Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
# ==============================================
|
| 2 |
-
# WEB SCRAPER FOR N8N -
|
| 3 |
# ==============================================
|
| 4 |
|
| 5 |
import gradio as gr
|
|
@@ -9,7 +9,8 @@ import time
|
|
| 9 |
import re
|
| 10 |
import html
|
| 11 |
from typing import Dict, Any
|
| 12 |
-
import
|
|
|
|
| 13 |
|
| 14 |
# ==============================================
|
| 15 |
# SIMPLE WEB SCRAPER
|
|
@@ -25,6 +26,8 @@ class WebScraper:
|
|
| 25 |
"""Main scraping function"""
|
| 26 |
start_time = time.time()
|
| 27 |
|
|
|
|
|
|
|
| 28 |
# Ensure URL has protocol
|
| 29 |
if not url.startswith(('http://', 'https://')):
|
| 30 |
url = 'https://' + url
|
|
@@ -56,7 +59,7 @@ class WebScraper:
|
|
| 56 |
"text_length": len(cleaned_text),
|
| 57 |
"status_code": response.status_code,
|
| 58 |
"execution_time": round(time.time() - start_time, 2),
|
| 59 |
-
"method": "
|
| 60 |
}
|
| 61 |
|
| 62 |
except Exception as e:
|
|
@@ -111,12 +114,80 @@ class WebScraper:
|
|
| 111 |
scraper = WebScraper()
|
| 112 |
|
| 113 |
# ==============================================
|
| 114 |
-
#
|
| 115 |
# ==============================================
|
| 116 |
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
|
| 121 |
# ==============================================
|
| 122 |
# GRADIO INTERFACE
|
|
@@ -149,106 +220,68 @@ def gradio_scrape(url: str):
|
|
| 149 |
### Preview:
|
| 150 |
{preview}
|
| 151 |
|
| 152 |
-
*Check JSON tab for full response*
|
| 153 |
"""
|
| 154 |
return output, result
|
| 155 |
else:
|
| 156 |
return f"## ❌ Error\n\n{result.get('error', 'Unknown error')}", result
|
| 157 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
# ==============================================
|
| 159 |
-
#
|
| 160 |
# ==============================================
|
| 161 |
|
| 162 |
-
#
|
| 163 |
-
|
| 164 |
-
gr.Markdown("# 🌐 Web Scraper for n8n")
|
| 165 |
-
gr.Markdown("Extract text content from webpages. Perfect for n8n workflows!")
|
| 166 |
-
|
| 167 |
-
with gr.Row():
|
| 168 |
-
with gr.Column(scale=2):
|
| 169 |
-
url_input = gr.Textbox(
|
| 170 |
-
label="Website URL",
|
| 171 |
-
placeholder="https://example.com",
|
| 172 |
-
value="https://en.wikipedia.org/wiki/Artificial_intelligence"
|
| 173 |
-
)
|
| 174 |
-
scrape_btn = gr.Button("Scrape", variant="primary")
|
| 175 |
-
|
| 176 |
-
with gr.Column(scale=1):
|
| 177 |
-
gr.Markdown("""
|
| 178 |
-
### API Usage (for n8n)
|
| 179 |
-
|
| 180 |
-
**Method:** `POST` to `/api/scrape`
|
| 181 |
-
|
| 182 |
-
**Body:**
|
| 183 |
-
```json
|
| 184 |
-
{
|
| 185 |
-
"url": "https://example.com"
|
| 186 |
-
}
|
| 187 |
-
```
|
| 188 |
-
|
| 189 |
-
**Response:** JSON with extracted text
|
| 190 |
-
""")
|
| 191 |
-
|
| 192 |
-
with gr.Row():
|
| 193 |
-
with gr.Column():
|
| 194 |
-
output_md = gr.Markdown(label="Result")
|
| 195 |
-
with gr.Column():
|
| 196 |
-
output_json = gr.JSON(label="API Response")
|
| 197 |
-
|
| 198 |
-
# Examples
|
| 199 |
-
gr.Examples(
|
| 200 |
-
examples=[
|
| 201 |
-
["https://en.wikipedia.org/wiki/Artificial_intelligence"],
|
| 202 |
-
["https://example.com"],
|
| 203 |
-
["https://httpbin.org/html"]
|
| 204 |
-
],
|
| 205 |
-
inputs=[url_input]
|
| 206 |
-
)
|
| 207 |
-
|
| 208 |
-
# Event handlers
|
| 209 |
-
def process_url(url):
|
| 210 |
-
return gradio_scrape(url)
|
| 211 |
-
|
| 212 |
-
scrape_btn.click(
|
| 213 |
-
fn=process_url,
|
| 214 |
-
inputs=[url_input],
|
| 215 |
-
outputs=[output_md, output_json]
|
| 216 |
-
)
|
| 217 |
-
|
| 218 |
-
url_input.submit(
|
| 219 |
-
fn=process_url,
|
| 220 |
-
inputs=[url_input],
|
| 221 |
-
