htmlpdfs

Sleeping

App Files Files Community

ABDALLALSWAITI commited on Oct 17, 2025

Commit

ce83640

verified ·

1 Parent(s): c804aef

Update app.py

Browse files

Files changed (1) hide show

app.py +75 -145

app.py CHANGED Viewed

@@ -8,105 +8,61 @@ import shutil
 import base64
 import logging
 from typing import List, Optional
-from contextlib import asynccontextmanager
 # Configure logging
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-)
 logger = logging.getLogger(__name__)
-# Global state
-app_state = {"ready": False, "error": None}
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    """Startup and shutdown events"""
-    logger.info("=" * 60)
     logger.info("HTML to PDF Converter API Starting...")
-    logger.info("=" * 60)
     logger.info("Checking dependencies...")
     try:
-        # Check Node.js
-        node_version = subprocess.run(
-            ['node', '--version'],
-            capture_output=True,
-            text=True,
-            timeout=5
         )
-        logger.info(f"Node.js version: {node_version.stdout.strip()}")
-        # Check Chromium
-        chromium_path = os.environ.get('PUPPETEER_EXECUTABLE_PATH', '/usr/bin/chromium')
         if os.path.exists(chromium_path):
             logger.info(f"Chromium found at: {chromium_path}")
         else:
-            logger.error(f"Chromium NOT found at: {chromium_path}")
-            app_state["error"] = f"Chromium not found at {chromium_path}"
-        # Check Puppeteer script
-        puppeteer_script = '/app/puppeteer_pdf.js'
-        if os.path.exists(puppeteer_script):
             logger.info("Puppeteer script found")
         else:
-            logger.error(f"Puppeteer script NOT found at {puppeteer_script}")
-            app_state["error"] = f"Puppeteer script not found"
-        # Test Puppeteer
-        logger.info("Testing Puppeteer...")
-        test_html = "<html><body><h1>Test</h1></body></html>"
-        test_dir = tempfile.mkdtemp()
-        try:
-            test_file = os.path.join(test_dir, "test.html")
-            with open(test_file, 'w') as f:
-                f.write(test_html)
-            result = subprocess.run(
-                ['node', puppeteer_script, test_file, '9:16'],
-                capture_output=True,
-                text=True,
-                timeout=30,
-                cwd='/app'
-            )
-            if result.returncode == 0:
-                logger.info("✓ Puppeteer test PASSED")
-                app_state["ready"] = True
-            else:
-                logger.error(f"✗ Puppeteer test FAILED: {result.stderr}")
-                app_state["error"] = f"Puppeteer test failed: {result.stderr}"
-        except Exception as e:
-            logger.error(f"✗ Puppeteer test FAILED with exception: {e}")
-            app_state["error"] = str(e)
-        finally:
-            shutil.rmtree(test_dir, ignore_errors=True)
-        logger.info("=" * 60)
-        if app_state["ready"]:
-            logger.info("✓ API is ready!")
-        else:
-            logger.error(f"✗ API NOT ready: {app_state.get('error', 'Unknown error')}")
-        logger.info("=" * 60)
-    except Exception as e:
-        logger.error(f"Startup check failed: {e}")
-        app_state["error"] = str(e)
-    # THIS IS THE KEY: yield and keep the app running!
-    yield
-    # Shutdown (only runs when app is stopping)
-    logger.info("Shutting down...")
-# Create FastAPI app with lifespan
-app = FastAPI(
-    title="HTML to PDF Converter API",
-    description="Convert HTML to PDF with page breaks and image support",
-    version="1.0.0",
-    lifespan=lifespan
-)
 # Add CORS middleware
 app.add_middleware(
@@ -121,9 +77,7 @@ app.add_middleware(
 async def root():
     """Root endpoint - returns immediately for health check"""
     return {
-        "status": "online" if app_state["ready"] else "error",
-        "ready": app_state["ready"],
-        "error": app_state.get("error"),
         "service": "HTML to PDF Converter API",
         "version": "1.0.0",
         "docs": "/docs",
@@ -133,49 +87,37 @@ async def root():
 @app.get("/health")
 async def health():
     """Health check endpoint"""
-    if not app_state["ready"]:
-        raise HTTPException(503, f"Service not ready: {app_state.get('error', 'Unknown error')}")
-    return {"status": "healthy", "ready": True}
 @app.get("/ui", response_class=HTMLResponse)
 async def ui():
     """UI documentation page"""
-    status_class = "online" if app_state["ready"] else "error"
-    status_text = "✓ Online" if app_state["ready"] else "✗ Error"
-    error_html = ""
-    if not app_state["ready"]:
-        error_html = f"""
-        <div style="background: #fee; border: 2px solid #c00; padding: 15px; margin: 20px 0; border-radius: 5px;">
-            <strong>⚠️ Service Error:</strong> {app_state.get('error', 'Unknown error')}
-        </div>
-        """
-    return f"""
     <!DOCTYPE html>
     <html>
     <head>
         <title>HTML to PDF API</title>
