Update app.py
Browse files
app.py
CHANGED
@@ -1,448 +1,51 @@
|
|
1 |
-
import
|
2 |
import json
|
3 |
-
import
|
4 |
-
import
|
5 |
-
import requests
|
6 |
-
import hashlib
|
7 |
-
import PyPDF2
|
8 |
-
import numpy as np
|
9 |
-
import pandas as pd
|
10 |
-
from io import BytesIO
|
11 |
-
from typing import List, Dict, Optional, Tuple, Any
|
12 |
-
from urllib.parse import urlparse, urljoin
|
13 |
-
from concurrent.futures import ThreadPoolExecutor, as_completed
|
14 |
-
from bs4 import BeautifulSoup
|
15 |
-
from pathlib import Path
|
16 |
-
from datetime import datetime
|
17 |
-
from collections import defaultdict
|
18 |
-
from sklearn.feature_extraction.text import TfidfVectorizer
|
19 |
-
from requests.adapters import HTTPAdapter
|
20 |
-
from urllib3.util.retry import Retry
|
21 |
-
from transformers import pipeline
|
22 |
-
from sentence_transformers import SentenceTransformer
|
23 |
-
import torch
|
24 |
import subprocess
|
25 |
import sys
|
26 |
-
import
|
27 |
-
import gradio as gr
|
28 |
-
import matplotlib.pyplot as plt
|
29 |
|
30 |
-
|
31 |
-
logging.basicConfig(
|
32 |
-
level=logging.INFO,
|
33 |
-
format='%(asctime)s - %(levelname)s - %(message)s'
|
34 |
-
)
|
35 |
logger = logging.getLogger(__name__)
|
36 |
|
37 |
-
|
38 |
-
def sanitize_filename(filename: str) -> str:
|
39 |
-
"""
|
40 |
-
Sanitiza el nombre de un archivo eliminando o reemplazando caracteres no permitidos.
|
41 |
-
"""
|
42 |
-
filename = re.sub(r'[<>:"/\\|?*]', '_', filename)
|
43 |
-
filename = re.sub(r'\s+', '_', filename)
|
44 |
-
return filename
|
45 |
-
|
46 |
-
|
47 |
-
class SEOSpaceAnalyzer:
|
48 |
"""
|
49 |
-
|
50 |
"""
|
51 |
-
|
52 |
-
""
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
"""
|
57 |
-
self.max_urls = max_urls
|
58 |
-
self.max_workers = max_workers
|
59 |
-
self.session = self._configure_session()
|
60 |
-
self.models = self._load_models()
|
61 |
-
self.base_dir = Path("content_storage")
|
62 |
-
self.base_dir.mkdir(parents=True, exist_ok=True)
|
63 |
-
self.current_analysis: Dict[str, Any] = {}
|
64 |
-
|
65 |
-
def _load_models(self) -> Dict[str, Any]:
|
66 |
-
"""Carga modelos optimizados para Hugging Face y spaCy."""
|
67 |
-
try:
|
68 |
-
device = 0 if torch.cuda.is_available() else -1
|
69 |
-
logger.info("Cargando modelos NLP...")
|
70 |
-
models = {
|
71 |
-
'summarizer': pipeline("summarization", model="facebook/bart-large-cnn", device=device),
|
72 |
-
'ner': pipeline("ner", model="dslim/bert-base-NER", aggregation_strategy="simple", device=device),
|
73 |
-
'semantic': SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2'),
|
74 |
-
'spacy': spacy.load("es_core_news_lg")
|
75 |
-
}
|
76 |
-
logger.info("Modelos cargados correctamente.")
|
77 |
-
return models
|
78 |
-
except Exception as e:
|
79 |
-
logger.error(f"Error cargando modelos: {e}")
|
80 |
-
raise
|
81 |
-
|
82 |
-
def _configure_session(self) -> requests.Session:
|
83 |
-
"""Configura una sesión HTTP con reintentos y headers personalizados."""
