Update app.py
Browse files
app.py
CHANGED
|
@@ -3,6 +3,18 @@ import requests
|
|
| 3 |
import urllib.parse
|
| 4 |
import re
|
| 5 |
import xmltodict
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
# Función para obtener sugerencias de DuckDuckGo
|
| 8 |
def fetch_duckduckgo_suggestions(query, lang_code="es"):
|
|
@@ -41,11 +53,9 @@ def fetch_youtube_suggestions(query, lang_code="es"):
|
|
| 41 |
|
| 42 |
if response.status_code == 200:
|
| 43 |
try:
|
| 44 |
-
# Extraer las sugerencias del formato window.google.ac.h(["..."])
|
| 45 |
match = re.search(r'window\.google\.ac\.h\(\["[^"]*",\[(.*?)\],', response.text)
|
| 46 |
if match:
|
| 47 |
suggestions_data = match.group(1)
|
| 48 |
-
# Extraemos las sugerencias
|
| 49 |
suggestions = re.findall(r'\["([^"]+)"', suggestions_data)
|
| 50 |
return suggestions
|
| 51 |
else:
|
|
@@ -58,7 +68,7 @@ def fetch_youtube_suggestions(query, lang_code="es"):
|
|
| 58 |
return []
|
| 59 |
|
| 60 |
# Función para obtener sugerencias de Bing
|
| 61 |
-
def fetch_bing_suggestions(query, market="
|
| 62 |
url = "https://api.bing.com/qsml.aspx"
|
| 63 |
params = {
|
| 64 |
"Market": market,
|
|
@@ -88,7 +98,7 @@ def fetch_bing_suggestions(query, market="en-US"):
|
|
| 88 |
return []
|
| 89 |
|
| 90 |
# Función para obtener sugerencias de Amazon
|
| 91 |
-
def fetch_amazon_suggestions(query, market_id="
|
| 92 |
url = "https://completion.amazon.com/api/2017/suggestions"
|
| 93 |
params = {
|
| 94 |
"mid": market_id,
|
|
@@ -100,7 +110,6 @@ def fetch_amazon_suggestions(query, market_id="ATVPDKIKX0DER", alias="aps"):
|
|
| 100 |
if response.status_code == 200:
|
| 101 |
try:
|
| 102 |
data = response.json()
|
| 103 |
-
# Extraemos las sugerencias desde el JSON bajo la clave 'suggestions'
|
| 104 |
return [item['value'] for item in data.get('suggestions', [])]
|
| 105 |
except ValueError:
|
| 106 |
print("Error decodificando JSON de Amazon")
|
|
@@ -110,83 +119,71 @@ def fetch_amazon_suggestions(query, market_id="ATVPDKIKX0DER", alias="aps"):
|
|
| 110 |
|
| 111 |
# Función para expandir la palabra clave
|
| 112 |
def expand_keyword(keyword):
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
return expanded_keywords
|
| 118 |
|
| 119 |
# Función principal
|
| 120 |
def main(keyword):
|
| 121 |
expanded_keywords = expand_keyword(keyword)
|
| 122 |
all_suggestions = {}
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
for exp_keyword in expanded_keywords:
|
| 131 |
-
suggestions = fetch_duckduckgo_suggestions(exp_keyword)
|
| 132 |
-
duckduckgo_suggestions_all.extend(suggestions) # Agregar todas las sugerencias
|
| 133 |
-
for suggestion in suggestions:
|
| 134 |
-
if suggestion in all_suggestions:
|
| 135 |
-
all_suggestions[suggestion] += 1
|
| 136 |
-
else:
|
| 137 |
-
all_suggestions[suggestion] = 1
|
| 138 |
-
|
| 139 |
-
# Obtener sugerencias de Google
|
| 140 |
-
for exp_keyword in expanded_keywords:
|
| 141 |
-
suggestions = fetch_google_suggestions(exp_keyword)
|
| 142 |
-
google_suggestions_all.extend(suggestions) # Agregar todas las sugerencias
