Блог

Я хочу добавить только проанализированные строки, которые имеют меньшее coord значение, чем 780 .

 directory = 'C:/Users/'
data = []
for file in os.listdir(directory):
    if not file.endswith(".pdf"):
        continue
    fake_file_handle = io.StringIO()


    with open(os.path.join(directory, file), 'rb') as fh:
        resource_manager = PDFResourceManager()
        laparams = LAParams(line_margin = 0.6)
        device = PDFPageAggregator(resource_manager, laparams = laparams)
        page_interpreter = PDFPageInterpreter(resource_manager, device)

        sizes = []
        fonts = []
        positions = []
        raw_text = []
        for page in PDFPage.get_pages(fh, caching=True, check_extractable=True):
            page_interpreter.process_page(page)
            text = fake_file_handle.getvalue()
            layout = device.get_result()
            for lobj in layout:
                if isinstance(lobj, LTTextBoxHorizontal):
                    coord, word = int(lobj.bbox[1]), lobj.get_text().strip()
                    raw_text.append([coord, word])
                    for text_line in lobj:
                        for character in text_line:
                            if isinstance(character, LTChar):
                                Font_size = character.size
                                Font_name = character.fontname[7:]
                                if character.matrix[0]>0 :
                                    position = character.bbox  # font-positon
                        sizes.append(Font_size)
                        fonts.append(Font_name)
                        positions.append(position)

        # filter those elements below coord=780.000 coordinate
        font_pos = []
        maxFontpos = int(780)
        for coord, word in enumerate(raw_text):
            if coord <= maxFontpos:
                font_pos.append(word)
            else:
                pass
        
        #strings = []
        #for i in font_pos:
        #    strings.append(word[i])

    data.append([Font_size, Font_name, font_pos])
    converter.close()
    fake_file_handle.close()
    
df1 = pd.DataFrame(data, columns =['Font_size', 'Font_name', 'text'])
 

дает мне этот список списков, в котором все еще есть символы с координатами больше 780, а именно 788 : 791

 print(df1.iloc[0]['text'])

[[778, 'text i want to keep'], 
[776, 'text i want to keep'], 
[546, 'text i want to keep'], 
[510, 'text i want to keep'], 
[174, 'text i want to keep'], 
[79, 'text i want to keep'], 
[48, 'text i want to keep'], 
[34, 'text i want to keep'], 
[788, 'text i dont want to keep'], 
[791, 'text i dont want to keep'], 
[735, 'text i want to keep'], 
[675, 'text i want to keep'], 
[651, 'text i want to keep']]
 

Вопрос: Почему этот фрагмент кода

     font_pos = []
    maxFontpos = int(780)
    for coord, word in enumerate(raw_text):
        if coord <= maxFontpos:
            font_pos.append(word)
        else:
            pass
    
data.append([Font_size, Font_name, font_pos])
 

не работает так, как задумывалось?

Не используйте enumerate , попробуйте это вживую:

 font_pos = []
maxFontpos = 780
for coord, word in raw_text:
    if coord <= maxFontpos:
        font_pos.append(word)
    else:
        pass