|
84 |
-
session = requests.Session()
|
85 |
-
retry = Retry(
|
86 |
-
total=3,
|
87 |
-
backoff_factor=1,
|
88 |
-
status_forcelist=[500, 502, 503, 504],
|
89 |
-
allowed_methods=['GET', 'HEAD']
|
90 |
-
)
|
91 |
-
adapter = HTTPAdapter(max_retries=retry)
|
92 |
-
session.mount('http://', adapter)
|
93 |
-
session.mount('https://', adapter)
|
94 |
-
session.headers.update({
|
95 |
-
'User-Agent': 'Mozilla/5.0 (compatible; SEOBot/1.0)',
|
96 |
-
'Accept-Language': 'es-ES,es;q=0.9'
|
97 |
-
})
|
98 |
-
return session
|
99 |
-
|
100 |
-
def analyze_sitemap(self, sitemap_url: str) -> Tuple[Dict, List[str], Dict, Dict]:
|
101 |
-
"""
|
102 |
-
Analiza un sitemap completo, procesando URLs en paralelo y generando estadísticas, análisis de contenido, enlaces y recomendaciones SEO.
|
103 |
-
:param sitemap_url: URL del sitemap XML.
|
104 |
-
:return: Tuple con estadísticas, recomendaciones, análisis de contenido y análisis de enlaces.
|
105 |
-
"""
|
106 |
-
try:
|
107 |
-
logger.info(f"Parseando sitemap: {sitemap_url}")
|
108 |
-
urls = self._parse_sitemap(sitemap_url)
|
109 |
-
if not urls:
|
110 |
-
logger.warning("No se pudieron extraer URLs del sitemap.")
|
111 |
-
return {"error": "No se pudieron extraer URLs del sitemap"}, [], {}, {}
|
112 |
-
|
113 |
-
results: List[Dict] = []
|
114 |
-
with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
115 |
-
futures = {executor.submit(self._process_url, url): url for url in urls[:self.max_urls]}
|
116 |
-
for future in as_completed(futures):
|
117 |
-
url = futures[future]
|
118 |
-
try:
|
119 |
-
res = future.result()
|
120 |
-
results.append(res)
|
121 |
-
logger.info(f"Procesado: {url}")
|
122 |
-
except Exception as e:
|
123 |
-
logger.error(f"Error procesando {url}: {e}")
|
124 |
-
results.append({'url': url, 'status': 'error', 'error': str(e)})
|
125 |
-
|
126 |
-
self.current_analysis = {
|
127 |
-
'stats': self._calculate_stats(results),
|
128 |
-
'content_analysis': self._analyze_content(results),
|
129 |
-
'links': self._analyze_links(results),
|
130 |
-
'recommendations': self._generate_seo_recommendations(results),
|
131 |
-
'details': results, # <-- Aquí se incluyen todos los detalles individuales
|
132 |
-
'timestamp': datetime.now().isoformat()
|
133 |
-
}
|
134 |
-
return (self.current_analysis['stats'],
|
135 |
-
self.current_analysis['recommendations'],
|
136 |
-
self.current_analysis['content_analysis'],
|
137 |
-
self.current_analysis['links']),
|
138 |
-
except Exception as e:
|
139 |
-
logger.error(f"Error en análisis: {e}")
|
140 |
-
return {"error": str(e)}, [], {}, {}
|
141 |
-
|
142 |
-
def _process_url(self, url: str) -> Dict:
|
143 |
-
"""Procesa una URL individual y decide el método de procesamiento según el tipo de contenido."""
|
144 |
-
try:
|
145 |
-
response = self.session.get(url, timeout=15)
|
146 |
-
response.raise_for_status()
|
147 |
-
content_type = response.headers.get('Content-Type', '')
|
148 |
-
result: Dict[str, Any] = {'url': url, 'status': 'success'}
|
149 |
-
|
150 |
-
if 'application/pdf' in content_type:
|
151 |
-
result.update(self._process_pdf(response.content))
|
152 |
-
elif 'text/html' in content_type:
|
153 |
-
result.update(self._process_html(response.text, url))
|
154 |
-
else:
|
155 |
-
result.update({'type': 'unknown', 'content': '', 'word_count': 0})
|
156 |
-
|
157 |
-
self._save_content(url, response.content)
|
158 |
-
return result
|
159 |
-
except requests.exceptions.RequestException as e:
|
160 |
-
logger.warning(f"Error procesando {url}: {str(e)}")
|
161 |
-
return {'url': url, 'status': 'error', 'error': str(e)}
|
162 |
-
except Exception as e:
|
163 |
-
logger.error(f"Error inesperado en {url}: {str(e)}")
|
164 |
-
return {'url': url, 'status': 'error', 'error': str(e)}
|
165 |
-
|
166 |
-
def _process_html(self, html: str, base_url: str) -> Dict:
|
167 |
-
"""Procesa contenido HTML: extrae y limpia el texto, enlaces y metadatos."""
