langchain-gluedly 0.1.0__tar.gz

langchain_gluedly-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+*.py[cod]
+.pytest_cache/
+*.egg-info/
+.venv/
+dist/
+build/
+.DS_Store

langchain_gluedly-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Donatas Petrikauskas
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

langchain_gluedly-0.1.0/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.5
+Name: langchain-gluedly
+Version: 0.1.0
+Summary: LangChain document loader for Gluedly scrape snapshots
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: langchain-core>=0.3.0
+Requires-Dist: requests>=2.31.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == 'dev'
+Requires-Dist: responses>=0.25.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# langchain-gluedly
+
+LangChain `BaseLoader` that turns Gluedly scrape snapshots into `Document` objects.
+
+## Install
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from langchain_gluedly import GluedlyLoader
+
+loader = GluedlyLoader(
+    api_key="YOUR_GLUEDLY_API_KEY",
+    page_id=12,
+    # snapshot_id=100,  # optional; omit to use the latest snapshot
+    # base_url="https://gluedly.com/api/v1",
+)
+documents = loader.load()
+```
+
+Each row becomes one document. Content preference: `markdown` → `summary` → `description` → `str(row)`.
+
+## Example
+
+```bash
+export GLUEDLY_API_KEY=…
+export GLUEDLY_PAGE_ID=12
+python examples/load_documents.py
+```
+
+## Tests
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

langchain_gluedly-0.1.0/README.md

@@ -0,0 +1,40 @@
+# langchain-gluedly
+
+LangChain `BaseLoader` that turns Gluedly scrape snapshots into `Document` objects.
+
+## Install
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from langchain_gluedly import GluedlyLoader
+
+loader = GluedlyLoader(
+    api_key="YOUR_GLUEDLY_API_KEY",
+    page_id=12,
+    # snapshot_id=100,  # optional; omit to use the latest snapshot
+    # base_url="https://gluedly.com/api/v1",
+)
+documents = loader.load()
+```
+
+Each row becomes one document. Content preference: `markdown` → `summary` → `description` → `str(row)`.
+
+## Example
+
+```bash
+export GLUEDLY_API_KEY=…
+export GLUEDLY_PAGE_ID=12
+python examples/load_documents.py
+```
+
+## Tests
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

langchain_gluedly-0.1.0/examples/load_documents.py

@@ -0,0 +1,30 @@
+"""Example: load Gluedly snapshot rows into LangChain Documents."""
+
+from __future__ import annotations
+
+import os
+
+from langchain_gluedly import GluedlyLoader
+
+
+def main() -> None:
+    api_key = os.environ["GLUEDLY_API_KEY"]
+    page_id = int(os.environ.get("GLUEDLY_PAGE_ID", "12"))
+    base_url = os.environ.get("GLUEDLY_BASE_URL", "https://gluedly.com/api/v1")
+
+    loader = GluedlyLoader(
+        api_key=api_key,
+        page_id=page_id,
+        base_url=base_url,
+    )
+    documents = loader.load()
+
+    print(f"Loaded {len(documents)} documents from page {page_id}")
+    for doc in documents[:3]:
+        print("---")
+        print(doc.metadata)
+        print(doc.page_content[:400])
+
+
+if __name__ == "__main__":
+    main()

langchain_gluedly-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "langchain-gluedly"
+version = "0.1.0"
+description = "LangChain document loader for Gluedly scrape snapshots"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+dependencies = [
+  "langchain-core>=0.3.0",
+  "requests>=2.31.0",
+]
+
+[project.optional-dependencies]
+dev = [
+  "pytest>=8.0.0",
+  "responses>=0.25.0",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/langchain_gluedly"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = ["tests"]

langchain_gluedly-0.1.0/src/langchain_gluedly/__init__.py

@@ -0,0 +1,5 @@
+"""LangChain integrations for Gluedly."""
+
+from langchain_gluedly.loader import GluedlyLoader
+
+__all__ = ["GluedlyLoader"]