|
| 143 |
-
for suggestion in suggestions:
|
| 144 |
-
if suggestion in all_suggestions:
|
| 145 |
-
all_suggestions[suggestion] += 1
|
| 146 |
-
else:
|
| 147 |
-
all_suggestions[suggestion] = 1
|
| 148 |
-
|
| 149 |
-
# Obtener sugerencias de YouTube
|
| 150 |
-
for exp_keyword in expanded_keywords:
|
| 151 |
-
suggestions = fetch_youtube_suggestions(exp_keyword)
|
| 152 |
-
youtube_suggestions_all.extend(suggestions) # Agregar todas las sugerencias
|
| 153 |
-
for suggestion in suggestions:
|
| 154 |
-
if suggestion in all_suggestions:
|
| 155 |
-
all_suggestions[suggestion] += 1
|
| 156 |
-
else:
|
| 157 |
-
all_suggestions[suggestion] = 1
|
| 158 |
-
|
| 159 |
-
# Obtener sugerencias de Bing
|
| 160 |
-
for exp_keyword in expanded_keywords:
|
| 161 |
-
suggestions = fetch_bing_suggestions(exp_keyword)
|
| 162 |
-
bing_suggestions_all.extend(suggestions)
|
| 163 |
-
for suggestion in suggestions:
|
| 164 |
-
if suggestion in all_suggestions:
|
| 165 |
-
all_suggestions[suggestion] += 1
|
| 166 |
-
else:
|
| 167 |
-
all_suggestions[suggestion] = 1
|
| 168 |
|
| 169 |
-
# Obtener sugerencias de
|
| 170 |
for exp_keyword in expanded_keywords:
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
|
| 186 |
# Ordenar y filtrar las sugerencias más frecuentes combinadas
|
| 187 |
sorted_suggestions = sorted(all_suggestions.items(), key=lambda item: item[1], reverse=True)
|
| 188 |
-
|
| 189 |
-
suggestions_str = ", ".join(
|
| 190 |
|
| 191 |
# Crear la lista de todas las palabras clave con su número de repeticiones
|
| 192 |
all_suggestions_str = "<ul>"
|
|
@@ -194,57 +191,25 @@ def main(keyword):
|
|
| 194 |
all_suggestions_str += f"<li>{suggestion} - {freq} repeticiones</li>"
|
| 195 |
all_suggestions_str += "</ul>"
|
| 196 |
|
| 197 |
-
# Crear el HTML de salida
|
| 198 |
html_output = f"""
|
| 199 |
<div>
|
| 200 |
-
<b>
|
| 201 |
<button class="lg secondary svelte-cmf5ev" style="font-size: small; padding: 2px; color: #808080ba; border: none; margin-left: 5px;"
|
| 202 |
onclick='navigator.clipboard.writeText(document.getElementById("suggestions_text").innerText).then(() => alert("Texto copiado al portapapeles"))'> ✂ </button>
|
| 203 |
</div>
|
| 204 |
-
|
| 205 |
-
<h4>Top 10 Sugerencias de Google:</h4>
|
| 206 |
-
<ul>
|
| 207 |
"""
|
| 208 |
-
for suggestion in google_top_10:
|
| 209 |
-
freq = all_suggestions[suggestion]
|
| 210 |
-
html_output += f"<li>{suggestion} ({freq})</li>"
|
| 211 |
-
html_output += "</ul>"
|
| 212 |
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
<h4>Top 10 Sugerencias de YouTube:</h4>
|
| 224 |
-
<ul>
|
| 225 |
-
"""
|
| 226 |
-
for suggestion in youtube_top_10:
|
| 227 |
-
freq = all_suggestions[suggestion]
|
| 228 |
-
html_output += f"<li>{suggestion} ({freq})</li>"
|
| 229 |
-
html_output += "</ul>"
|
| 230 |
-
|
| 231 |
-
html_output += """
|
| 232 |
-
<h4>Top 10 Sugerencias de Bing:</h4>
|
| 233 |
-
<ul>
|
| 234 |
-
"""
|
| 235 |
-
for suggestion in bing_top_10:
|
| 236 |
-
freq = all_suggestions[suggestion]
|
| 237 |
