GPT

Mode

from PyPDF2 import PdfReader import re def extracttextbypage(pdfpath): Initialize the PDF reader reader = PdfReader(pdfpath) segments = [] Iterate through each page, clean text, and store in the segments list for

Prompt text

Original English text. Replace placeholders with your own details.

from PyPDF2 import PdfReader
import re

def extract_text_by_page(pdf_path):
 # Initialize the PDF reader
 reader = PdfReader(pdf_path)
 segments = []
 
 # Iterate through each page, clean text, and store in the segments list
 for page in reader.pages:
 page_text = page.extract_text() if page.extract_text() else ""
 # Clean the text for each page using the defined regex pattern
 strict_pattern = r'[\u4e00-\u9fff\u3040-\u30ff\uAC00-\uD7A3\u0370-\u03ff\u0400-\u04FFa-zA-Z\s0-9]'
 cleaned_page_text = re.findall(strict_pattern, page_text)
 cleaned_page_text = ''.join(cleaned_page_text)
 cleaned_page_text = re.sub(r'\s+', ' ', cleaned_page_text)
 # Add the cleaned text of the current page to the segments list
 segments.append(cleaned_page_text)
 
 return segments

# Extract text by page and store in segments list
segments = extract_text_by_page(pdf_path)

# Display the number of pages (segments) and all the text of the first page for verification (max 16000)
len(segments), segments[0][:16000]

Source & attribution

Awesome Prompts · Awesome Prompts

Source-listed license: GPL-3.0. Prompt text is preserved; titles and previews may be shortened for display. Source examples are not NexGateHub test results.

View original source ↗ · Source credits & licenses

Explore more prompts →