def extract_text_from_pdf(file_path): pdf_file_obj = open(file_path, 'rb') pdf_reader = PyPDF2.PdfFileReader(pdf_file_obj) num_pages = pdf_reader.numPages text = '' for page in range(num_pages): page_obj = pdf_reader.getPage(page) text += page_obj.extractText() pdf_file_obj.close() return text
def extract_text_from_pdf(file_path): pdf_file_obj = open(file_path, 'rb') pdf_reader = PyPDF2.PdfFileReader(pdf_file_obj) num_pages = pdf_reader.numPages text = '' for page in range(num_pages): page_obj = pdf_reader.getPage(page) text += page_obj.extractText() pdf_file_obj.close() return text
