IB parsers rewritten accordingly to fixed Parser class.
This commit is contained in:
parent
f3ef07af68
commit
78d4a62c17
GPG Key ID:
610DF2574456329F
@ -10,31 +10,38 @@ __all__ = ["DvachParser"]
|
||||
class DvachParser(Parser):
|
||||
"""JSON parser for 2ch.hk image board."""
|
||||
|
||||
__url_thread_json = "https://2ch.hk/{board}/res/{thread}.json"
|
||||
__url_file_link = "https://2ch.hk"
|
||||
|
||||
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))['threads'][0]['posts']
|
||||
super(DvachParser, self).__init__(board, thread, posts, skip_posts)
|
||||
super().__init__(board, thread, skip_posts)
|
||||
|
||||
@property
|
||||
def json_thread_url(self) -> str:
|
||||
return "https://2ch.hk/{board}/res/{thread}.json"
|
||||
|
||||
@property
|
||||
def file_base_url(self) -> str:
|
||||
return "https://2ch.hk"
|
||||
|
||||
@property
|
||||
def subject_field(self) -> str:
|
||||
return "subject"
|
||||
|
||||
@property
|
||||
def comment_field(self) -> str:
|
||||
return "comment"
|
||||
|
||||
@property
|
||||
def imageboard(self) -> str:
|
||||
return "2ch.hk"
|
||||
|
||||
@property
|
||||
def op(self) -> Optional[str]:
|
||||
op = ""
|
||||
if 'subject' in self._op_post:
|
||||
op = f"{self._op_post['subject']}\n"
|
||||
if 'comment' in self._op_post:
|
||||
op += self._op_post['comment']
|
||||
return op if not op == "" else None
|
||||
def _extract_posts_list(self, lst: List) -> List[dict]:
|
||||
return lst['threads'][0]['posts']
|
||||
|
||||
def _parse_post(self, post) -> Optional[List[FileInfo]]:
|
||||
if not 'files' in post: return None
|
||||
|
||||
files = []
|
||||
|
||||
for f in post['files']:
|
||||
if not 'sticker' in f:
|
||||
if match(r"^image\.\w+$", f['fullname']) is None:
|
||||
@ -47,10 +54,10 @@ class DvachParser(Parser):
|
||||
# completely fine to hardcode `hash_algo`.
|
||||
if 'md5' in f:
|
||||
files.append(FileInfo(fullname, f['size'],
|
||||
f"{self.__url_file_link}{f['path']}",
|
||||
f"{self.file_base_url}{f['path']}",
|
||||
f['md5'], 'md5'))
|
||||
else:
|
||||
files.append(FileInfo(fullname, f['size'],
|
||||
f"{self.__url_file_link}{f['path']}",
|
||||
f"{self.file_base_url}{f['path']}",
|
||||
None, None))
|
||||
return files
|
||||
|
||||
@ -1,63 +1,25 @@
|
||||
from re import match
|
||||
from typing import List, Optional
|
||||
from typing import Optional
|
||||
|
||||
from scrapthechan.fileinfo import FileInfo
|
||||
from scrapthechan.parser import Parser
|
||||
from scrapthechan.parsers.tinyboardlike import TinyboardLikeParser
|
||||
|
||||
__all__ = ["EightKunParser"]
|
||||
|
||||
|
||||
class EightKunParser(Parser):
|
||||
class EightKunParser(TinyboardLikeParser):
|
||||
"""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)
|
||||
super().__init__(board, thread, 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 json_thread_url(self) -> str:
|
||||
return "https://8kun.top/{board}/res/{thread}.json"
|
||||
|
||||
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']}"
|
||||
|
||||
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(r"^image\.\w+$", post['filename']) 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
|
||||
@property
|
||||
def file_base_url(self) -> str:
|
||||
return "https://media.8kun.top/file_dl/{filename}"
|
||||
|
||||
@ -1,51 +1,25 @@
|
||||
from re import match
|
||||
from typing import List, Optional
|
||||
from typing import Optional
|
||||
|
||||
from scrapthechan.fileinfo import FileInfo
|
||||
from scrapthechan.parser import Parser
|
||||
from scrapthechan.parsers.tinyboardlike import TinyboardLikeParser
|
||||
|
||||
__all__ = ["FourChanParser"]
|
||||
|
||||
|
||||
class FourChanParser(Parser):
|
||||
class FourChanParser(TinyboardLikeParser):
|
||||
"""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)
|
||||
super().__init__(board, thread, 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 json_thread_url(self) -> str:
|
||||
return "https://a.4cdn.org/{board}/thread/{thread}.json"
|
||||
|
||||
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')]
|
||||
@property
|
||||
def file_base_url(self) -> str:
|
||||
return "https://i.4cdn.org/{board}/{filename}"
|
||||
|
||||
@ -1,66 +1,25 @@
|
||||
from re import match
|
||||
from typing import List, Optional
|
||||
from typing import Optional
|
||||
|
||||
from scrapthechan.parser import Parser
|
||||
from scrapthechan.fileinfo import FileInfo
|
||||
from scrapthechan.parsers.tinyboardlike import TinyboardLikeParser
|
||||
|
||||
__all__ = ["LainchanParser"]
|
||||
|
||||
|
||||
class LainchanParser(Parser):
|
||||
"""JSON parser for lainchan.org image board.
|
||||
JSON structure is identical to 4chan.org's, so this parser is just inherited
|
||||
from 4chan.org's parser and only needed things are redefined.
|
||||
"""
|
||||
|
||||
__url_thread_json = "https://lainchan.org/{board}/res/{thread}.json"
|
||||
__url_file_link = "https://lainchan.org/{board}/src/{filename}"
|
||||
class LainchanParser(TinyboardLikeParser):
|
||||
"""JSON parser for lainchan.org image board."""
|
||||
|
||||
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(LainchanParser, self).__init__(board, thread, posts, skip_posts)
|
||||
super().__init__(board, thread, skip_posts)
|
||||
|
||||
@property
|
||||
def imageboard(self) -> str:
|
||||
return "lainchan.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 json_thread_url(self) -> str:
|
||||
return "https://lainchan.org/{board}/res/{thread}.json"
|
||||
|
||||
def _parse_post(self, post) -> List[FileInfo]:
|
||||
if not 'tim' in post: return None
|
||||
|
||||
dlfname = f"{post['tim']}{post['ext']}"
|
||||
|
||||
if "filename" in post:
|
||||
if match(r"^image\.\w+$", post['filename']) is None:
|
||||
filename = dlfname
|
||||
else:
|
||||
filename = f"{post['filename']}{post['ext']}"
|
||||
|
||||
files = []
|
||||
files.append(FileInfo(filename, post['fsize'],
|
||||
self.__url_file_link.format(board=self.board, filename=dlfname),
|
||||
post['md5'], 'md5'))
|
||||
|
||||
if "extra_files" in post:
|
||||
for f in post["extra_files"]:
|
||||
dlfname = f"{f['tim']}{f['ext']}"
|
||||
if "filename" in post:
|
||||
if match(r"^image\.\w+$", post['filename']) 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
|
||||
@property
|
||||
def file_base_url(self) -> str:
|
||||
return "https://lainchan.org/{board}/src/{filename}"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user