|
168 |
-
soup = BeautifulSoup(html, 'html.parser')
|
169 |
-
clean_text = self._clean_text(soup.get_text())
|
170 |
-
return {
|
171 |
-
'type': 'html',
|
172 |
-
'content': clean_text,
|
173 |
-
'word_count': len(clean_text.split()),
|
174 |
-
'links': self._extract_links(soup, base_url),
|
175 |
-
'metadata': self._extract_metadata(soup)
|
176 |
-
}
|
177 |
-
|
178 |
-
def _process_pdf(self, content: bytes) -> Dict:
|
179 |
-
"""Procesa documentos PDF extrayendo texto de cada página."""
|
180 |
-
try:
|
181 |
-
text = ""
|
182 |
-
with BytesIO(content) as pdf_file:
|
183 |
-
reader = PyPDF2.PdfReader(pdf_file)
|
184 |
-
for page in reader.pages:
|
185 |
-
extracted = page.extract_text()
|
186 |
-
text += extracted if extracted else ""
|
187 |
-
clean_text = self._clean_text(text)
|
188 |
-
return {
|
189 |
-
'type': 'pdf',
|
190 |
-
'content': clean_text,
|
191 |
-
'word_count': len(clean_text.split()),
|
192 |
-
'page_count': len(reader.pages)
|
193 |
-
}
|
194 |
-
except PyPDF2.PdfReadError as e:
|
195 |
-
logger.error(f"Error leyendo PDF: {e}")
|
196 |
-
return {'type': 'pdf', 'error': str(e)}
|
197 |
-
|
198 |
-
def _clean_text(self, text: str) -> str:
|
199 |
-
"""Realiza la limpieza y normalización del texto."""
|
200 |
-
if not text:
|
201 |
-
return ""
|
202 |
-
text = re.sub(r'\s+', ' ', text)
|
203 |
-
return re.sub(r'[^\w\sáéíóúñÁÉÍÓÚÑ]', ' ', text).strip()
|
204 |
-
|
205 |
-
def _extract_links(self, soup: BeautifulSoup, base_url: str) -> List[Dict]:
|
206 |
-
"""Extrae y clasifica enlaces presentes en el HTML."""
|
207 |
-
links: List[Dict] = []
|
208 |
-
base_netloc = urlparse(base_url).netloc
|
209 |
-
|
210 |
-
for tag in soup.find_all('a', href=True):
|
211 |
-
try:
|
212 |
-
href = tag['href'].strip()
|
213 |
-
if not href or href.startswith('javascript:'):
|
214 |
-
continue
|
215 |
-
full_url = urljoin(base_url, href)
|
216 |
-
parsed = urlparse(full_url)
|
217 |
-
links.append({
|
218 |
-
'url': full_url,
|
219 |
-
'type': 'internal' if parsed.netloc == base_netloc else 'external',
|
220 |
-
'anchor': self._clean_text(tag.get_text())[:100],
|
221 |
-
'file_type': self._get_file_type(parsed.path)
|
222 |
-
})
|
223 |
-
except Exception as e:
|
224 |
-
logger.warning(f"Error procesando enlace {tag.get('href')}: {e}")
|
225 |
-
continue
|
226 |
-
return links
|
227 |
-
|
228 |
-
def _get_file_type(self, path: str) -> str:
|
229 |
-
"""Determina el tipo de archivo según la extensión encontrada en la URL."""
|
230 |
-
ext = Path(path).suffix.lower()
|
231 |
-
return ext[1:] if ext else 'html'
|
232 |
-
|
233 |
-
def _extract_metadata(self, soup: BeautifulSoup) -> Dict:
|
234 |
-
"""Extrae metadatos relevantes para SEO (título, descripción, keywords y etiquetas OpenGraph)."""