langchain_gluedly-0.1.0/src/langchain_gluedly/loader.py

@@ -0,0 +1,82 @@
+"""Load web data snapshots from Gluedly into LangChain Document objects."""
+
+from __future__ import annotations
+
+from typing import Any, List, Optional
+
+import requests
+from langchain_core.document_loaders import BaseLoader
+from langchain_core.documents import Document
+
+DEFAULT_BASE_URL = "https://gluedly.com/api/v1"
+
+
+class GluedlyLoader(BaseLoader):
+    """Load web data snapshots from Gluedly into LangChain Document objects."""
+
+    def __init__(
+        self,
+        api_key: str,
+        page_id: int,
+        snapshot_id: Optional[int] = None,
+        base_url: str = DEFAULT_BASE_URL,
+        session: Optional[requests.Session] = None,
+        timeout: float = 30,
+    ) -> None:
+        if not api_key:
+            raise ValueError("api_key is required")
+
+        self.api_key = api_key
+        self.page_id = page_id
+        self.snapshot_id = snapshot_id
+        self.base_url = base_url.rstrip("/")
+        self.headers = {"Authorization": f"Bearer {self.api_key}"}
+        self.session = session or requests.Session()
+        self.timeout = timeout
+
+    def load(self) -> List[Document]:
+        target_snapshot_id = self.snapshot_id
+        if not target_snapshot_id:
+            res = self.session.get(
+                f"{self.base_url}/pages/{self.page_id}/data",
+                headers=self.headers,
+                timeout=self.timeout,
+            )
+            res.raise_for_status()
+            snapshots = res.json().get("data", [])
+            if not snapshots:
+                return []
+            target_snapshot_id = int(snapshots[0]["id"])
+
+        payload_res = self.session.get(
+            f"{self.base_url}/pages/{self.page_id}/data/{target_snapshot_id}",
+            headers=self.headers,
+            timeout=self.timeout,
+        )
+        payload_res.raise_for_status()
+        payload: dict[str, Any] = payload_res.json()
+
+        documents: List[Document] = []
+        rows = payload.get("data", {}).get("rows", [])
+        for idx, row in enumerate(rows):
+            if not isinstance(row, dict):
+                page_content = str(row)
+                source = f"page_{self.page_id}"
+            else:
+                page_content = (
+                    row.get("markdown")
+                    or row.get("summary")
+                    or row.get("description")
+                    or str(row)
+                )
+                source = row.get("url") or f"page_{self.page_id}"
+
+            metadata = {
+                "source": source,
+                "page_id": self.page_id,
+                "snapshot_id": target_snapshot_id,
+                "row_index": idx,
+            }
+            documents.append(Document(page_content=str(page_content), metadata=metadata))
+
+        return documents

langchain_gluedly-0.1.0/tests/test_loader.py

@@ -0,0 +1,94 @@
+from __future__ import annotations
+
+import responses
+
+from langchain_gluedly import GluedlyLoader
+
+BASE = "https://gluedly.com/api/v1"
+
+
+@responses.activate
+def test_load_resolves_latest_snapshot_and_maps_rows() -> None:
+    responses.add(
+        responses.GET,
+        f"{BASE}/pages/12/data",
+        json={"data": [{"id": 100}, {"id": 99}]},
+        status=200,
+    )
+    responses.add(
+        responses.GET,
+        f"{BASE}/pages/12/data/100",
+        json={
+            "id": 100,
+            "page_id": 12,
+            "data": {
+                "ok": True,
+                "rows": [
+                    {
+                        "url": "https://example.com/a",
+                        "markdown": "# Product A",
+                        "summary": "ignored when markdown present",
+                    },
+                    {
+                        "url": "https://example.com/b",
+                        "summary": "Summary only",
+                    },
+                ],
+                "match_counts": {},
+                "warnings": [],
+            },
+        },
+        status=200,
+    )
+
+    docs = GluedlyLoader(api_key="test-key", page_id=12).load()
+
+    assert len(docs) == 2
+    assert docs[0].page_content == "# Product A"
+    assert docs[0].metadata == {
+        "source": "https://example.com/a",
+        "page_id": 12,
+        "snapshot_id": 100,
+        "row_index": 0,
+    }
+    assert docs[1].page_content == "Summary only"
+    assert docs[1].metadata["row_index"] == 1
+
+
+@responses.activate
+def test_load_returns_empty_when_no_snapshots() -> None:
+    responses.add(
+        responses.GET,
+        f"{BASE}/pages/12/data",
+        json={"data": []},
+        status=200,
+    )
+
+    docs = GluedlyLoader(api_key="test-key", page_id=12).load()
+    assert docs == []
+
+
+@responses.activate
+def test_load_uses_explicit_snapshot_id() -> None:
+    responses.add(
+        responses.GET,
+        f"{BASE}/pages/12/data/55",
+        json={
+            "id": 55,
+            "page_id": 12,
+            "data": {
+                "ok": True,
+                "rows": [{"description": "From description"}],
+                "match_counts": {},
+                "warnings": [],
+            },
+        },
+        status=200,
+    )
+
+    docs = GluedlyLoader(api_key="test-key", page_id=12, snapshot_id=55).load()
+
+    assert len(docs) == 1
+    assert docs[0].page_content == "From description"
+    assert docs[0].metadata["snapshot_id"] == 55
+    assert len(responses.calls) == 1