outputs=[output_md, output_json]
|
| 222 |
-
)
|
| 223 |
-
|
| 224 |
-
# ==============================================
|
| 225 |
-
# ADD API ENDPOINT DIRECTLY IN GRADIO
|
| 226 |
-
# ==============================================
|
| 227 |
-
|
| 228 |
-
# Create a separate API endpoint
|
| 229 |
-
@app.app.post("/api/scrape")
|
| 230 |
-
async def api_scrape(request: dict):
|
| 231 |
-
"""API endpoint for n8n"""
|
| 232 |
-
try:
|
| 233 |
-
url = request.get("url", "").strip()
|
| 234 |
-
if not url:
|
| 235 |
-
return {"success": False, "error": "URL is required"}
|
| 236 |
-
|
| 237 |
-
return api_scrape_function(url)
|
| 238 |
-
except Exception as e:
|
| 239 |
-
return {"success": False, "error": str(e)}
|
| 240 |
|
| 241 |
# ==============================================
|
| 242 |
-
#
|
| 243 |
# ==============================================
|
| 244 |
|
| 245 |
-
#
|
| 246 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
|
| 248 |
-
# For local testing
|
| 249 |
if __name__ == "__main__":
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
)
|
|
|
|
| 1 |
# ==============================================
|
| 2 |
+
# WEB SCRAPER FOR N8N - WORKING VERSION
|
| 3 |
# ==============================================
|
| 4 |
|
| 5 |
import gradio as gr
|
|
|
|
| 9 |
import re
|
| 10 |
import html
|
| 11 |
from typing import Dict, Any
|
| 12 |
+
from fastapi import FastAPI, Request
|
| 13 |
+
import uvicorn
|
| 14 |
|
| 15 |
# ==============================================
|
| 16 |
# SIMPLE WEB SCRAPER
|
|
|
|
| 26 |
"""Main scraping function"""
|
| 27 |
start_time = time.time()
|
| 28 |
|
| 29 |
+
print(f"🌐 Scraping: {url}")
|
| 30 |
+
|
| 31 |
# Ensure URL has protocol
|
| 32 |
if not url.startswith(('http://', 'https://')):
|
| 33 |
url = 'https://' + url
|
|
|
|
| 59 |
"text_length": len(cleaned_text),
|
| 60 |
"status_code": response.status_code,
|
| 61 |
"execution_time": round(time.time() - start_time, 2),
|
| 62 |
+
"method": "direct_html"
|
| 63 |
}
|
| 64 |
|
| 65 |
except Exception as e:
|
|
|
|
| 114 |
scraper = WebScraper()
|
| 115 |
|
| 116 |
# ==============================================
|
| 117 |
+
# CREATE FASTAPI APP FIRST
|
| 118 |
# ==============================================
|
| 119 |
|
| 120 |
+
# Create FastAPI app
|
| 121 |
+
fastapi_app = FastAPI(
|
| 122 |
+
title="Web Scraper API",
|
| 123 |
+
description="Extract text from webpages for n8n workflows",
|
| 124 |
+
version="1.0"
|
| 125 |
+
)
|
| 126 |
+
|
| 127 |
+
# Add CORS middleware
|
| 128 |
+
from fastapi.middleware.cors import CORSMiddleware
|
| 129 |
+
from fastapi.responses import JSONResponse
|
| 130 |
+
|
| 131 |
+
fastapi_app.add_middleware(
|
| 132 |
+
CORSMiddleware,
|
| 133 |
+
allow_origins=["*"],
|
| 134 |
+
allow_credentials=True,
|
| 135 |
+
allow_methods=["*"],
|
| 136 |
+
allow_headers=["*"],
|
| 137 |
+
)
|
| 138 |
+
|
| 139 |
+
@fastapi_app.get("/")
|
| 140 |
+
async def root():
|
| 141 |
+
return {
|
| 142 |
+
"service": "Web Scraper API",
|
| 143 |
+
"version": "1.0",
|
| 144 |
+
"endpoints": {
|
| 145 |
+
"GET /": "This info",
|
| 146 |
+
"GET /health": "Health check",
|
| 147 |
+
"POST /scrape": "Scrape a webpage (for n8n)"
|
| 148 |
+
},
|
| 149 |
+
"usage": {
|
| 150 |
+
"curl": 'curl -X POST "https://your-space.hf.space/scrape" -H "Content-Type: application/json" -d \'{"url":"https://example.com"}\'',
|
| 151 |
+
"n8n": "HTTP Request node: POST to /scrape with JSON body"
|
| 152 |
+
}
|
| 153 |
+
}
|
| 154 |
+
|
| 155 |
+
@fastapi_app.get("/health")
|
| 156 |
+
async def health():
|
| 157 |
+
return {
|
| 158 |
+
"status": "healthy",
|
| 159 |
+
"timestamp": time.time()
|
| 160 |
