peepdf.py

#!/usr/bin/env python

import sys
from peepdf.PDFCore import PDFParser, PDFObject, PDFDictionary


def check_cyrillic_support(pdf_file):
    parser = PDFParser()
    ret, pdf = parser.parse(pdf_file)

    if ret != 0:
        print("Error parsing PDF file")
        return

    pdf_body = pdf.body[0]

    # Проверка шрифтов
    fonts = []
    cyrillic_fonts = []

    for obj in pdf_body.objects.values():
        if isinstance(obj.object, PDFDictionary):
            dict_obj = obj.object
            if '/Type' in dict_obj.elements and dict_obj.elements['/Type'].getValue() == '/Font':
                fonts.append(dict_obj)
                if '/Encoding' in dict_obj.elements:
                    encoding = dict_obj.elements['/Encoding']
                    if isinstance(encoding, PDFObject):
                        encoding = encoding.getValue()
                    if encoding in ['/Identity-H', '/WinAnsiEncoding', '/Unicode']:
                        cyrillic_fonts.append(dict_obj)

    if not cyrillic_fonts:
        print("Warning: No fonts with potential Cyrillic support found")
    else:
        print(f"Found {len(cyrillic_fonts)} fonts with potential Cyrillic support")

    # Проверка текстовых объектов
    text_objects = []
    cyrillic_text_objects = []

    for obj in pdf_body.objects.values():
        if obj.object.type == 'stream' and '/Filter' in obj.object.dictType:
            if obj.object.dictType['/Filter'].getValue() == '/FlateDecode':
                decoded_stream = obj.object.decodedStream
                if b'BT' in decoded_stream and b'ET' in decoded_stream:
                    text_objects.append(obj.object)
                    if any(0x0400 <= ord(chr(b)) <= 0x04FF for b in decoded_stream):
                        cyrillic_text_objects.append(obj.object)

    if not cyrillic_text_objects:
        print("Warning: No text objects with Cyrillic characters found")
    else:
        print(f"Found {len(cyrillic_text_objects)} text objects with Cyrillic characters")


if __name__ == "__main__":
    pdf_file = r"C:\Users\user\source\repos\PDFGenerator\PDFGenerator\bin\Debug\MediumTermLeaseAgreement.pdf"
    check_cyrillic_support(pdf_file)