ScrapTheChan/scrapthechan/parsers/fourchan.py

from re import match
from typing import List, Optional

from scrapthechan.fileinfo import FileInfo
from scrapthechan.parser import Parser

__all__ = ["FourChanParser"]


class FourChanParser(Parser):
	"""JSON parser for 4chan.org image board."""

	__url_thread_json = "https://a.4cdn.org/{board}/thread/{thread}.json"
	__url_file_link = "https://i.4cdn.org/{board}/{filename}"

	def __init__(self, board: str, thread: str,
				 skip_posts: Optional[int] = None) -> None:
		posts = self._get_json(self.__url_thread_json.format(board=board, \
			thread=thread))['posts']
		super(FourChanParser, self).__init__(board, thread, posts, skip_posts)

	@property
	def imageboard(self) -> str:
		return "4chan.org"

	@property
	def op(self) -> Optional[str]:
		op = ""
		if 'sub' in self._op_post:
			op = f"{self._op_post['sub']}\n"
		if 'com' in self._op_post:
			op += self._op_post['com']
		return op if not op == "" else None

	def _parse_post(self, post: dict) -> List[FileInfo]:
		if not 'tim' in post: return None

		dlfname = f"{post['tim']}{post['ext']}"

		if "filename" in post:
			if match(r"^image\.\w+$", post['filename']) is None:
				filename = dlfname
			else:
				filename = f"{post['filename']}{post['ext']}"

		# Hash algorithm is hardcoded since it is highly unlikely that it will
		# be changed in foreseeable future. And if it'll change then this line
		# will be necessarily updated anyway.
		return [FileInfo(filename, post['fsize'],
			self.__url_file_link.format(board=self.board, filename=dlfname),
			post['md5'], 'md5')]