me-suzy

import os

# Calea către folderul care conține imaginile
folder_path = r'e:\Carte\BB\17 - Site Leadership\Principal 2022\ro\images'

# Obținem o listă cu numele fișierelor webp din folder, fără extensie
webp_files = [os.path.splitext(filename)[0] for filename in os.listdir(folder_path) if filename.endswith('.webp')]

# Iterăm prin fișierele din folder și ștergem fișierele jpg care au același nume cu fișierele webp
for filename in os.listdir(folder_path):

me-suzy

import os

# Calea către folderul care conține imaginile
folder_path = r'e:\Carte\BB\17 - Site Leadership\Principal 2022\ro\images'

# Set pentru a stoca numele fișierelor .webp fără extensie
webp_files = set()

# Colectăm numele fișierelor .webp
for filename in os.listdir(folder_path):

me-suzy

import os
import PyPDF2
from pdfminer.high_level import extract_text
import fitz  # PyMuPDF
from PIL import Image

def print_step(step):
    print(f"\n{'='*20} {step} {'='*20}")

def repair_with_pypdf2(input_path, output_path):

me-suzy

```
https://archive.org  Internet Archive Upload PDF ERROR MESSAGE
There is a network problem

Resume Uploading
400 Bad Data (details)

<Error><Code>BadContent</Code><Message>Uploaded content is unacceptable.</Message><Resource>Syntax error detected in pdf data. You may be able to repair the pdf file with a repair tool, pdftk is one such tool.</Resource><RequestId>440a5d56-535c-4a53-9453-a6713c02b289</RequestId></Error>
```

me-suzy

import os
import PyPDF2
import requests
import json

# Funcție pentru a extrage textul din PDF
def extract_text_from_pdf(pdf_path):
    try:
        with open(pdf_path, 'rb') as file:
            reader = PyPDF2.PdfReader(file)

me-suzy

import os
import PyPDF2
import pikepdf
import requests
import fitz  # PyMuPDF

def check_and_repair_pdf(file_path):
    print(f"\nAnalizăm fișierul: {file_path}")

    # Verifică dimensiunea fișierului

me-suzy

import os

root_directory = 'j:\\PDF c\\2\\'

for folder_name, subfolders, files in os.walk(root_directory):
    for file_name in files:
        if file_name.endswith('.pdf'):
            old_path = os.path.join(folder_name, file_name)
            new_name = f"{os.path.basename(folder_name)} - {file_name}"

me-suzy

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from webdriver_manager.chrome import ChromeDriverManager
from urllib.parse import urljoin, unquote
import os

me-suzy

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from webdriver_manager.chrome import ChromeDriverManager
from urllib.parse import urljoin, unquote
import os

me-suzy

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from webdriver_manager.chrome import ChromeDriverManager
from urllib.parse import urljoin, unquote
import os