Scribd
Upload
8 views2 pages

Extract Circle Questions from PDF

The document is a Python script that extracts questions related to 'Circle' from a specified PDF file. It uses the PyPDF2 library to read the PDF and the ReportLab library to create a new PDF containing the extracted questions. The script captures questions based on specific criteria and saves them in a new output PDF file.

Uploaded by

Anonymous YBAHVQ
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views2 pages

Extract Circle Questions from PDF

The document is a Python script that extracts questions related to 'Circle' from a specified PDF file. It uses the PyPDF2 library to read the PDF and the ReportLab library to create a new PDF containing the extracted questions. The script captures questions based on specific criteria and saves them in a new output PDF file.

Uploaded by

Anonymous YBAHVQ
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

import PyPDF2

import re
from [Link] import letter
from [Link] import canvas

def extract_circle_questions_from_pdf(pdf_path, output_pdf_path):


# Open the PDF file
with open(pdf_path, 'rb') as file:
reader = [Link](file)
total_pages = len([Link])

# List to hold extracted questions


extracted_questions = []

for page_num in range(total_pages):


page = [Link][page_num]
text = page.extract_text()

# Split the text into lines


lines = [Link]('\n')
question_text = ""
capturing_question = False

for line in lines:


# Check if the line contains "Circle", "circle", "Circles" or
"circles"
# and doesn't match the exclusion conditions
if ("Circle the" not in line and
"Circle your answer" not in line and
[Link](r'\b[Cc]ircle[s]?\b', line)):
capturing_question = True

# If we are capturing a question related to "Circle" or


"Circles", add the line to the question text
if capturing_question:
question_text += line + " "

# If the line ends with a punctuation mark, assume the


question ends here
if [Link](r'[.!?]$', [Link]()):
extracted_questions.append(question_text.strip()) #
Store the question text
question_text = ""
capturing_question = False

# Now, create a new PDF file and write extracted questions into it
create_pdf_with_questions(extracted_questions, output_pdf_path)

def create_pdf_with_questions(questions, output_pdf_path):


# Create a new PDF using reportlab
c = [Link](output_pdf_path, pagesize=letter)
width, height = letter
y_position = height - 40 # Starting y position
# Loop through each extracted question and write it to the new PDF
for question in questions:
if y_position < 40: # If there's no more space on the current page,
start a new page
[Link]()
y_position = height - 40

[Link](40, y_position, question)


y_position -= 20 # Move down for the next question

# Save the new PDF


[Link]()

# Example usage
pdf_file_path = 'C:/Personal/Python/AQA-83002H-QP-NOV18P_OCR.pdf' # Replace
with your actual PDF file path
output_pdf_path = 'C:/Personal/Python/extracted_circle_questions.pdf' # Output
PDF file path
extract_circle_questions_from_pdf(pdf_file_path, output_pdf_path)

You might also like