extract_word_from_pdf

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.layout import LAParams, LTTextBox, LTTextLine
from pdfminer.converter import PDFPageAggregator

def pdf2txt(one_file,target_regex=None):
    password = ""

    fp = open(one_file, "rb")
    parser = PDFParser(fp)
    document = PDFDocument(parser, password)
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed

    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    whole_extracted_text = ""
    for page in PDFPage.create_pages(document):
        interpreter.process_page(page)
        layout = device.get_result()
        for lt_obj in layout:
            if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
                extracted_text = lt_obj.get_text()
                if target_regex is not None:
                    target_content = target_regex.sub(' ', extracted_text)
                else:
                    target_content = extracted_text
                whole_extracted_text += target_content
    fp.close()
    return whole_extracted_text

def read_txt(txt_filepath):
    with open(txt_filepath, "r", encoding='utf-8') as f:
        content = f.read()
    return content

print(pdf2txt('/Users/ypi/Desktop/Tiktok.pdf'))