-
html_output += f"<li>{suggestion} ({freq})</li>"
|
| 238 |
-
html_output += "</ul>"
|
| 239 |
-
|
| 240 |
-
html_output += """
|
| 241 |
-
<h4>Top 10 Sugerencias de Amazon:</h4>
|
| 242 |
-
<ul>
|
| 243 |
-
"""
|
| 244 |
-
for suggestion in amazon_top_10:
|
| 245 |
-
freq = all_suggestions[suggestion]
|
| 246 |
-
html_output += f"<li>{suggestion} ({freq})</li>"
|
| 247 |
-
html_output += "</ul>"
|
| 248 |
|
| 249 |
# Agregar la lista completa de todas las palabras clave
|
| 250 |
html_output += """
|
|
@@ -260,8 +225,8 @@ iface = gr.Interface(
|
|
| 260 |
inputs="text",
|
| 261 |
outputs="html",
|
| 262 |
title="<div style='margin:0 auto;text-align:center'><div style='margin:0 auto;text-align:center'><img style='width:100px;display: inline-table;margin-bottom:-10px' src='https://artxeweb.com/media/files/search.jpg'><p>Sugerencias Combinadas de Google, DuckDuckGo, YouTube, Bing y Amazon</p></div>",
|
| 263 |
-
description="<p style='margin-bottom:10px;text-align:center;background: #ffffff; padding: 8px; border-radius: 8px; border-width: 1px; border: solid 1px #e5e7eb;'>Ingrese una palabra clave para obtener sugerencias de búsqueda relacionadas de Google, DuckDuckGo, YouTube, Bing y Amazon. Se mostrarán las
|
| 264 |
article="<div style='margin-top:10px'><p style='text-align: center !important; background: #ffffff; padding: 5px 30px; border-radius: 8px; border-width: 1px; border: solid 1px #e5e7eb; width: fit-content; margin: auto;'>Desarrollada por <a style='text-decoration: none !important; color: #e12a31 !important;' href='https://artxeweb.com'>© Artxe Web</a></p></div>"
|
| 265 |
)
|
| 266 |
|
| 267 |
-
iface.launch()
|
|
|
|
| 3 |
import urllib.parse
|
| 4 |
import re
|
| 5 |
import xmltodict
|
| 6 |
+
from itertools import product
|
| 7 |
+
import nltk
|
| 8 |
+
from nltk.corpus import stopwords
|
| 9 |
+
from nltk.stem import SnowballStemmer
|
| 10 |
+
|
| 11 |
+
# Descargar recursos de NLTK
|
| 12 |
+
nltk.download('stopwords', quiet=True)
|
| 13 |
+
nltk.download('punkt', quiet=True)
|
| 14 |
+
|
| 15 |
+
# Inicializar el stemmer y la lista de stopwords
|
| 16 |
+
stemmer = SnowballStemmer("spanish")
|
| 17 |
+
stop_words = set(stopwords.words('spanish'))
|
| 18 |
|
| 19 |
# Función para obtener sugerencias de DuckDuckGo
|
| 20 |
def fetch_duckduckgo_suggestions(query, lang_code="es"):
|
|
|
|
| 53 |
|
| 54 |
if response.status_code == 200:
|
| 55 |
try:
|
|
|
|
| 56 |
match = re.search(r'window\.google\.ac\.h\(\["[^"]*",\[(.*?)\],', response.text)
|
| 57 |
if match:
|
| 58 |
suggestions_data = match.group(1)
|
|
|
|
| 59 |
suggestions = re.findall(r'\["([^"]+)"', suggestions_data)
|
| 60 |
return suggestions
|
| 61 |
else:
|
|
|
|
| 68 |
return []
|
| 69 |
|
| 70 |
# Función para obtener sugerencias de Bing
|
| 71 |
+
def fetch_bing_suggestions(query, market="es-ES"):
|
| 72 |
url = "https://api.bing.com/qsml.aspx"
|
| 73 |
params = {
|
| 74 |
"Market": market,
|
|
|
|
| 98 |
return []
|
| 99 |
|
| 100 |
# Función para obtener sugerencias de Amazon
|
| 101 |
+
