AutOmatizacionEs

				
					!python -m spacy download es_core_news_sm

import requests
from bs4 import BeautifulSoup
from collections import Counter
import json
import re
from urllib.parse import urljoin
import spacy

# Load the spaCy English model
nlp = spacy.load("en_core_web_sm")

# Load the spaCy Spanish model
nlp_es = spacy.load("es_core_news_sm")

# Function to fetch the HTML content of a page
def fetch_html(url):
  headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
  }
  response = requests.get(url, headers=headers)
  if response.status_code == 200:
      return response.text
  else:
      print(f"Failed to fetch {url}: {response.status_code}")
      return None

# Function to get total count and enumerated headings for h1, h2, and h3 tags
def analyze_structure(html):
  soup = BeautifulSoup(html, 'html.parser')
  headings = {}
  for tag in ["h1", "h2", "h3"]:
    elements = soup.find_all(tag)
    headings[tag] = {
        "total_count": len(elements),
        "headings_list": [{"text": element.text, "index": index + 1} for index, element in enumerate(elements)]
    }
  return {"headings": headings}

# Function to analyze basic SEO
def analyze_seo(html):
  soup = BeautifulSoup(html, 'html.parser')
  title = soup.find('title').text if soup.find('title') else None
  meta_description = soup.find('meta', attrs={'name': 'description'})
  meta_description_content = meta_description['content'] if meta_description and 'content' in meta_description.attrs else None
  return {"title": title, "meta_description": meta_description_content}

'''
# Function to analyze main CTAs
def analyze_ctas(html):
  soup = BeautifulSoup(html, 'html.parser')
  ctas = []
  for tag in soup.find_all(['a', 'button']):
    text = tag.text.strip()
    if text and any(keyword in text.lower() for keyword in ["comprar ahora", "más información", "buy now", "learn more"]):  # Keywords for CTAs
      ctas.append({"text": text, "location": tag.name}) # Add location (a or button)
  return {"ctas": ctas}
'''

# Function to analyze multimedia usage
def analyze_multimedia(html):
  soup = BeautifulSoup(html, 'html.parser')
  images = soup.find_all("img")
  videos = soup.find_all("video")
  images_with_alt = len([img for img in images if img.get("alt")])
  return {"images_count": len(images), "videos_count": len(videos), "images_with_alt": images_with_alt}

# Function to analyze links and pages
def analyze_links(html, base_url):
    soup = BeautifulSoup(html, 'html.parser')
    links = []
    for a_tag in soup.find_all('a', href=True):
        absolute_url = urljoin(base_url, a_tag['href'])
        if absolute_url.startswith(base_url) and absolute_url not in links: # Only internal and unique links
            links.append(absolute_url)
    return {"total_links": len(links), "links_list": links}

# Explicit list of custom stopwords
stop_words_manual = set([
    'el', 'la', 'los', 'las', 'un', 'una', 'unos', 'unas', 'del', 'de la', 'a la', 'al', 'yo', 'tú', 'él', 
    'ella', 'nosotros', 'nosotras', 'vosotros', 'vosotras', 'ellos', 'ellas', 'me', 'te', 'lo', 'la', 'le', 
    'nos', 'os', 'les', 'se', 'mi', 'tu', 'su', 'nuestro', 'vuestra', 'estas', 'esas', 'aquellas', 'quien', 
    'quienes', 'a', 'ante', 'bajo', 'con', 'contra', 'de', 'desde', 'en', 'entre', 'hacia', 'hasta', 'para', 
    'por', 'según', 'sin', 'sobre', 'tras', 'durante', 'a través de', 'en frente de', 'y', 'o', 'pero', 'sino', 
    'aunque', 'porque', 'pues', 'ni', 'cuando', 'como', 'que', 'si', 'además', 'ya que', 'entonces', 'mientras', 
    'para que', 'muy', 'bien', 'mal', 'tanto', 'poco', 'mucho', 'más', 'menos', 'ya', 'aquí', 'allí', 'ahora', 
    'entonces', 'nunca', 'siempre', 'casi', 'todo', 'algo', 'ser', 'estar', 'haber', 'tener', 'hacer', 'poder', 
    'deber', 'venir', 'ir', 'lo', 'la', 'las', 'los', 'esto', 'eso', 'aquello', 'cuál', 'quien', 'cuya', 'cuyas', 
    'todos', 'todas', 'alguno', 'alguna', 'algunos', 'algunas', 'sus', 'está', 'están', 'es'
])

# Function to analyze content and extract key concepts
def analyze_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    text = soup.get_text()

     # Detect language
    try:
        language = detect(text)
    except:
        language = 'es'  # Default to Spanish if detection fails

    # Choose the appropriate spaCy model
    nlp = nlp_es if language == 'es' else nlp_en

    # Process the text with spaCy
    doc = nlp(text)

    # Filter out stop words, punctuation, and functional words
    filtered_words = [
        token.text.lower() for token in doc
        if token.is_alpha and not token.is_stop and token.text.lower() not in stop_words_manual
    ]

    # Calculate keyword frequencies
    keyword_counts = Counter(filtered_words)

    # Get top 10 most frequent keywords
    top_keywords = keyword_counts.most_common(10)

    return {"word_count": len(doc), "top_keywords": top_keywords}


# Function to analyze a single URL (modified)
def analyze_url(url):
    html = fetch_html(url)
    if not html:
        return None

    structure = analyze_structure(html)
    seo = analyze_seo(html)
    #ctas = analyze_ctas(html)
    multimedia = analyze_multimedia(html)
    readability = analyze_content(html)  # Call the modified analyze_content function
    links = analyze_links(html, url)  # Analyze links and pages

    return {
        "url": url,
        "structure": structure,
        "seo": seo,
       #"ctas": ctas,
        "multimedia": multimedia,
        "readability": readability,  # Updated readability section
        "links": links  # Added links section
    }

# Function to analyze multiple URLs and generate a report
def generate_report(urls):
  report = []
  for url in urls:
      print(f"Analyzing {url}...")
      result = analyze_url(url)
      if result:
          report.append(result)

  # Save report to JSON
  with open("benchmark_report.json", "w", encoding="utf-8") as f:
      json.dump(report, f, ensure_ascii=False, indent=4)

  print("Report generated: benchmark_report.json")

# Main function to execute the script
def main():
  urls = [
      "https://www.marca.com/"
  ]  # Replace with your list of URLs
  generate_report(urls)

if __name__ == "__main__":
  main()

# Main function to execute the script
def main():
  urls = [
      "https://www.marca.com/"
  ]  # Replace with your list of URLs
  generate_report(urls)

if __name__ == "__main__":
  main()
  
with open('benchmark_report.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

# Imprime el contenido formateado:
print(json.dumps(data, indent=4, ensure_ascii=False))