39 lines
1.4 KiB
Python
39 lines
1.4 KiB
Python
"""Here are defined the JSON parsers for imageboards."""
|
|
from re import search
|
|
from typing import List, Optional
|
|
|
|
from scrapthechan.parser import Parser
|
|
|
|
|
|
__all__ = ["SUPPORTED_IMAGEBOARDS", "get_parser_by_url", "get_parser_by_site"]
|
|
|
|
|
|
URLRX = r"https?:\/\/(?P<s>[\w\.]+)\/(?P<b>\w+)\/(?:\w+)?\/(?P<t>\w+)"
|
|
SUPPORTED_IMAGEBOARDS: List[str] = ["4chan.org", "lainchan.org", "2ch.hk", \
|
|
"8kun.top"]
|
|
|
|
|
|
def get_parser_by_url(url: str, skip_posts: Optional[int] = None) -> Parser:
|
|
"""Parses URL and extracts from it site name, board and thread.
|
|
And then returns initialised Parser object for detected imageboard."""
|
|
site, board, thread = search(URLRX, url).groups()
|
|
return get_parser_by_site(site, board, thread, skip_posts)
|
|
|
|
def get_parser_by_site(site: str, board: str, thread: str,
|
|
skip_posts: Optional[int] = None) -> Parser:
|
|
"""Returns an initialised parser for `site` with `board` and `thread`."""
|
|
if '4chan' in site:
|
|
from .fourchan import FourChanParser
|
|
return FourChanParser(board, thread, skip_posts)
|
|
elif 'lainchan' in site:
|
|
from .lainchan import LainchanParser
|
|
return LainchanParser(board, thread, skip_posts)
|
|
elif '2ch' in site:
|
|
from .dvach import DvachParser
|
|
return DvachParser(board, thread, skip_posts)
|
|
elif '8kun' in site:
|
|
from .eightkun import EightKunParser
|
|
return EightKunParser(board, thread, skip_posts)
|
|
else:
|
|
raise NotImplementedError(f"Parser for {site} is not implemented")
|