         <meta name="viewport" content="width=device-width, initial-scale=1">
         <style>
-            * {{ margin: 0; padding: 0; box-sizing: border-box; }}
-            body {{
                 font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Arial, sans-serif;
                 line-height: 1.6;
                 color: #333;
                 background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
                 min-height: 100vh;
                 padding: 20px;
-            }}
-            .container {{
                 max-width: 900px;
                 margin: 0 auto;
                 background: white;
                 border-radius: 10px;
                 padding: 40px;
                 box-shadow: 0 10px 40px rgba(0,0,0,0.2);
-            }}
-            h1 {{ color: #667eea; margin-bottom: 10px; font-size: 2.5em; }}
-            .status {{
                 display: inline-block;
                 background: #10b981;
                 color: white;
@@ -183,29 +125,34 @@ async def ui():
                 border-radius: 20px;
                 font-size: 0.9em;
                 margin-bottom: 30px;
-            }}
-            .status.error {{
-                background: #ef4444;
-            }}
-            h2 {{ color: #333; margin: 30px 0 15px; border-bottom: 2px solid #667eea; padding-bottom: 10px; }}
-            .endpoint {{
                 background: #f8f9fa;
                 border-left: 4px solid #667eea;
                 padding: 20px;
                 margin: 15px 0;
                 border-radius: 5px;
-            }}
-            .endpoint h3 {{ color: #667eea; margin-bottom: 10px; }}
-            code {{
                 background: #e9ecef;
                 padding: 3px 8px;
                 border-radius: 4px;
                 font-family: 'Courier New', monospace;
                 font-size: 0.9em;
-            }}
-            ul {{ margin-left: 20px; }}
-            li {{ margin: 8px 0; }}
-            .btn {{
                 display: inline-block;
                 background: #667eea;
                 color: white;
@@ -214,20 +161,18 @@ async def ui():
                 text-decoration: none;
                 margin: 5px;
                 transition: all 0.3s;
-            }}
-            .btn:hover {{
                 background: #5568d3;
                 transform: translateY(-2px);
                 box-shadow: 0 4px 12px rgba(102, 126, 234, 0.4);
-            }}
         </style>
     </head>
     <body>
         <div class="container">
             <h1>📄 HTML to PDF Converter API</h1>
-            <span class="status {status_class}">{status_text}</span>
-            {error_html}
             <p style="margin: 20px 0; font-size: 1.1em;">
                 A powerful API to convert HTML documents to PDF with support for
@@ -313,9 +258,6 @@ def inject_page_css(html: str, ratio: str) -> str:
 def convert_to_pdf(html: str, ratio: str) -> bytes:
     """Convert HTML to PDF using Puppeteer"""
-    if not app_state["ready"]:
-        raise HTTPException(503, f"Service not ready: {app_state.get('error', 'Unknown')}")
     temp_dir = tempfile.mkdtemp()
     try:
         html = inject_page_css(html, ratio)
@@ -330,18 +272,18 @@ def convert_to_pdf(html: str, ratio: str) -> bytes:
             ['node', '/app/puppeteer_pdf.js', html_file, ratio],
             capture_output=True,
             text=True,
-            timeout=50,  # Reduced from 60 to give buffer
             cwd='/app'
         )
         if result.returncode != 0:
             logger.error(f"Conversion failed: {result.stderr}")
-            raise HTTPException(500, f"PDF conversion failed: {result.stderr}")
         pdf_file = html_file.replace('.html', '.pdf')
         if not os.path.exists(pdf_file):
-            raise HTTPException(500, "PDF file was not generated")
         with open(pdf_file, 'rb') as f:
             pdf_bytes = f.read()
@@ -349,12 +291,6 @@ def convert_to_pdf(html: str, ratio: str) -> bytes:
         logger.info(f"PDF generated: {len(pdf_bytes)} bytes")
         return pdf_bytes
-    except subprocess.TimeoutExpired:
-        logger.error("PDF conversion timed out")
-        raise HTTPException(504, "PDF conversion timed out. Try a simpler HTML document.")
-    except Exception as e:
-        logger.error(f"Conversion error: {str(e)}")
-        raise HTTPException(500, str(e))
     finally:
         shutil.rmtree(temp_dir, ignore_errors=True)
@@ -398,8 +334,6 @@ async def convert(
             }
         )
-    except HTTPException:
-        raise
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))
@@ -431,8 +365,6 @@ async def convert_html(
             }
         )
-    except HTTPException:
-        raise
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))
@@ -463,8 +395,6 @@ async def convert_base64(
             "size_bytes": len(pdf)
         })
-    except HTTPException:
-        raise
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))

