Spaces:
Runtime error
Runtime error
| #!pip install gradio | |
| import gradio as gr | |
| def read_pdf(pdf_path): | |
| # create a PDF file object | |
| pdfFileObj = open(pdf_path, 'rb') | |
| # create a PDF reader object | |
| pdfReader = PyPDF2.PdfReader(pdfFileObj) | |
| # Create the dictionary to extract text from each page | |
| text_per_page = {} | |
| # We extract the pages from the PDF | |
| for pagenum, page in enumerate(extract_pages(pdf_path)): | |
| # Initialize the variables needed for the text extraction from the page | |
| pageObj = pdfReader.pages[pagenum] | |
| page_text = [] | |
| line_format = [] | |
| text_from_images = [] | |
| text_from_tables = [] | |
| page_content = [] | |
| # Initialize the number of the examined tables | |
| table_num = 0 | |
| first_element= True | |
| table_extraction_flag= False | |
| # Open the pdf file | |
| pdf = pdfplumber.open(pdf_path) | |
| # Find the examined page | |
| page_tables = pdf.pages[pagenum] | |
| # Find the number of tables on the page | |
| tables = page_tables.find_tables() | |
| # Find all the elements | |
| page_elements = [(element.y1, element) for element in page._objs] | |
| # Sort all the elements as they appear in the page | |
| page_elements.sort(key=lambda a: a[0], reverse=True) | |
| # Find the elements that composed a page | |
| for i, component in enumerate(page_elements): | |
| # Extract the position of the top side of the element in the PDF | |
| pos = component[0] | |
| # Extract the element of the page layout | |
| element = component[1] | |
| # Check if the element is a text element | |
| if isinstance(element, LTTextContainer): | |
| # Check if the text appeared in a table | |
| if table_extraction_flag == False: | |
| # Use the function to extract the text and format for each text element | |
| (line_text, format_per_line) = text_extraction(element) | |
| # Append the text of each line to the page text | |
| page_text.append(line_text) | |
| # Append the format for each line containing text | |
| line_format.append(format_per_line) | |
| page_content.append(line_text) | |
| else: | |
| # Omit the text that appeared in a table | |
| pass | |
| # Create the key of the dictionary | |
| dctkey = 'Page_'+str(pagenum) | |
| # Add the list of list as the value of the page key | |
| text_per_page[dctkey] = [page_text, line_format, text_from_images, text_from_tables, page_content] | |
| # Closing the pdf file object | |
| pdfFileObj.close() | |
| return text_per_page | |
| pdf_path = '/content/Article 11 Hidden Technical Debt in Machine Learning Systems.pdf' | |
| text_per_page = read_pdf(pdf_path) | |
| Page_0 = text_per_page['Page_0'] | |
| def nested_list_to_string(nested_list): | |
| result = '' | |
| for element in nested_list: | |
| if isinstance(element, list): # Check if the element is a list | |
| result += nested_list_to_string(element) # Recursively process the list | |
| elif isinstance(element, str): # Check if the element is a string | |
| result += element # Append the string to the result | |
| return result | |
| Page_0 = text_per_page['Page_0'] | |
| string_result = nested_list_to_string(Page_0) | |
| def extract_abstract(page_0): | |
| def nested_list_to_string(nested_list): | |
| result = '' | |
| for element in nested_list: | |
| if isinstance(element, list): # Check if the element is a list | |
| result += nested_list_to_string(element) # Recursively process the list | |
| elif isinstance(element, str): # Check if the element is a string | |
| result += element # Append the string to the result | |
| return result | |
| # Convert the nested list into a single string | |
| full_text = nested_list_to_string(page_0) | |
| # Find the start of the 'Abstract' section and the end of it (start of 'Introduction') | |
| start_index = full_text.find('Abstract') | |
| end_index = full_text.find('Introduction') | |
| # If both 'Abstract' and 'Introduction' are found, extract the text in between | |
| if start_index != -1 and end_index != -1: | |
| # Extract the text and remove the word 'Abstract' | |
| abstract_text = full_text[start_index + len('Abstract'):end_index] | |
| return abstract_text.strip() | |
| else: | |
| return "Abstract or Introduction section not found." | |
| # Example usage | |
| Page_0 = text_per_page['Page_0'] | |
| abstract_text = extract_abstract(Page_0) | |
| wall_of_text = abstract_text | |
| result = summarizer( | |
| wall_of_text, | |
| min_length=1, | |
| max_length=30, | |
| no_repeat_ngram_size=3, | |
| encoder_no_repeat_ngram_size=3, | |
| repetition_penalty=3.5, | |
| num_beams=4, | |
| early_stopping=True, | |
| ) | |
| # Access the first element of the list (which is the dictionary) and then the value of 'summary_text' | |
| summary_string = result[0]['summary_text'] | |
| print(summary_string) | |
| app = gra.Interface(fn = user_greeting, inputs=summary_string, outputs=summary_string) | |
| app.launch() | |