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
25 from fba.helpers import config
26 from fba.helpers import cookies
27 from fba.helpers import domain as domain_helper
29 from fba.http import network
31 from fba.models import instances
33 logging.basicConfig(level=logging.INFO)
34 logger = logging.getLogger(__name__)
36 def determine(domain: str, headers: dict) -> dict:
37 logger.debug("domain='%s',headers()=%d - CALLED!", domain, len(headers))
38 domain_helper.raise_on(domain)
40 if not isinstance(headers, dict):
41 raise ValueError(f"Parameter headers[]='{type(headers)}' is not 'dict'")
43 # Default headers with no CSRF
46 # Fetch / to check for meta tag indicating csrf
47 logger.debug("Fetching / from domain='%s' for CSRF check ...", domain)
50 headers=network.web_headers,
51 timeout=(config.get("connection_timeout"), config.get("read_timeout"))
53 components = urlparse(response.url)
55 logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text))
56 if response.ok and response.status_code < 300 and response.text.strip() != "" and response.text.find("<html") > 0 and domain == components.netloc:
58 logger.debug("Parsing response.text()=%d Bytes ...", len(response.text))
59 cookies.store(domain, response.cookies.get_dict())
62 meta = bs4.BeautifulSoup(
66 logger.debug("meta[]='%s'", type(meta))
67 tag = meta.find("meta", attrs={"name": "csrf-token"})
69 logger.debug("tag[%s]='%s'", type(tag), tag)
71 logger.debug("Adding CSRF token='%s' for domain='%s'", tag["content"], domain)
72 reqheaders["X-CSRF-Token"] = tag["content"]
73 elif domain != components.netloc:
74 logger.warning("domain='%s' doesn't match components.netloc='%s', maybe redirect to other domain?", domain, components.netloc)
75 message = f"Redirect from domain='{domain}' to components.netloc='{components.netloc}'"
76 instances.set_last_error(domain, message)
77 raise requests.exceptions.TooManyRedirects(message)
79 logger.debug("reqheaders()=%d - EXIT!", len(reqheaders))