 import base64
 import logging
 from typing import List, Optional
+import asyncio # Required for async subprocess
 # Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger(__name__)
+# Create FastAPI app
+app = FastAPI(
+    title="HTML to PDF Converter API",
+    description="Convert HTML to PDF with page breaks and image support",
+    version="1.0.0"
+)
+# --- START: Corrected Startup Logic ---
+@app.on_event("startup")
+async def startup_event():
+    """
+    Run startup checks. This code runs only once when the server starts.
+    """
+    logger.info("============================================================")
     logger.info("HTML to PDF Converter API Starting...")
+    logger.info("============================================================")
     logger.info("Checking dependencies...")
     try:
+        # Check Node.js version asynchronously
+        proc = await asyncio.create_subprocess_shell(
+            "node --version",
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE
         )
+        stdout, stderr = await proc.communicate()
+        if proc.returncode == 0:
+            logger.info(f"Node.js version: {stdout.decode().strip()}")
+        else:
+            logger.error(f"Could not get Node.js version: {stderr.decode().strip()}")
+        # Check for Chromium executable
+        chromium_path = os.getenv("PUPPETEER_EXECUTABLE_PATH", "/usr/bin/chromium")
         if os.path.exists(chromium_path):
             logger.info(f"Chromium found at: {chromium_path}")
         else:
+            logger.error(f"Chromium executable not found at {chromium_path}!")
+        # Check for Puppeteer script
+        if os.path.exists("/app/puppeteer_pdf.js"):
             logger.info("Puppeteer script found")
         else:
+            logger.error("puppeteer_pdf.js not found in /app directory!")
+        logger.info("============================================================")
+        logger.info("API is ready!")
+        logger.info("============================================================")
+    except Exception as e:
+        logger.critical(f"A critical error occurred during startup: {e}")
+# --- END: Corrected Startup Logic ---
 # Add CORS middleware
 app.add_middleware(
 async def root():
     """Root endpoint - returns immediately for health check"""
     return {
+        "status": "online",
         "service": "HTML to PDF Converter API",
         "version": "1.0.0",
         "docs": "/docs",
 @app.get("/health")
 async def health():
     """Health check endpoint"""
+    return {"status": "healthy"}
 @app.get("/ui", response_class=HTMLResponse)
 async def ui():
     """UI documentation page"""
+    return """
     <!DOCTYPE html>
     <html>
     <head>
         <title>HTML to PDF API</title>
         <meta name="viewport" content="width=device-width, initial-scale=1">
         <style>
+            * { margin: 0; padding: 0; box-sizing: border-box; }
+            body {
                 font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Arial, sans-serif;
                 line-height: 1.6;
                 color: #333;
                 background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
                 min-height: 100vh;
                 padding: 20px;
+            }
+            .container {
                 max-width: 900px;
                 margin: 0 auto;
                 background: white;
                 border-radius: 10px;
