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/>.
23 from fba.helpers import config
24 from fba.helpers import cookies
25 from fba.helpers import domain as domain_helper
27 from fba.http import network
29 from fba.models import instances
31 logging.basicConfig(level=logging.INFO)
32 logger = logging.getLogger(__name__)
34 def determine(domain: str, headers: dict) -> dict:
35 logger.debug("domain='%s',headers()=%d - CALLED!", domain, len(headers))
36 domain_helper.raise_on(domain)
38 if not isinstance(headers, dict):
39 raise ValueError(f"Parameter headers[]='{type(headers)}' is not of type 'dict'")
41 # Default headers with no CSRF
44 # Fetch / to check for meta tag indicating csrf
45 logger.debug("Fetching / from domain='%s' for CSRF check ...", domain)
46 response = network.fetch_response(
49 headers=network.web_headers,
50 timeout=(config.get("connection_timeout"), config.get("read_timeout"))
53 logger.debug("response.ok='%s',response.status_code=%d,response.text()=%d", response.ok, response.status_code, len(response.text))
54 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):
56 logger.debug("Parsing response.text()=%d Bytes ...", len(response.text))
57 cookies.store(domain, response.cookies.get_dict())
60 meta = bs4.BeautifulSoup(
64 logger.debug("meta[]='%s'", type(meta))
65 tag = meta.find("meta", attrs={"name": "csrf-token"})
67 logger.debug("tag[%s]='%s'", type(tag), tag)
69 logger.debug("Adding CSRF token='%s' for domain='%s'", tag["content"], domain)
70 reqheaders["X-CSRF-Token"] = tag["content"]
71 elif not domain_helper.is_in_url(domain, response.url):
72 logger.warning("domain='%s' doesn't match with response.url='%s', maybe redirect to other domain?", domain, response.url)
74 message = f"Redirect from domain='{domain}' to response.url='{response.url}'"
75 instances.set_last_error(domain, message)
76 raise requests.exceptions.TooManyRedirects(message)
78 logger.debug("reqheaders()=%d - EXIT!", len(reqheaders))