|
235 |
-
metadata: Dict[str, Any] = {
|
236 |
-
'title': '',
|
237 |
-
'description': '',
|
238 |
-
'keywords': [],
|
239 |
-
'og': {}
|
240 |
-
}
|
241 |
-
if soup.title and soup.title.string:
|
242 |
-
metadata['title'] = soup.title.string.strip()[:200]
|
243 |
-
|
244 |
-
for meta in soup.find_all('meta'):
|
245 |
-
name = meta.get('name', '').lower()
|
246 |
-
property_ = meta.get('property', '').lower()
|
247 |
-
content = meta.get('content', '')
|
248 |
-
if name == 'description':
|
249 |
-
metadata['description'] = content[:300]
|
250 |
-
elif name == 'keywords':
|
251 |
-
metadata['keywords'] = [kw.strip() for kw in content.split(',') if kw.strip()]
|
252 |
-
elif property_.startswith('og:'):
|
253 |
-
metadata['og'][property_[3:]] = content
|
254 |
-
return metadata
|
255 |
-
|
256 |
-
def _parse_sitemap(self, sitemap_url: str) -> List[str]:
|
257 |
-
"""
|
258 |
-
Parsea un sitemap XML e incluso maneja índices de sitemaps.
|
259 |
-
:return: Lista de URLs encontradas en el sitemap.
|
260 |
-
"""
|
261 |
-
try:
|
262 |
-
response = self.session.get(sitemap_url, timeout=10)
|
263 |
-
response.raise_for_status()
|
264 |
-
|
265 |
-
if 'xml' not in response.headers.get('Content-Type', ''):
|
266 |
-
logger.warning(f"El sitemap no parece ser XML: {sitemap_url}")
|
267 |
-
return []
|
268 |
-
|
269 |
-
soup = BeautifulSoup(response.text, 'lxml-xml')
|
270 |
-
urls: List[str] = []
|
271 |
-
# Manejo de sitemap index
|
272 |
-
if soup.find('sitemapindex'):
|
273 |
-
for sitemap in soup.find_all('loc'):
|
274 |
-
url = sitemap.text.strip()
|
275 |
-
if url.endswith('.xml'):
|
276 |
-
urls.extend(self._parse_sitemap(url))
|
277 |
-
else:
|
278 |
-
urls = [loc.text.strip() for loc in soup.find_all('loc')]
|
279 |
-
# Filtrar URLs que empiezan por http y eliminar duplicados
|
280 |
-
filtered_urls = list({url for url in urls if url.startswith('http')})
|
281 |
-
return filtered_urls
|
282 |
-
except Exception as e:
|
283 |
-
logger.error(f"Error al parsear el sitemap {sitemap_url}: {e}")
|
284 |
-
return []
|
285 |
-
|
286 |
-
def _save_content(self, url: str, content: bytes) -> None:
|
287 |
-
"""
|
288 |
-
Almacena el contenido descargado en una estructura organizada. Antes de escribir, verifica si ya existe el archivo.
|
289 |
-
"""
|
290 |
-
try:
|
291 |
-
parsed = urlparse(url)
|
292 |
-
domain_dir = self.base_dir / parsed.netloc
|
293 |
-
# Construir ruta a partir de la ruta URL
|
294 |
-
path = parsed.path.lstrip('/')
|
295 |
-
if not path or path.endswith('/'):
|
296 |
-
path = os.path.join(path, 'index.html')
|
297 |
-
safe_path = sanitize_filename(path)
|
298 |
-
save_path = domain_dir / safe_path
|
299 |
-
save_path.parent.mkdir(parents=True, exist_ok=True)
|
300 |
-
|
301 |
-
# Calcula hash del contenido y evita re-escribir si el archivo existe y es idéntico
|
302 |
-
new_hash = hashlib.md5(content).hexdigest()
|
303 |
-
if save_path.exists():
|
304 |
-
with open(save_path, 'rb') as f:
|
305 |
-
existing_content = f.read()
|
306 |
-
existing_hash = hashlib.md5(existing_content).hexdigest()
|
307 |
-
if new_hash == existing_hash:
|
308 |
-
logger.debug(f"El contenido de {url} ya está guardado y es idéntico.")
|
309 |
-
return
|
310 |
-
|
311 |
-
with open(save_path, 'wb') as f:
|
312 |
-
f.write(content)
|
313 |
-
logger.info(f"Contenido guardado en: {save_path}")
|
314 |
-
except Exception as e:
|
315 |
-
logger.error(f"Error al guardar contenido para {url}: {e}")
|
316 |
-
|
317 |
-
def _calculate_stats(self, results: List[Dict]) -> Dict:
|
318 |
-
"""Calcula estadísticas básicas sobre el conjunto de resultados procesados."""