+
}
|
| 161 |
+
|
| 162 |
+
@fastapi_app.post("/scrape")
|
| 163 |
+
async def api_scrape(request: Request):
|
| 164 |
+
"""Main API endpoint for n8n"""
|
| 165 |
+
try:
|
| 166 |
+
# Parse JSON body
|
| 167 |
+
body = await request.json()
|
| 168 |
+
url = body.get("url", "").strip()
|
| 169 |
+
|
| 170 |
+
if not url:
|
| 171 |
+
return JSONResponse(
|
| 172 |
+
status_code=400,
|
| 173 |
+
content={"success": False, "error": "URL parameter is required"}
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
print(f"📨 API Request received for: {url}")
|
| 177 |
+
result = scraper.scrape(url)
|
| 178 |
+
|
| 179 |
+
return result
|
| 180 |
+
|
| 181 |
+
except json.JSONDecodeError:
|
| 182 |
+
return JSONResponse(
|
| 183 |
+
status_code=400,
|
| 184 |
+
content={"success": False, "error": "Invalid JSON payload"}
|
| 185 |
+
)
|
| 186 |
+
except Exception as e:
|
| 187 |
+
return JSONResponse(
|
| 188 |
+
status_code=500,
|
| 189 |
+
content={"success": False, "error": f"Internal error: {str(e)}"}
|
| 190 |
+
)
|
| 191 |
|
| 192 |
# ==============================================
|
| 193 |
# GRADIO INTERFACE
|
|
|
|
| 220 |
### Preview:
|
| 221 |
{preview}
|
| 222 |
|
| 223 |
+
*Check JSON tab for full API response*
|
| 224 |
"""
|
| 225 |
return output, result
|
| 226 |
else:
|
| 227 |
return f"## ❌ Error\n\n{result.get('error', 'Unknown error')}", result
|
| 228 |
|
| 229 |
+
# Create Gradio interface
|
| 230 |
+
gradio_interface = gr.Interface(
|
| 231 |
+
fn=gradio_scrape,
|
| 232 |
+
inputs=gr.Textbox(
|
| 233 |
+
label="Website URL",
|
| 234 |
+
placeholder="https://example.com",
|
| 235 |
+
value="https://example.com"
|
| 236 |
+
),
|
| 237 |
+
outputs=[
|
| 238 |
+
gr.Markdown(label="Result"),
|
| 239 |
+
gr.JSON(label="API Response")
|
| 240 |
+
],
|
| 241 |
+
title="🌐 Web Scraper for n8n",
|
| 242 |
+
description="Extract text from webpages. Use POST /scrape for n8n integration.",
|
| 243 |
+
examples=[
|
| 244 |
+
["https://example.com"],
|
| 245 |
+
["https://en.wikipedia.org/wiki/Artificial_intelligence"],
|
| 246 |
+
["https://httpbin.org/html"]
|
| 247 |
+
]
|
| 248 |
+
)
|
| 249 |
+
|
| 250 |
# ==============================================
|
| 251 |
+
# MOUNT GRADIO TO FASTAPI
|
| 252 |
# ==============================================
|
| 253 |
|
| 254 |
+
# Mount Gradio app to FastAPI at root path
|
| 255 |
+
app = gr.mount_gradio_app(fastapi_app, gradio_interface, path="/")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
|
| 257 |
# ==============================================
|
| 258 |
+
# ALTERNATIVE: If mounting doesn't work, try this:
|
| 259 |
# ==============================================
|
| 260 |
|
| 261 |
+
# Instead of mounting, you can also define routes manually
|
| 262 |
+
# Uncomment below if mounting doesn't work:
|
| 263 |
+
|
| 264 |
+
# @fastapi_app.get("/")
|
| 265 |
+
# async def gradio_root():
|
| 266 |
+
# # This will redirect to the Gradio interface
|
| 267 |
+
# from fastapi.responses import RedirectResponse
|
| 268 |
+
# return RedirectResponse(url="/")
|
| 269 |
+
|
| 270 |
+
# ==============================================
|
| 271 |
+
# LAUNCH THE APP
|
| 272 |
+
# ==============================================
|
| 273 |
|
|
|
|
| 274 |
if __name__ == "__main__":
|
| 275 |
+
print("\n" + "="*60)
|
| 276 |
+
print("🚀 Web Scraper API Starting")
|
| 277 |
+
print("="*60)
|
| 278 |
+
print("API Endpoint: POST /scrape")
|
| 279 |
+
print("Web Interface: GET /")
|
| 280 |
+
print("="*60 + "\n")
|
| 281 |
+
|
| 282 |
+
uvicorn.run(
|
| 283 |
+
app,
|
| 284 |
+
host="0.0.0.0",
|
| 285 |
+
port=7860,
|
| 286 |
+
log_level="info"
|
| 287 |
)
|