python-office
python-office copied to clipboard
pdf转word提示字体错误
[INFO] Start to convert C:\Users\zspym\Desktop\PyQt6 Python桌面开发.pdf
[INFO] [1/4] Opening document...
[INFO] [2/4] Analyzing document...
Traceback (most recent call last):
File "D:\python\tools\app\view\ocr_ofd_to_pdf_ui.py", line 33, in doTransfor
popdf.pdf2docx(file_path=r''+self.fname,output_path=r''+newfile)
File "D:\installed\Python311\Lib\site-packages\popdf\api\pdf.py", line 70, in pdf2docx
mainPDF.pdf2docx(file_path, output_path)
File "D:\installed\Python311\Lib\site-packages\popdf\core\PDFType.py", line 86, in pdf2docx
cv.convert(word_path)
File "D:\installed\Python311\Lib\site-packages\pdf2docx\converter.py", line 329, in convert
self.parse(start, end, pages, **settings).make_docx(docx_filename, **settings)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\converter.py", line 112, in parse
return self.load_pages(start, end, pages)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\converter.py", line 153, in parse_document
self._pages.parse(self.fitz_doc, **kwargs)
File "D:\installed\Python311\Lib\site-packages\pdf2docx\page\Pages.py", line 37, in parse
raw_page.restore(**settings)
File "D:\installed\Python311\Lib\site-packages\pdf2docx\common\share.py", line 226, in inner
objects = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\page\RawPage.py", line 67, in restore
super().restore(raw_dict)
File "D:\installed\Python311\Lib\site-packages\pdf2docx\layout\Layout.py", line 74, in restore
self.blocks.restore(data.get('blocks', []))
File "D:\installed\Python311\Lib\site-packages\pdf2docx\layout\Blocks.py", line 98, in restore
block = TextBlock(raw_block)
^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\TextBlock.py", line 49, in init
self.lines = Lines(parent=self).restore(raw.get('lines', []))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\Lines.py", line 31, in restore
line = Line(raw)
^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\Line.py", line 54, in init
self.spans = Spans(parent=self).restore(raw.get('spans', []))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\Spans.py", line 19, in restore
span = TextSpan(raw_span)
^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\TextSpan.py", line 78, in init
self._change_font_and_update_bbox(constants.DEFAULT_FONT_NAME)
File "D:\installed\Python311\Lib\site-packages\pdf2docx\text\TextSpan.py", line 121, in _change_font_and_update_bbox
font = fitz.Font(font_name)
^^^^^^^^^^^^^^^^^^^^
File "D:\installed\Python311\Lib\site-packages\fitz\fitz.py", line 9404, in init
_fitz.Font_swiginit(self, _fitz.new_Font(fontname, fontfile, fontbuffer, script, language, ordering, is_bold, is_italic, is_serif, embed))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: cannot find builtin font with name 'Arial'
python 3.11 ,win11x64开发环境
上游库 pdf2docx
的问题,已在0.5.7
版本中修复。
pip install pdf2docx --upgrade