feat: add WebPreviews blocks

apps/api/pyproject.toml

@@ -38,6 +38,7 @@ dependencies = [
     "stripe>=11.1.1",
     "python-jose>=3.3.0",
     "logfire[sqlalchemy]>=3.8.0",
+    "beautifulsoup4>=4.13.4",
 ]
 
 [tool.ruff]

apps/api/src/router.py

@@ -10,6 +10,7 @@ from src.routers.ee import cloud_internal, payments
 from src.routers.install import install
 from src.services.dev.dev import isDevModeEnabledOrRaise
 from src.services.install.install import isInstallModeEnabled
+from src.routers.utils import router as utils_router
 
 
 v1_router = APIRouter(prefix="/api/v1")
@@ -61,3 +62,5 @@ v1_router.include_router(
     tags=["install"],
     dependencies=[Depends(isInstallModeEnabled)],
 )
+
+v1_router.include_router(utils_router, prefix="/utils", tags=["utils"])

apps/api/src/routers/utils.py

@@ -0,0 +1,12 @@
+from fastapi import APIRouter, HTTPException, Query
+from src.services.utils.link_preview import fetch_link_preview
+
+router = APIRouter()
+
+@router.get("/link-preview")
+async def link_preview(url: str = Query(..., description="URL to preview")):
+    try:
+        data = await fetch_link_preview(url)
+        return data
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Failed to fetch link preview: {str(e)}") 

apps/api/src/services/utils/link_preview.py

@@ -0,0 +1,70 @@
+import httpx
+from bs4 import BeautifulSoup, Tag
+from typing import Optional, Dict
+from urllib.parse import urljoin, urlparse
+
+async def fetch_link_preview(url: str) -> Dict[str, Optional[str]]:
+    async with httpx.AsyncClient(follow_redirects=True, timeout=10) as client:
+        response = await client.get(url)
+        response.raise_for_status()
+        html = response.text
+
+    soup = BeautifulSoup(html, 'html.parser')
+
+    def get_meta(property_name: str, attr: str = 'property') -> Optional[str]:
+        tag = soup.find('meta', attrs={attr: property_name})
+        if tag and isinstance(tag, Tag) and tag.has_attr('content'):
+            content = tag['content']
+            if isinstance(content, str):
+                return content
+        return None
+
+    # Title
+    title = soup.title.string.strip() if soup.title and soup.title.string else None
+    # Description
+    description = get_meta('og:description') or get_meta('description', 'name')
+    # OG Image
+    og_image = get_meta('og:image')
+    if og_image and isinstance(og_image, str) and not og_image.startswith('http'):
+        og_image = urljoin(url, og_image)
+    # Favicon (robust)
+    favicon = None
+    icon_rels = [
+        'icon',
+        'shortcut icon',
+        'apple-touch-icon',
+        'apple-touch-icon-precomposed',
+    ]
+    for link in soup.find_all('link'):
+        if not isinstance(link, Tag):
+            continue
+        rels = link.get('rel')
+        href = link.get('href')
+        if rels and href:
+            rels_lower = [r.lower() for r in rels]
+            if any(rel in rels_lower for rel in icon_rels):
+                if isinstance(href, str):
+                    favicon = href
+                    break
+    # Fallback to /favicon.ico if not found
+    if not favicon:
+        parsed = urlparse(url)
+        favicon = f"{parsed.scheme}://{parsed.netloc}/favicon.ico"
+    elif favicon and not favicon.startswith('http'):
+        favicon = urljoin(url, favicon)
+    # OG Title
+    og_title = get_meta('og:title')
+    # OG Type
+    og_type = get_meta('og:type')
+    # OG URL
+    og_url = get_meta('og:url')
+
+    return {
+        'title': og_title or title,
+        'description': description,
+        'og_image': og_image,
+        'favicon': favicon,
+        'og_type': og_type,
+        'og_url': og_url or url,
+        'url': url,
+    } 

apps/api/uv.lock

@@ -157,6 +157,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/b9/d51d34e6cd6d887adddb28a8680a1d34235cc45b9d6e238ce39b98199ca0/bcrypt-4.2.1-cp39-abi3-win_amd64.whl", hash = "sha256:e84e0e6f8e40a242b11bce56c313edc2be121cec3e0ec2d76fce01f6af33c07c", size = 153078 },
 ]
 
+[[package]]
+name = "beautifulsoup4"
+version = "4.13.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "soupsieve" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285 },
+]
+
 [[package]]
 name = "boto3"
 version = "1.36.22"
@@ -999,6 +1012,7 @@ source = { virtual = "." }
 dependencies = [
     { name = "alembic" },
     { name = "alembic-postgresql-enum" },
+    { name = "beautifulsoup4" },
     { name = "boto3" },
     { name = "botocore" },
     { name = "chromadb" },
@@ -1037,6 +1051,7 @@ dependencies = [
 requires-dist = [
     { name = "alembic", specifier = ">=1.13.2" },
     { name = "alembic-postgresql-enum", specifier = ">=1.2.0" },
+    { name = "beautifulsoup4", specifier = ">=4.13.4" },
     { name = "boto3", specifier = ">=1.34.79" },
     { name = "botocore", specifier = ">=1.34.93" },
     { name = "chromadb", specifier = "==0.5.16" },
@@ -1909,6 +1924,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
 ]
 
+[[package]]
+name = "soupsieve"
+version = "2.7"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677 },
+]
+
 [[package]]
 name = "sqlalchemy"
 version = "2.0.38"