me-suzy

import os
import regex

def remove_quotes_from_meta_tags(html_content):
    # Pattern pentru <meta name="description" content="...">
    pattern1 = regex.compile(r'(<meta name="description" content=")(.*?)(">)', regex.DOTALL)
    
    # Pattern pentru <meta property="og:description" content="...">
    pattern2 = regex.compile(r'(<meta property="og:description" content=")(.*?)(">)', regex.DOTALL)
    

me-suzy

import os
import regex

def remove_quotes_from_meta_tags(html_content):
    # Pattern pentru <meta name="description" content="...">
    pattern1 = regex.compile(r'(<meta name="description" content=")(.*?)(">)', regex.DOTALL)

    # Pattern pentru <meta property="og:description" content="...">
    pattern2 = regex.compile(r'(<meta property="og:description" content=")(.*?)(">)', regex.DOTALL)

me-suzy

import re
import os

def replace_headers_in_html(file_path):
    # Read the content of the HTML file
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()

    # Store original content for comparison
    original_content = content

me-suzy

import re
import os

def replace_headers_in_html(file_path):
    # Read the content of the HTML file
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()

    # Store original content for comparison
    original_content = content

me-suzy

import os
import requests
from bs4 import BeautifulSoup, Comment
import time

def get_image_from_local_file(file_path):
    """Extrage imaginea din fișierul HTML local"""
    try:
        if not os.path.exists(file_path):
            return None, None

me-suzy

import os
import requests
from bs4 import BeautifulSoup, Comment
import time

def get_image_from_article_page(url):
    """Extrage imaginea din pagina individuală"""
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'

me-suzy

import os
import requests
from bs4 import BeautifulSoup, Comment
import time
import re

def get_image_from_article_page(url):
    """Extrage imaginea din pagina individuală a articolului"""
    try:
        headers = {

me-suzy

import json

json_data = [
    {
        "html_file": "lideri-si-atitudine.html",
        "line_count": 37,
        "title_links": 37,
        "read_more_links": 37,
        "repeated_links": {}
    },

me-suzy

Ai dreptate, se duplică conținutul. Iată soluția corectă - să ascund complet secțiunea desktop pe mobil:

## HTML simplificat:

```html
<article class="blog-box heading-space-half">
    <div class="blog-listing-inner news_item">
        <div class="article-card-new">
            
            <!-- Layout DESKTOP - ascuns pe mobil -->

me-suzy

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
This script sends the given command-line arguments as a query to the running
DocFetcher instance. The results returned by the latter are printed as filename-
filepath pairs on the standard output.

For more advanced processing of the results, call the search function below
directly. In principle, you can also reuse the code in the search function for