MinerU [WinError 127] 找不到指定的程序

Description of the bug | 错误描述

2024-08-16 16:39:45.419 | INFO | magic_pdf.libs.pdf_check:detect_invalid_chars:57 - cid_count: 0, text_len: 1, cid_chars_radio: 0.0 2024-08-16 16:39:45.420 | WARNING | magic_pdf.filter.pdf_classify_by_type:classify:334 - pdf is not classified by area and text_len, by_image_area: False, by_text: False, by_avg_words: False, by_img_num: True, by_text_layout: False, by_img_narrow_strips: True, by_invalid_chars: True 2024-08-16 16:39:47.282 | ERROR | magic_pdf.tools.cli:parse_doc:69 - [WinError 127] 找不到指定的程序。 Traceback (most recent call last):

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, │ │ └ {'name': 'main', 'doc': None, 'package': '', 'loader': <zipimporter object "C:\Users\XN963FS\AppData\Loca... │ └ <code object at 0x00000208217B0240, file "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Scripts\magic-pdf... └ <function _run_code at 0x00000208214EFC70>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) │ └ {'name': 'main', 'doc': None, 'package': '', 'loader': <zipimporter object "C:\Users\XN963FS\AppData\Loca... └ <code object at 0x00000208217B0240, file "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Scripts\magic-pdf...

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Scripts\magic-pdf.exe_main_.py", line 7, in sys.exit(cli()) │ │ └ <Command cli> │ └ └ <module 'sys' (built-in)>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1157, in call return self.main(*args, **kwargs) │ │ │ └ {} │ │ └ () │ └ <function BaseCommand.main at 0x0000020823398A60> └ <Command cli>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1078, in main rv = self.invoke(ctx) │ │ └ <click.core.Context object at 0x00000208217E87C0> │ └ <function Command.invoke at 0x0000020823399510> └ <Command cli>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) │ │ │ │ │ └ {'path': 'C:\Users\XN963FS\Downloads\PDF-Extract-Kit', 'output_dir': 'C:\Users\XN963FS\Downloads', 'method': 'auto'} │ │ │ │ └ <click.core.Context object at 0x00000208217E87C0> │ │ │ └ <function cli at 0x0000020857363A30> │ │ └ <Command cli> │ └ <function Context.invoke at 0x0000020823398280> └ <click.core.Context object at 0x00000208217E87C0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 783, in invoke return __callback(*args, **kwargs) │ └ {'path': 'C:\Users\XN963FS\Downloads\PDF-Extract-Kit', 'output_dir': 'C:\Users\XN963FS\Downloads', 'method': 'auto'} └ ()

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\tools\cli.py", line 73, in cli parse_doc(doc_path) │ └ WindowsPath('C:/Users/XN963FS/Downloads/PDF-Extract-Kit/186e654a02c94ecf0c0800342099e8c.pdf') └ <function cli..parse_doc at 0x00000208217EC9D0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\tools\cli.py", line 60, in parse_doc do_parse( └ <function do_parse at 0x00000208237A13F0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\tools\common.py", line 65, in do_parse pipe.pipe_analyze() │ └ <function UNIPipe.pipe_analyze at 0x0000020857362E60> └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x000002085737C0D0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\pipe\UNIPipe.py", line 31, in pipe_analyze self.model_list = doc_analyze(self.pdf_bytes, ocr=True) │ │ │ │ └ b'%PDF-1.4\n%\xe2\xe3\xcf\xd3\n1 0 obj\n<<\n/CreationDate (D:20240719121335+08'00')\n/CreatorTool (PDF-XChange Standard \(... │ │ │ └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x000002085737C0D0> │ │ └ <function doc_analyze at 0x000002083B9BBD90> │ └ [] └ <magic_pdf.pipe.UNIPipe.UNIPipe object at 0x000002085737C0D0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\model\doc_analyze_by_custom_model.py", line 109, in doc_analyze custom_model = model_manager.get_model(ocr, show_log) │ │ │ └ False │ │ └ True │ └ <function ModelSingleton.get_model at 0x000002083B9BBD00> └ <magic_pdf.model.doc_analyze_by_custom_model.ModelSingleton object at 0x000002085737D780>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\model\doc_analyze_by_custom_model.py", line 63, in get_model self._models[key] = custom_model_init(ocr=ocr, show_log=show_log) │ │ │ │ │ └ False │ │ │ │ └ True │ │ │ └ <function custom_model_init at 0x000002083B9BBBE0> │ │ └ (True, False) │ └ {} └ <magic_pdf.model.doc_analyze_by_custom_model.ModelSingleton object at 0x000002085737D780>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\model\doc_analyze_by_custom_model.py", line 83, in custom_model_init from magic_pdf.model.pdf_extract_kit import CustomPEKModel

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\magic_pdf\model\pdf_extract_kit.py", line 14, in import torchtext

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torchtext_init_.py", line 18, in from torchtext import _extension # noqa: F401

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torchtext_extension.py", line 64, in _init_extension() └ <function _init_extension at 0x000002085FF03760>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torchtext_extension.py", line 58, in _init_extension _load_lib("libtorchtext") └ <function _load_lib at 0x000002085FF035B0>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torchtext_extension.py", line 50, in _load_lib torch.ops.load_library(path) │ │ │ └ WindowsPath('C:/Users/XN963FS/AppData/Local/Programs/Python/Python310/lib/site-packages/torchtext/lib/libtorchtext.pyd') │ │ └ <function _Ops.load_library at 0x000002085DA59360> │ └ <module 'torch.ops' from '_ops.py'> └ <module 'torch' from 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\init.py'>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\site-packages\torch_ops.py", line 1295, in load_library ctypes.CDLL(path) │ │ └ 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Lib\site-packages\torchtext\lib\libtorchtext.pyd' │ └ <class 'ctypes.CDLL'> └ <module 'ctypes' from 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\ctypes\init.py'>

File "C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\lib\ctypes_init_.py", line 374, in init self._handle = _dlopen(self._name, mode) │ │ │ │ │ └ 4352 │ │ │ │ └ 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Lib\site-packages\torchtext\lib\libtorchtext.pyd' │ │ │ └ <CDLL 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Lib\site-packages\torchtext\lib\libtorchtext.pyd', handle 0 a... │ │ └ <built-in function LoadLibrary> │ └ 0 └ <CDLL 'C:\Users\XN963FS\AppData\Local\Programs\Python\Python310\Lib\site-packages\torchtext\lib\libtorchtext.pyd', handle 0 a...

OSError: [WinError 127] 找不到指定的程序。