kabigon 0.6.0__py3-none-any.whl → 0.6.1__py3-none-any.whl

kabigon/__init__.py

@@ -11,7 +11,6 @@ from .loader import Loader
 from .pdf import PDFLoader
 from .playwright import PlaywrightLoader
 from .reel import ReelLoader
-from .singlefile import SinglefileLoader
 from .youtube import YoutubeLoader
 from .ytdlp import YtdlpLoader
 

kabigon/compose.py

@@ -3,18 +3,19 @@ from urllib.parse import urlunparse
 
 from loguru import logger
 
-from .errors import LoaderError
+from .errors import KabigonError
 from .loader import Loader
 
 REPLACEMENTS = {
-    "api.fxtwitter.com": [
+    # fixupx.com seems better than api.fxtwitter.com
+    "fixupx.com": [
         "twitter.com",
         "x.com",
         "fxtwitter.com",
         "vxtwitter.com",
         "fixvx.com",
         "twittpr.com",
-        "fixupx.com",
+        "api.fxtwitter.com",
     ]
 }
 
@@ -49,7 +50,7 @@ class Compose(Loader):
             except Exception as e:
                 logger.info("[{}] Failed to load URL: {}, got error: {}", loader.__class__.__name__, url, e)
 
-        raise LoaderError(f"Failed to load URL: {url}")
+        raise KabigonError(f"Failed to load URL: {url}")
 
     async def async_load(self, url: str) -> str:
         url = replace_domain(url)
@@ -68,4 +69,4 @@ class Compose(Loader):
             except Exception as e:
                 logger.info("[{}] Failed to load URL: {}, got error: {}", loader.__class__.__name__, url, e)
 
-        raise LoaderError(f"Failed to load URL: {url}")
+        raise KabigonError(f"Failed to load URL: {url}")

kabigon/errors.py

@@ -1,23 +1,23 @@
-class LoaderError(Exception):
+class KabigonError(Exception):
     pass
 
 
-class FirecrawlKeyError(LoaderError):
+class FirecrawlKeyError(KabigonError):
     def __init__(self) -> None:
         super().__init__("FIRECRAWL_API_KEY is not set.")
 
 
-class FirecrawlError(LoaderError):
+class FirecrawlError(KabigonError):
     def __init__(self, url: str, error: str) -> None:
         msg = f"Failed to load URL: {url}, got: {error}"
         super().__init__(msg)
 
 
-class NotPDFError(LoaderError):
+class NotPDFError(KabigonError):
     def __init__(self, url: str) -> None:
         super().__init__(f"URL is not a PDF: {url}")
 
 
-class NotReelURLError(LoaderError):
+class NotReelURLError(KabigonError):
     def __init__(self, url: str):
         super().__init__(f"URL is not an Instagram Reel: {url}")

kabigon/ytdlp.py

@@ -14,7 +14,7 @@ from loguru import logger
 from .loader import Loader
 
 try:
-    import mlx_whisper  # noqa: F401
+    import mlx_whisper  # noqa: F401 # type: ignore
 
     _mlx_whisper_installed = True
 except ImportError:

{kabigon-0.6.0.dist-info → kabigon-0.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kabigon
-Version: 0.6.0
+Version: 0.6.1
 Author-email: narumi <toucans-cutouts0f@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.10