def fetch_amazon_suggestions(query, market_id="A1F83G8C2ARO7P", alias="aps"):
|
| 102 |
url = "https://completion.amazon.com/api/2017/suggestions"
|
| 103 |
params = {
|
| 104 |
"mid": market_id,
|
|
|
|
| 110 |
if response.status_code == 200:
|
| 111 |
try:
|
| 112 |
data = response.json()
|
|
|
|
| 113 |
return [item['value'] for item in data.get('suggestions', [])]
|
| 114 |
except ValueError:
|
| 115 |
print("Error decodificando JSON de Amazon")
|
|
|
|
| 119 |
|
| 120 |
# Función para expandir la palabra clave
|
| 121 |
def expand_keyword(keyword):
|
| 122 |
+
# Tokenizar la palabra clave
|
| 123 |
+
tokens = nltk.word_tokenize(keyword.lower())
|
| 124 |
+
|
| 125 |
+
# Eliminar stopwords y aplicar stemming
|
| 126 |
+
tokens = [stemmer.stem(token) for token in tokens if token not in stop_words]
|
| 127 |
+
|
| 128 |
+
# Generar variaciones
|
| 129 |
+
variations = []
|
| 130 |
+
for i in range(1, len(tokens) + 1):
|
| 131 |
+
variations.extend(list(product(tokens, repeat=i)))
|
| 132 |
+
|
| 133 |
+
# Convertir tuplas a strings
|
| 134 |
+
expanded_keywords = [" ".join(variation) for variation in variations]
|
| 135 |
+
|
| 136 |
+
# Añadir variaciones con prefijos y sufijos
|
| 137 |
+
prefixes = ['como', 'que', 'donde', 'cuando', 'por que', 'cual']
|
| 138 |
+
suffixes = ['gratis', 'online', 'pdf', 'precios', 'opiniones']
|
| 139 |
+
|
| 140 |
+
for prefix in prefixes:
|
| 141 |
+
expanded_keywords.append(f"{prefix} {keyword}")
|
| 142 |
+
|
| 143 |
+
for suffix in suffixes:
|
| 144 |
+
expanded_keywords.append(f"{keyword} {suffix}")
|
| 145 |
+
|
| 146 |
+
# Añadir plurales (simplificado)
|
| 147 |
+
expanded_keywords.extend([f"{kw}s" for kw in expanded_keywords])
|
| 148 |
+
|
| 149 |
+
# Eliminar duplicados y la palabra clave original vacía
|
| 150 |
+
expanded_keywords = list(set(expanded_keywords) - {''})
|
| 151 |
+
|
| 152 |
return expanded_keywords
|
| 153 |
|
| 154 |
# Función principal
|
| 155 |
def main(keyword):
|
| 156 |
expanded_keywords = expand_keyword(keyword)
|
| 157 |
all_suggestions = {}
|
| 158 |
+
platform_suggestions = {
|
| 159 |
+
'Google': set(),
|
| 160 |
+
'DuckDuckGo': set(),
|
| 161 |
+
'YouTube': set(),
|
| 162 |
+
'Bing': set(),
|
| 163 |
+
'Amazon': set()
|
| 164 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 165 |
|
| 166 |
+
# Obtener sugerencias de todas las plataformas
|
| 167 |
for exp_keyword in expanded_keywords:
|
| 168 |
+
for platform, fetch_func in [
|
| 169 |
+
('Google', fetch_google_suggestions),
|
| 170 |
+
('DuckDuckGo', fetch_duckduckgo_suggestions),
|
| 171 |
+
('YouTube', fetch_youtube_suggestions),
|
| 172 |
+
('Bing', fetch_bing_suggestions),
|
| 173 |
+
('Amazon', fetch_amazon_suggestions)
|
| 174 |
+
]:
|
| 175 |
+
suggestions = fetch_func(exp_keyword)
|
| 176 |
+
platform_suggestions[platform].update(suggestions)
|
| 177 |
+
for suggestion in suggestions:
|
| 178 |
+
if suggestion in all_suggestions:
|
| 179 |
+
all_suggestions[suggestion] += 1
|
| 180 |
+
else:
|
| 181 |
+
all_suggestions[suggestion] = 1
|
| 182 |
|
