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__)
33 # Cache for function is_in_url()
36 # Cache for function is_wanted()
39 # Cache for function raise_on()
43 def raise_on(domain: str):
44 logger.debug("domain='%s' - CALLED!", domain)
46 if not isinstance(domain, str):
47 raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
49 raise ValueError("Parameter 'domain' is empty")
50 elif domain in _cache["raise_on"]:
51 logger.debug("Returning cached raised_on='%s' - EXIT!", _cache["raise_on"][domain])
52 return _cache["raise_on"][domain]
53 elif domain.lower() != domain:
54 raise ValueError(f"Parameter domain='{domain}' must be all lower-case")
55 elif not validators.domain(domain.split("/")[0]):
56 raise ValueError(f"domain='{domain}' is not a valid domain")
57 elif domain.endswith(".onion"):
58 raise ValueError(f"domain='{domain}' is a TOR, please don't crawl them!")
59 elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
60 raise ValueError(f"domain='{domain}' is an I2P, please don't crawl them!")
61 elif domain.endswith(".arpa"):
62 raise ValueError(f"domain='{domain}' is a domain for reversed IP addresses, please don't crawl them!")
63 elif domain.endswith(".tld"):
64 raise ValueError(f"domain='{domain}' is a fake domain, please don't crawl them!")
66 _cache["raise_on"][domain] = True
69 def is_in_url(domain: str, url: str) -> bool:
70 logger.debug("domain='%s',url='%s' - CALLED!", domain, url)
73 if blacklist.is_blacklisted(domain):
74 raise ValueError(f"domain='{domain}' is blacklisted but function was invoked")
75 elif not isinstance(url, str):
76 raise ValueError(f"Parameter url[]='{type(url)}' is not of type 'str'")
78 raise ValueError("Parameter 'url' is empty")
79 elif domain + url in _cache["is_in_url"]:
80 logger.debug("Returning cached is_in_url='%s' - EXIT!", _cache["is_in_url"][domain + url])
81 return _cache["is_in_url"][domain + url]
83 punycode = domain.encode("idna").decode("utf-8")
85 components = urlparse(url)
86 logger.debug("components[]='%s',punycode='%s'", type(components), punycode)
88 is_found = (punycode in [components.netloc, components.hostname])
91 _cache["is_in_url"][domain + url] = is_found
93 logger.debug("is_found='%s' - EXIT!", is_found)
96 def is_wanted(domain: str) -> bool:
97 logger.debug("domain='%s' - CALLED!", domain)
99 if not isinstance(domain, str):
100 raise ValueError(f"Parameter domain[]='{type(domain)}' is not of type 'str'")
102 raise ValueError("Parameter 'domain' is empty")
103 elif domain in _cache["is_wanted"]:
104 logger.debug("Returning cached is_found='%s' - EXIT!", _cache["is_wanted"][domain])
105 return _cache["is_wanted"][domain]
108 if domain.lower() != domain:
109 logger.debug("domain='%s' is not all-lowercase - setting False ...", domain)
111 elif not validators.domain(domain.split("/")[0]):
112 logger.debug("domain='%s' is not a valid domain name - setting False ...", domain)
114 elif domain.endswith(".arpa"):
115 logger.debug("domain='%s' is a domain for reversed IP addresses - setting False ...", domain)
117 elif domain.endswith(".onion"):
118 logger.debug("domain='%s' is a TOR .onion domain - setting False ...", domain)
120 elif domain.endswith(".i2p") and config.get("allow_i2p_domain") == "true":
121 logger.debug("domain='%s' is an I2P domain - setting False ...", domain)
123 elif domain.endswith(".tld"):
124 logger.debug("domain='%s' is a fake domain - setting False ...", domain)
126 elif blacklist.is_blacklisted(domain):
127 logger.debug("domain='%s' is blacklisted - setting False ...", domain)
129 elif domain.find("/profile/") > 0 or domain.find("/users/") > 0 or (instances.is_registered(domain.split("/")[0]) and domain.find("/c/") > 0):
130 logger.debug("domain='%s' is a single user", domain)
132 elif domain.find("/tag/") > 0:
133 logger.debug("domain='%s' is a tag", domain)
137 _cache["is_wanted"][domain] = wanted
139 logger.debug("wanted='%s' - EXIT!", wanted)