError(f"Parameter domain='{domain}' must be all lower-case")
43 elif not validators.domain(domain.split("/")[0]):
44 raise ValueError(f"domain='{domain}' is not a valid domain")
45 elif domain.endswith(".onion"):
46 raise ValueError(f"domain='{domain}' is a TOR, please don't crawl them!")
47 elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
48 raise ValueError(f"domain='{domain}' is an I2P, please don't crawl them!")
49 elif domain.endswith(".arpa"):
50 raise ValueError(f"domain='{domain}' is a domain for reversed IP addresses, please don't crawl them!")
51 elif domain.endswith(".tld"):
52 raise ValueError(f"domain='{domain}' is a fake domain, please don't crawl them!")
56 def is_in_url(domain: str, url: str) -> bool:
57 logger.debug("domain='%s',url='%s' - CALLED!", domain, url)
60 if not isinstance(url, str):
61 raise ValueError(f"Parameter url[]='{type(url)}' is not of type 'str'")
63 raise ValueError("Parameter 'url' is empty")
64 elif "is_in_url" in _cache and domain + url in _cache["is_in_url"]:
65 logger.debug("Returning cached is_found='%s' - EXIT!", _cache["is_in_url"][domain + url])
66 return _cache["is_in_url"][domain + url]
67 elif "is_in_url" not in _cache:
68 logger.debug("Initializing cache for function 'is_in_url' ...")
69 _cache["is_in_url"] = {}
71 punycode = domain.encode("idna").decode("utf-8")
73 components = urlparse(url)
74 logger.debug("components[]='%s',punycode='%s'", type(components), punycode)
76 is_found = (punycode in [components.netloc, components.hostname])
77 _cache["is_in_url"][domain + url] = is_found
79 logger.debug("is_found='%s' - EXIT!", is_found)
82 def is_wanted(domain: str) -> bool:
83 logger.debug("domain='%s' - CALLED!", domain)
85 if not isinstance(domain, str):
86 raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
88 raise ValueError("Parameter 'domain' is empty")
89 elif "is_wanted" in _cache and domain in _cache["is_wanted"]:
90 logger.debug("Returning cached is_found='%s' - EXIT!", _cache["is_wanted"][domain])
91 return _cache["is_wanted"][domain]
92 elif "is_wanted" not in _cache:
93 logger.debug("Initializing cache for function 'is_wanted' ...")
94 _cache["is_wanted"] = {}
97 if domain.lower() != domain:
98 logger.debug("domain='%s' is not all-lowercase - setting False ...", domain)
100 elif not validators.domain(domain.split("/")[0]):
101 logger.debug("domain='%s' is not a valid domain name - setting False ...", domain)
103 elif domain.endswith(".arpa"):
104 logger.debug("domain='%s' is a domain for reversed IP addresses - setting False ...", domain)
106 elif domain.endswith(".onion"):
107 logger.debug("domain='%s' is a TOR .onion domain - setting False ...", domain)
109 elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
110 logger.debug("domain='%s' is an I2P domain - setting False ...", domain)
112 elif domain.endswith(".tld"):
113 logger.debug("domain='%s' is a fake domain - setting False ...", domain)
115 elif blacklist.is_blacklisted(domain):
116 logger.debug("domain='%s' is blacklisted - setting False ...", domain)
118 elif domain.find("/profile/") > 0 or domain.find("/users/") > 0 or (instances.is_registered(domain.split("/")[0]) and domain.find("/c/") > 0):
119 logger.debug("domain='%s' is a single user", domain)
121 elif domain.find("/tag/") > 0:
122 logger.debug("domain='%s' is a tag", domain)
125 _cache["is_wanted"][domain] = wanted
126 logger.debug("wanted='%s' - EXIT!", wanted)