|
319 |
-
successful = [r for r in results if r.get('status') == 'success']
|
320 |
-
content_types = [r.get('type', 'unknown') for r in successful]
|
321 |
-
avg_word_count = round(np.mean([r.get('word_count', 0) for r in successful]) if successful else 0, 1)
|
322 |
-
return {
|
323 |
-
'total_urls': len(results),
|
324 |
-
'successful': len(successful),
|
325 |
-
'failed': len(results) - len(successful),
|
326 |
-
'content_types': pd.Series(content_types).value_counts().to_dict(),
|
327 |
-
'avg_word_count': avg_word_count,
|
328 |
-
'failed_urls': [r['url'] for r in results if r.get('status') != 'success']
|
329 |
-
}
|
330 |
-
|
331 |
-
def _analyze_content(self, results: List[Dict]) -> Dict:
|
332 |
-
"""
|
333 |
-
Analiza el contenido extraído usando TF-IDF y muestra algunas muestras.
|
334 |
-
:return: Diccionario con keywords y ejemplos de contenido.
|
335 |
-
"""
|
336 |
-
successful = [r for r in results if r.get('status') == 'success' and r.get('content')]
|
337 |
-
texts = [r['content'] for r in successful if len(r['content'].split()) > 10]
|
338 |
-
if not texts:
|
339 |
-
return {'top_keywords': [], 'content_samples': []}
|
340 |
try:
|
341 |
-
|
342 |
-
|
343 |
-
|
344 |
-
|
345 |
-
|
346 |
-
|
347 |
-
|
348 |
-
|
349 |
-
|
350 |
-
|
351 |
-
'top_keywords': top_keywords,
|
352 |
-
'content_samples': [{'url': r['url'], 'sample': (r['content'][:500] + '...') if len(r['content']) > 500 else r['content']}
|
353 |
-
for r in successful[:3]]
|
354 |
-
}
|
355 |
-
|
356 |
-
def _analyze_links(self, results: List[Dict]) -> Dict:
|
357 |
-
"""
|
358 |
-
Analiza la estructura de enlaces en el contenido procesado.
|
359 |
-
:return: Estadísticas de enlaces internos, dominios externos, anclas y tipos de archivos.
|
360 |
-
"""
|
361 |
-
all_links = []
|
362 |
-
for result in results:
|
363 |
-
if result.get('links'):
|
364 |
-
all_links.extend(result['links'])
|
365 |
-
if not all_links:
|
366 |
-
return {
|
367 |
-
'internal_links': {},
|
368 |
-
'external_domains': {},
|
369 |
-
'common_anchors': {},
|
370 |
-
'file_types': {}
|
371 |
-
}
|
372 |
-
df = pd.DataFrame(all_links)
|
373 |
-
return {
|
374 |
-
'internal_links': df[df['type'] == 'internal']['url'].value_counts().head(20).to_dict(),
|
375 |
-
'external_domains': df[df['type'] == 'external']['url']
|
376 |
-
.apply(lambda x: urlparse(x).netloc)
|
377 |
-
.value_counts().head(10).to_dict(),
|
378 |
-
'common_anchors': df['anchor'].value_counts().head(10).to_dict(),
|
379 |
-
'file_types': df['file_type'].value_counts().to_dict()
|
380 |
-
}
|
381 |
-
|
382 |
-
def _generate_seo_recommendations(self, results: List[Dict]) -> List[str]:
|
383 |
-
"""
|
384 |
-
Genera recomendaciones SEO basadas en metadatos, cantidad de contenido y estructura de enlaces.
|
385 |
-
:return: Lista de recomendaciones.