| 183 |
# Ordenar y filtrar las sugerencias más frecuentes combinadas
|
| 184 |
sorted_suggestions = sorted(all_suggestions.items(), key=lambda item: item[1], reverse=True)
|
| 185 |
+
combined_top_suggestions = [sug for sug, freq in sorted_suggestions if freq >= 2][:50] # Aumentado a top 50
|
| 186 |
+
suggestions_str = ", ".join(combined_top_suggestions)
|
| 187 |
|
| 188 |
# Crear la lista de todas las palabras clave con su número de repeticiones
|
| 189 |
all_suggestions_str = "<ul>"
|
|
|
|
| 191 |
all_suggestions_str += f"<li>{suggestion} - {freq} repeticiones</li>"
|
| 192 |
all_suggestions_str += "</ul>"
|
| 193 |
|
| 194 |
+
# Crear el HTML de salida
|
| 195 |
html_output = f"""
|
| 196 |
<div>
|
| 197 |
+
<b>Top 50 Sugerencias combinadas:</b> <span id='suggestions_text'>{suggestions_str}</span>
|
| 198 |
<button class="lg secondary svelte-cmf5ev" style="font-size: small; padding: 2px; color: #808080ba; border: none; margin-left: 5px;"
|
| 199 |
onclick='navigator.clipboard.writeText(document.getElementById("suggestions_text").innerText).then(() => alert("Texto copiado al portapapeles"))'> ✂ </button>
|
| 200 |
</div>
|
|
|
|
|
|
|
|
|
|
| 201 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
| 202 |
|
| 203 |
+
# Agregar las top sugerencias de cada plataforma
|
| 204 |
+
for platform, suggestions in platform_suggestions.items():
|
| 205 |
+
html_output += f"""
|
| 206 |
+
<h4>Top 20 Sugerencias de {platform}:</h4>
|
| 207 |
+
<ul>
|
| 208 |
+
"""
|
| 209 |
+
for suggestion in list(suggestions)[:20]:
|
| 210 |
+
freq = all_suggestions[suggestion]
|
| 211 |
+
html_output += f"<li>{suggestion} ({freq})</li>"
|
| 212 |
+
html_output += "</ul>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
|
| 214 |
# Agregar la lista completa de todas las palabras clave
|
| 215 |
html_output += """
|
|
|
|
| 225 |
inputs="text",
|
| 226 |
outputs="html",
|
| 227 |
title="<div style='margin:0 auto;text-align:center'><div style='margin:0 auto;text-align:center'><img style='width:100px;display: inline-table;margin-bottom:-10px' src='https://artxeweb.com/media/files/search.jpg'><p>Sugerencias Combinadas de Google, DuckDuckGo, YouTube, Bing y Amazon</p></div>",
|
| 228 |
+
description="<p style='margin-bottom:10px;text-align:center;background: #ffffff; padding: 8px; border-radius: 8px; border-width: 1px; border: solid 1px #e5e7eb;'>Ingrese una palabra clave para obtener sugerencias de búsqueda relacionadas de Google, DuckDuckGo, YouTube, Bing y Amazon. Se mostrarán las 50 primeras sugerencias combinadas y también las 20 principales de cada plataforma por separado.</p>",
|
| 229 |
article="<div style='margin-top:10px'><p style='text-align: center !important; background: #ffffff; padding: 5px 30px; border-radius: 8px; border-width: 1px; border: solid 1px #e5e7eb; width: fit-content; margin: auto;'>Desarrollada por <a style='text-decoration: none !important; color: #e12a31 !important;' href='https://artxeweb.com'>© Artxe Web</a></p></div>"
|
| 230 |
)
|
| 231 |
|
| 232 |
+
iface.launch()
|