path: root/src/bbss/friends.py

from bbss.lists import BaseListFile, ListFileEntry, parse_listfile
import bbss.site as site
from bbss import DEFAULT_PATHS
from dataclasses import dataclass
from typing import cast, Optional
from collections.abc import Sequence
import requests
import re

FRIEND_REGEX = re.compile(r"""^
                              (?:(?P<scheme>[a-z]+)://)? # match the URL scheme, e.x. `https://`
                              (?P<domain>(?:[a-z0-9\-]+\.)*(?:[a-z])+) # match the actual domain
                              (?:
                                | # match no path
                                (?P<path>(?:/[^/\s#?]+)*/?) # match a path
                              )
                              $""", re.X)

@dataclass(frozen=True)
class FriendListFileEntry(ListFileEntry):
  url: str
  domain: str
  scheme: str
  path: str

  def __init__(self, entry: str, comment: Optional[str]):
    super().__init__(entry, comment)
    m = FRIEND_REGEX.match(entry)
    if m is None: return
    self.__setattr__('scheme', m.group('scheme') or None)
    self.__setattr__('domain', m.group('domain'))
    self.__setattr__('path', m.group('path').removesuffix('/'))
    self.__setattr__('url', (self.scheme if self.scheme else 'https') + '://' + self.domain + (self.path if self.path is not None else ""))

  def exists(self) -> bool:
    if self.path is not None:
      return requests.head(self.url + "/sizes.txt").ok or requests.head(self.url + "/88x31/list.txt").ok
    else:
      for default in DEFAULT_PATHS:
        if requests.head(default + "sizes.txt").ok or requests.head(default + "/88x31/list.txt").ok:
          return True
    return False

  def get(self) -> "site.Site":
    return site.Site(self.domain, self.path, scheme = self.scheme)

class FriendListFile(BaseListFile[FriendListFileEntry]):
  def __init__(self, contents: str):
    super().__init__(contents)
    self._entries = parse_listfile(contents, FriendListFileEntry)

__all__ = ["FriendListFileEntry", "FriendListFile"]