|
386 |
-
"""
|
387 |
-
successful = [r for r in results if r.get('status') == 'success']
|
388 |
-
if not successful:
|
389 |
-
return ["No se pudo analizar ningún contenido exitosamente"]
|
390 |
-
|
391 |
-
recs = []
|
392 |
-
missing_titles = sum(1 for r in successful if not r.get('metadata', {}).get('title'))
|
393 |
-
if missing_titles:
|
394 |
-
recs.append(f"📌 Añadir títulos a {missing_titles} páginas")
|
395 |
-
short_descriptions = sum(1 for r in successful if not r.get('metadata', {}).get('description'))
|
396 |
-
if short_descriptions:
|
397 |
-
recs.append(f"📌 Añadir meta descripciones a {short_descriptions} páginas")
|
398 |
-
short_content = sum(1 for r in successful if r.get('word_count', 0) < 300)
|
399 |
-
if short_content:
|
400 |
-
recs.append(f"📝 Ampliar contenido en {short_content} páginas (menos de 300 palabras)")
|
401 |
-
|
402 |
-
all_links = [link for r in results for link in r.get('links', [])]
|
403 |
-
if all_links:
|
404 |
-
df_links = pd.DataFrame(all_links)
|
405 |
-
internal_links = df_links[df_links['type'] == 'internal']
|
406 |
-
if len(internal_links) > 100:
|
407 |
-
recs.append(f"🔗 Optimizar estructura de enlaces internos ({len(internal_links)} enlaces)")
|
408 |
-
return recs if recs else ["✅ No se detectaron problemas críticos de SEO"]
|
409 |
-
|
410 |
-
def _plot_internal_links(self, links_data: Dict) -> Optional[plt.Figure]:
|
411 |
-
"""
|
412 |
-
Genera un gráfico de barras para la distribución de enlaces internos.
|
413 |
-
:param links_data: Diccionario con los enlaces internos.
|
414 |
-
:return: Figura de matplotlib o None si no hay datos.
|
415 |
-
"""
|
416 |
-
internal_links = links_data.get('internal_links', {})
|
417 |
-
if not internal_links:
|
418 |
-
return None
|
419 |
-
fig, ax = plt.subplots()
|
420 |
-
names = list(internal_links.keys())
|
421 |
-
counts = list(internal_links.values())
|
422 |
-
ax.barh(names, counts)
|
423 |
-
ax.set_xlabel("Cantidad de enlaces")
|
424 |
-
ax.set_title("Top 20 Enlaces Internos")
|
425 |
-
plt.tight_layout()
|
426 |
-
return fig
|
427 |
-
|
428 |
|
429 |
def create_interface() -> gr.Blocks:
|
430 |
-
"""
|
431 |
-
Crea la interfaz de usuario utilizando Gradio.
|
432 |
-
"""
|
433 |
analyzer = SEOSpaceAnalyzer()
|
434 |
with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as interface:
|
435 |
gr.Markdown("""
|
436 |
# 🕵️ SEO Analyzer Pro
|
437 |
**Analizador SEO avanzado con modelos de lenguaje**
|
438 |
|
439 |
-
|
440 |
""")
|
441 |
with gr.Row():
|
442 |
with gr.Column():
|
443 |
-
sitemap_input = gr.Textbox(
|
444 |
-
|
445 |
-
|
|
|
|
|
446 |
analyze_btn = gr.Button("Analizar Sitio", variant="primary")
|
447 |
with gr.Row():
|
448 |
clear_btn = gr.Button("Limpiar")
|
@@ -450,97 +53,48 @@ def create_interface() -> gr.Blocks:
|
|
450 |
plot_btn = gr.Button("Visualizar Enlaces Internos", variant="secondary")
|
451 |
with gr.Column():
|
452 |
status_output = gr.Textbox(label="Estado del Análisis", interactive=False)
|
453 |
-
progress_bar = gr.Progress()
|
454 |
-
|
455 |
with gr.Tabs():
|
456 |
with gr.Tab("📊 Resumen"):
|
457 |
stats_output = gr.JSON(label="Estadísticas Generales")
|
458 |
recommendations_output = gr.JSON(label="Recomendaciones SEO")
|
459 |
with gr.Tab("📝 Contenido"):
|
460 |
content_output = gr.JSON(label="Análisis de Contenido")
|
461 |
-
gr.Examples(
|
462 |
-
examples=[{"content": "Ejemplo de análisis de contenido..."}],
|
463 |
-
inputs=[content_output],
|
464 |
-
label="Ejemplos de Salida"
|
465 |
-
)
|
466 |
with gr.Tab("🔗 Enlaces"):
|
467 |
links_output = gr.JSON(label="Análisis de Enlaces")
|
468 |
links_plot = gr.Plot(label="Visualización de Enlaces Internos")
|
469 |
-
with gr.Tab("
|
470 |
-
gr.
