64 lines
1.8 KiB
Python
64 lines
1.8 KiB
Python
from re import match
|
|
from typing import List, Optional
|
|
|
|
from scrapthechan.fileinfo import FileInfo
|
|
from scrapthechan.parser import Parser
|
|
|
|
__all__ = ["EightKunParser"]
|
|
|
|
|
|
class EightKunParser(Parser):
|
|
"""JSON parser for 8kun.top image board."""
|
|
|
|
__url_thread_json = "https://8kun.top/{board}/res/{thread}.json"
|
|
__url_file_link = "https://media.8kun.top/file_store/{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(EightKunParser, self).__init__(board, thread, posts, skip_posts)
|
|
|
|
@property
|
|
def imageboard(self) -> str:
|
|
return "8kun.top"
|
|
|
|
@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(post['filename'], r"^image\.\w{1,4}$") is None:
|
|
filename = dlfname
|
|
else:
|
|
filename = f"{post['filename']}{post['ext']}"
|
|
|
|
files = []
|
|
files.append(FileInfo(filename, post['fsize'],
|
|
self.__url_file_link.format(board=self.board, filename=dlfname),
|
|
post['md5'], 'md5'))
|
|
|
|
if "extra_files" in post:
|
|
for f in post["extra_files"]:
|
|
dlfname = f"{f['tim']}{f['ext']}"
|
|
if "filename" in post:
|
|
if match(post['filename'], r"^image\.\w+$") is None:
|
|
filename = dlfname
|
|
else:
|
|
filename = f"{post['filename']}{post['ext']}"
|
|
dlurl = self.__url_file_link.format(board=self.board, \
|
|
filename=dlfname)
|
|
files.append(FileInfo(filename, f['fsize'], \
|
|
dlurl, f['md5'], 'md5'))
|
|
return files
|