ค้นหา PDF ผ่าน Python

import aspose.pdf as apdf

from os import path
path_infile = path.join(self.data_dir, infile)

document = apdf.Document(path_infile)

# Create TextAbsorber object to find all instances of the input search phrase
textFragmentAbsorber = apdf.text.TextFragmentAbsorber("PDF")

# Accept the absorber for all the pages
document.pages.accept(textFragmentAbsorber)

# Loop through the fragments
for textFragment in textFragmentAbsorber.text_fragments:
    print(f"Text : {textFragment.text}" )
    print(f"Position : {textFragment.position}")
    print(f"XIndent : {textFragment.position.x_indent}")
    print(f"YIndent : {textFragment.position.y_indent}")
    print(f"Font - Name : {textFragment.text_state.font.font_name}" )
    print(f"Font - IsAccessible : {textFragment.text_state.font.is_accessible} " )
    print(f"Font - IsEmbedded : {textFragment.text_state.font.is_embedded} " )
    print(f"Font - IsSubset : {textFragment.text_state.font.is_subset} ")
    print(f"Font Size : {textFragment.text_state.font_size}" )
    print(f"Foreground Color : {textFragment.text_state.foreground_color} " )