From 520d88c76a4547786621ae280613c9b4fd29305b Mon Sep 17 00:00:00 2001
From: "Alexander \"Arav\" Andreev" <me@arav.top>
Date: Mon, 20 Jul 2020 03:45:51 +0400
Subject: [PATCH] Parser for 8kun.top added. And I changed compares in
 __init__.

---
 scrapthechan/parsers/__init__.py | 13 ++++---
 scrapthechan/parsers/eightkun.py | 63 ++++++++++++++++++++++++++++++++
 setup.cfg                        |  3 +-
 3 files changed, 73 insertions(+), 6 deletions(-)
 create mode 100644 scrapthechan/parsers/eightkun.py

diff --git a/scrapthechan/parsers/__init__.py b/scrapthechan/parsers/__init__.py
index adc71a1..aaaa774 100644
--- a/scrapthechan/parsers/__init__.py
+++ b/scrapthechan/parsers/__init__.py
@@ -8,7 +8,8 @@ from scrapthechan.parser import Parser
 __all__ = ["SUPPORTED_IMAGEBOARDS", "get_parser_by_url", "get_parser_by_site"]
 
 
-SUPPORTED_IMAGEBOARDS: List[str] = ["4chan.org", "lainchan.org", "2ch.hk"]
+SUPPORTED_IMAGEBOARDS: List[str] = ["4chan.org", "lainchan.org", "2ch.hk", \
+	"8kun.top"]
 
 
 def get_parser_by_url(url: str) -> Parser:
@@ -20,15 +21,17 @@ def get_parser_by_url(url: str) -> Parser:
 
 def get_parser_by_site(site: str, board: str, thread: str) -> Parser:
 	"""Returns an initialised parser for `site` with `board` and `thread`."""
-	if site in ['boards.4chan.org', 'boards.4channel.org',
-				'4chan', '4chan.org']:
+	if '4chan' in site:
 		from .fourchan import FourChanParser
 		return FourChanParser(board, thread)
-	elif site in ['lainchan.org', 'lainchan']:
+	elif 'lainchan' in site:
 		from .lainchan import LainchanParser
 		return LainchanParser(board, thread)
-	elif site in ['2ch.hk', '2ch']:
+	elif '2ch' in site:
 		from .dvach import DvachParser
 		return DvachParser(board, thread)
+	elif '8kun' in site:
+		from .eightkun import EightKunParser
+		return EightKunParser(board, thread)
 	else:
 		raise NotImplementedError(f"Parser for {site} is not implemented")
diff --git a/scrapthechan/parsers/eightkun.py b/scrapthechan/parsers/eightkun.py
new file mode 100644
index 0000000..afc506b
--- /dev/null
+++ b/scrapthechan/parsers/eightkun.py
@@ -0,0 +1,63 @@
+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
diff --git a/setup.cfg b/setup.cfg
index 82fb1c6..c63356d 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -3,7 +3,7 @@ name = scrapthechan
 version = attr: scrapthechan.__version__
 description =
     Scrap the files posted in a thread on an imageboard. Currently supports
-    4chan.org, lainchan.org and 2ch.hk.
+    4chan.org, lainchan.org, 2ch.hk and 8kun.top.
 long_description = file: README.md
 long_description_content_type = text/markdown
 author = Alexander "Arav" Andreev
@@ -15,6 +15,7 @@ keywords =
     4chan
     2ch
     lainchan
+    8kun.top
 license = MIT
 license_file = COPYING
 classifiers =