{kabigon-0.6.0.dist-info → kabigon-0.6.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
-kabigon/__init__.py,sha256=L64FtFCQQxkqXXHDkW2rniWGAnufmC9WG6KBwutXU4w,539
+kabigon/__init__.py,sha256=_1LdKfp7qm0m7Fa_IJ9zcg4TRB14c9bB-r9M3fwASWI,498
 kabigon/cli.py,sha256=XSTyD1RFqq2Qok_52kSjJlBLUXl6t-K9QtsxCfB15o4,611
-kabigon/compose.py,sha256=Yhn9fe0mylVLpK01sT9OWWItIY1gD8TZLQ4qY8hAeSQ,2110
-kabigon/errors.py,sha256=tYokuDQ1-U25zq3hWu-GsYJBDpDq3VuObUijnd7Nc7M,613
+kabigon/compose.py,sha256=5H_hWQ7ENUmEdeOpB2bkRv4U_U18_1IyNTran-cLYaM,2166
+kabigon/errors.py,sha256=3eSPQtLocreKuq9mhwRk7IMdA2xh8KkmIFEUhGmTPxg,618
 kabigon/firecrawl.py,sha256=Xnrlhco_R58x5kwGy9ZCKTnVqS4Pp-D3G0u-qnuGEsU,800
 kabigon/httpx.py,sha256=uDdLks6zVzirY7-mnsJkypX86kAI5XmUVfK-lFifdJA,895
 kabigon/loader.py,sha256=KhOJvlzLDM0o05o4VqMRgiyRVjofkzuGEcihQagj-8M,452
@@ -9,12 +9,11 @@ kabigon/pdf.py,sha256=yJcgkdMMF52baFsFxJp9Jn89KsTKBboLTLwD3gs6U5U,1775
 kabigon/playwright.py,sha256=MZ-r0Ej2wWAOJkDLwYRvO77wcDvh38KXz2wgDsCTgm0,1358
 kabigon/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 kabigon/reel.py,sha256=J2QOxGMYi_HaEscQPIipPEoHGN_iksGxR6pV_XvryME,929
-kabigon/singlefile.py,sha256=CeTT2WPYm0vb1xWPNdyBN4uHRw9hRqfZm68D-nEcUA8,1800
 kabigon/utils.py,sha256=eNTLtHLSB2erDac2HH3jWemgfr8Ou_ozwVb8h9BD-4g,922
 kabigon/youtube.py,sha256=HoiFNq0ookPL7_rO_wloBaY8yTIX6xP8A77F7y02q64,1166
-kabigon/ytdlp.py,sha256=kG1fXqU650otOWespjOSkGK_-jk1wO-sWiR60_UPJxY,3125
-kabigon-0.6.0.dist-info/METADATA,sha256=zsjAoTye8jH1NtI_ZylcCI8Vt-S0CqQWcN-ca39cbLY,1078
-kabigon-0.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kabigon-0.6.0.dist-info/entry_points.txt,sha256=O3FYAO9w-NQvlGMJrBvtrnGHSK2QkUnQBTa30YXRbVE,45
-kabigon-0.6.0.dist-info/licenses/LICENSE,sha256=H2T3_RTgmcngMeC7p_SXT3GwBLkd2DaNgAZuxulcfiA,1066
-kabigon-0.6.0.dist-info/RECORD,,
+kabigon/ytdlp.py,sha256=_QRcyFx9s7NnI1MvcWdKKxlX-hHLnqtduCSL5_UH6dU,3140
+kabigon-0.6.1.dist-info/METADATA,sha256=78J35ClbTdy2-vU8GtlQWjgSTitntFI8J-Cz07FGqoo,1078
+kabigon-0.6.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kabigon-0.6.1.dist-info/entry_points.txt,sha256=O3FYAO9w-NQvlGMJrBvtrnGHSK2QkUnQBTa30YXRbVE,45
+kabigon-0.6.1.dist-info/licenses/LICENSE,sha256=H2T3_RTgmcngMeC7p_SXT3GwBLkd2DaNgAZuxulcfiA,1066
+kabigon-0.6.1.dist-info/RECORD,,

kabigon/singlefile.py

@@ -1,65 +0,0 @@
-import os
-import subprocess
-import tempfile
-from functools import cache
-from pathlib import Path
-from typing import Final
-
-import charset_normalizer
-from loguru import logger
-
-from .loader import Loader
-from .utils import html_to_markdown
-
-DEFAULT_SINGLEFILE_PATH: Final[str] = "single-file"
-
-
-@cache
-def get_singlefile_path() -> str:
-    path = os.getenv("SINGLEFILE_PATH")
-    if not path:
-        path = DEFAULT_SINGLEFILE_PATH
-        logger.warning("SINGLEFILE_PATH not set, using default: {}", DEFAULT_SINGLEFILE_PATH)
-    return path
-
-
-class SinglefileLoader(Loader):
-    def __init__(self, cookies_file: str | None = None, browser_headless: bool = False) -> None:
-        self.cookies_file = cookies_file
-        self.browser_headless = browser_headless
-
-    def load(self, url: str) -> str:
-        filename = self.download(url)
-        content = str(charset_normalizer.from_path(filename).best())
-        return html_to_markdown(content)
-
-    def download(self, url: str) -> str:
-        logger.info("Downloading HTML using SingleFile: {}", url)
-
-        filename = tempfile.mktemp(suffix=".html")
-        singlefile_path = get_singlefile_path()
-
-        cmds = [singlefile_path]
-
-        if self.cookies_file is not None:
-            cookies_path = Path(self.cookies_file)
-            if not cookies_path.exists():
-                raise FileNotFoundError(f"Cookies file not found: {self.cookies_file}")
-
-            cmds += [
-                "--browser-cookies-file",
-                str(cookies_path),
-            ]
-
-        cmds += [
-            "--filename-conflict-action",
-            "overwrite",
-            "--browser-headless",
-            str(self.browser_headless).lower(),
-            url,
-            filename,
-        ]
-
-        subprocess.run(cmds)
-
-        return filename