|
471 |
-
|
472 |
-
Los documentos descargados se guardan en la carpeta `content_storage/`
|
473 |
-
""")
|
474 |
-
|
475 |
-
# Función que genera el reporte y lo guarda en disco
|
476 |
-
def generate_report() -> Optional[str]:
|
477 |
if analyzer.current_analysis:
|
478 |
report_path = "content_storage/seo_report.json"
|
479 |
-
|
480 |
-
|
481 |
-
|
482 |
-
|
483 |
-
|
484 |
-
|
485 |
-
return None
|
486 |
-
return None
|
487 |
-
|
488 |
-
# Callback para generar gráfico de enlaces internos a partir del análisis almacenado
|
489 |
-
def generate_internal_links_plot(links_json: Dict) -> Any:
|
490 |
-
fig = analyzer._plot_internal_links(links_json)
|
491 |
-
return fig if fig is not None else {}
|
492 |
-
|
493 |
-
# Asignación de acciones a botones y otros eventos
|
494 |
analyze_btn.click(
|
495 |
fn=analyzer.analyze_sitemap,
|
496 |
inputs=sitemap_input,
|
497 |
-
outputs=[stats_output, recommendations_output, content_output, links_output],
|
498 |
show_progress=True
|
499 |
)
|
500 |
clear_btn.click(
|
501 |
-
fn=lambda: [None
|
502 |
-
outputs=[stats_output, recommendations_output, content_output, links_output]
|
503 |
)
|
504 |
download_btn.click(
|
505 |
fn=generate_report,
|
506 |
outputs=gr.File(label="Descargar Reporte")
|
507 |
)
|
508 |
plot_btn.click(
|
509 |
-
fn=
|
510 |
inputs=links_output,
|
511 |
outputs=links_plot
|
512 |
)
|
513 |
return interface
|
514 |
|
515 |
-
|
516 |
-
def setup_spacy_model() -> None:
|
517 |
-
"""
|
518 |
-
Verifica y descarga el modelo de spaCy 'es_core_news_lg' si no está instalado.
|
519 |
-
"""
|
520 |
-
try:
|
521 |
-
spacy.load("es_core_news_lg")
|
522 |
-
logger.info("Modelo spaCy 'es_core_news_lg' cargado correctamente.")
|
523 |
-
except OSError:
|
524 |
-
logger.info("Descargando modelo spaCy 'es_core_news_lg'...")
|
525 |
-
try:
|
526 |
-
subprocess.run(
|
527 |
-
[sys.executable, "-m", "spacy", "download", "es_core_news_lg"],
|
528 |
-
check=True,
|
529 |
-
stdout=subprocess.PIPE,
|
530 |
-
stderr=subprocess.PIPE
|
531 |
-
)
|
532 |
-
logger.info("Modelo descargado exitosamente.")
|
533 |
-
except subprocess.CalledProcessError as e:
|
534 |
-
logger.error(f"Error al descargar modelo: {e.stderr.decode()}")
|
535 |
-
raise RuntimeError("No se pudo descargar el modelo spaCy") from e
|
536 |
-
|
537 |
-
|
538 |
if __name__ == "__main__":
|
539 |
setup_spacy_model()
|
540 |
app = create_interface()
|
541 |
-
app.launch(
|
542 |
-
server_name="0.0.0.0",
|
543 |
-
server_port=7860,
|
544 |
-
show_error=True,
|
545 |
-
share=False
|
546 |
-
)
|
|
|
1 |
+
import gradio as gr
|
2 |
import json
|
3 |
+
from seo_analyzer import SEOSpaceAnalyzer
|
4 |
+
import spacy
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
import subprocess
|
6 |
import sys
|
7 |
+
import logging
|
|
|
|
|
8 |
|
9 |
+
logging.basicConfig(level=logging.INFO)
|
|
|
|
|
|
|
|
|
10 |
logger = logging.getLogger(__name__)
|
11 |
|
12 |
+
def setup_spacy_model() -> None:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"""
|
14 |
+
Verifica y descarga el modelo de spaCy 'es_core_news_lg' si no está instalado.
|
15 |
"""
|
16 |
+
try:
|
17 |
+
spacy.load("es_core_news_lg")
|
18 |
+
logger.info("Modelo spaCy 'es_core_news_lg' cargado correctamente.")
|
19 |
+
except OSError:
|
20 |
+
logger.info("Descargando modelo spaCy 'es_core_news_lg'...")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
try:
|
22 |
+
subprocess.run(
|
23 |
+
[sys.executable, "-m", "spacy", "download", "es_core_news_lg"],
|
24 |
+
check=True,
|
25 |
+
stdout=subprocess.PIPE,
|
26 |
+
stderr=subprocess.PIPE
|
27 |
+
)
|
28 |
+
logger.info("Modelo descargado exitosamente.")