                 padding: 40px;
                 box-shadow: 0 10px 40px rgba(0,0,0,0.2);
+            }
+            h1 { color: #667eea; margin-bottom: 10px; font-size: 2.5em; }
+            .status {
                 display: inline-block;
                 background: #10b981;
                 color: white;
                 border-radius: 20px;
                 font-size: 0.9em;
                 margin-bottom: 30px;
+            }
+            h2 { color: #333; margin: 30px 0 15px; border-bottom: 2px solid #667eea; padding-bottom: 10px; }
+            .endpoint {
                 background: #f8f9fa;
                 border-left: 4px solid #667eea;
                 padding: 20px;
                 margin: 15px 0;
                 border-radius: 5px;
+            }
+            .endpoint h3 { color: #667eea; margin-bottom: 10px; }
+            code {
                 background: #e9ecef;
                 padding: 3px 8px;
                 border-radius: 4px;
                 font-family: 'Courier New', monospace;
                 font-size: 0.9em;
+            }
+            pre {
+                background: #2d3748;
+                color: #fff;
+                padding: 15px;
+                border-radius: 5px;
+                overflow-x: auto;
+                margin: 10px 0;
+            }
+            ul { margin-left: 20px; }
+            li { margin: 8px 0; }
+            .btn {
                 display: inline-block;
                 background: #667eea;
                 color: white;
                 text-decoration: none;
                 margin: 5px;
                 transition: all 0.3s;
+            }
+            .btn:hover {
                 background: #5568d3;
                 transform: translateY(-2px);
                 box-shadow: 0 4px 12px rgba(102, 126, 234, 0.4);
+            }
         </style>
     </head>
     <body>
         <div class="container">
             <h1>📄 HTML to PDF Converter API</h1>
+            <span class="status">✓ Online</span>
             <p style="margin: 20px 0; font-size: 1.1em;">
                 A powerful API to convert HTML documents to PDF with support for
 def convert_to_pdf(html: str, ratio: str) -> bytes:
     """Convert HTML to PDF using Puppeteer"""
     temp_dir = tempfile.mkdtemp()
     try:
         html = inject_page_css(html, ratio)
             ['node', '/app/puppeteer_pdf.js', html_file, ratio],
             capture_output=True,
             text=True,
+            timeout=60,
             cwd='/app'
         )
         if result.returncode != 0:
             logger.error(f"Conversion failed: {result.stderr}")
+            raise Exception(f"PDF conversion failed: {result.stderr}")
         pdf_file = html_file.replace('.html', '.pdf')
         if not os.path.exists(pdf_file):
+            raise Exception("PDF file was not generated")
         with open(pdf_file, 'rb') as f:
             pdf_bytes = f.read()
         logger.info(f"PDF generated: {len(pdf_bytes)} bytes")
         return pdf_bytes
     finally:
         shutil.rmtree(temp_dir, ignore_errors=True)
             }
         )
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))
             }
         )
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))
             "size_bytes": len(pdf)
         })
     except Exception as e:
         logger.error(f"Error: {str(e)}")
         raise HTTPException(500, str(e))