|
29 |
+
except subprocess.CalledProcessError as e:
|
30 |
+
logger.error(f"Error al descargar modelo: {e.stderr.decode()}")
|
31 |
+
raise RuntimeError("No se pudo descargar el modelo spaCy") from e
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
def create_interface() -> gr.Blocks:
|
|
|
|
|
|
|
34 |
analyzer = SEOSpaceAnalyzer()
|
35 |
with gr.Blocks(title="SEO Analyzer Pro", theme=gr.themes.Soft()) as interface:
|
36 |
gr.Markdown("""
|
37 |
# 🕵️ SEO Analyzer Pro
|
38 |
**Analizador SEO avanzado con modelos de lenguaje**
|
39 |
|
40 |
+
Ingresa la URL de un sitemap.xml para analizar el sitio web.
|
41 |
""")
|
42 |
with gr.Row():
|
43 |
with gr.Column():
|
44 |
+
sitemap_input = gr.Textbox(
|
45 |
+
label="URL del Sitemap",
|
46 |
+
placeholder="https://ejemplo.com/sitemap.xml",
|
47 |
+
interactive=True
|
48 |
+
)
|
49 |
analyze_btn = gr.Button("Analizar Sitio", variant="primary")
|
50 |
with gr.Row():
|
51 |
clear_btn = gr.Button("Limpiar")
|
|
|
53 |
plot_btn = gr.Button("Visualizar Enlaces Internos", variant="secondary")
|
54 |
with gr.Column():
|
55 |
status_output = gr.Textbox(label="Estado del Análisis", interactive=False)
|
|
|
|
|
56 |
with gr.Tabs():
|
57 |
with gr.Tab("📊 Resumen"):
|
58 |
stats_output = gr.JSON(label="Estadísticas Generales")
|
59 |
recommendations_output = gr.JSON(label="Recomendaciones SEO")
|
60 |
with gr.Tab("📝 Contenido"):
|
61 |
content_output = gr.JSON(label="Análisis de Contenido")
|
|
|
|
|
|
|
|
|
|
|
62 |
with gr.Tab("🔗 Enlaces"):
|
63 |
links_output = gr.JSON(label="Análisis de Enlaces")
|
64 |
links_plot = gr.Plot(label="Visualización de Enlaces Internos")
|
65 |
+
with gr.Tab("📄 Detalles"):
|
66 |
+
details_output = gr.JSON(label="Detalles Individuales")
|
67 |
+
def generate_report() -> str:
|
|
|
|
|
|
|
|
|
|
|
68 |
if analyzer.current_analysis:
|
69 |
report_path = "content_storage/seo_report.json"
|
70 |
+
with open(report_path, 'w', encoding='utf-8') as f:
|
71 |
+
json.dump(analyzer.current_analysis, f, indent=2, ensure_ascii=False)
|
72 |
+
return report_path
|
73 |
+
return ""
|
74 |
+
def plot_internal_links(links_json: dict) -> any:
|
75 |
+
return analyzer.plot_internal_links(links_json)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
analyze_btn.click(
|
77 |
fn=analyzer.analyze_sitemap,
|
78 |
inputs=sitemap_input,
|
79 |
+
outputs=[stats_output, recommendations_output, content_output, links_output, details_output],
|
80 |
show_progress=True
|
81 |
)
|
82 |
clear_btn.click(
|
83 |
+
fn=lambda: [None, None, None, None, None],
|
84 |
+
outputs=[stats_output, recommendations_output, content_output, links_output, details_output]
|
85 |
)
|
86 |
download_btn.click(
|
87 |
fn=generate_report,
|
88 |
outputs=gr.File(label="Descargar Reporte")
|
89 |
)
|
90 |
plot_btn.click(
|
91 |
+
fn=plot_internal_links,
|
92 |
inputs=links_output,
|
93 |
outputs=links_plot
|
94 |
)
|
95 |
return interface
|
96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
if __name__ == "__main__":
|
98 |
setup_spacy_model()
|
99 |
app = create_interface()
|
100 |
+
app.launch(server_name="0.0.0.0", server_port=7860, show_error=True, share=False)
|
|
|
|
|
|
|
|
|
|