unstructured[patch]: support loading URLs (#26670)

`unstructured.partition.auto.partition` supports a `url` kwarg, but
`url` in `UnstructuredLoader.__init__` is reserved for the server URL.
Here we add a `web_url` kwarg that is passed to the partition kwargs:
```python
self.unstructured_kwargs["url"] = web_url
```

docs/docs/integrations/document_loaders/unstructured_file.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/document_loaders/file_loaders/unstructured/)|\n",
     "| :--- | :--- | :---: | :---: |  :---: |\n",
-    "| [UnstructuredLoader](https://python.langchain.com/api_reference/unstructured/document_loaders/langchain_unstructured.document_loaders.UnstructuredLoader.html) | [langchain_community](https://python.langchain.com/api_reference/unstructured/index.html) | ✅ | ❌ | ✅ | \n",
+    "| [UnstructuredLoader](https://python.langchain.com/api_reference/unstructured/document_loaders/langchain_unstructured.document_loaders.UnstructuredLoader.html) | [langchain_unstructured](https://python.langchain.com/api_reference/unstructured/index.html) | ✅ | ❌ | ✅ | \n",
     "### Loader features\n",
     "| Source | Document Lazy Loading | Native Async Support\n",
     "| :---: | :---: | :---: | \n",
@@ -519,6 +519,47 @@
     "print(\"Length of text in the document:\", len(docs[0].page_content))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3ec3c22d-02cd-498b-921f-b839d1404f32",
+   "metadata": {},
+   "source": [
+    "## Loading web pages\n",
+    "\n",
+    "`UnstructuredLoader` accepts a `web_url` kwarg when run locally that populates the `url` parameter of the underlying Unstructured [partition](https://docs.unstructured.io/open-source/core-functionality/partitioning). This allows for the parsing of remotely hosted documents, such as HTML web pages.\n",
+    "\n",
+    "Example usage:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "bf9a8546-659d-4861-bff2-fdf1ad93ac65",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page_content='Example Domain' metadata={'category_depth': 0, 'languages': ['eng'], 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'Title', 'element_id': 'fdaa78d856f9d143aeeed85bf23f58f8'}\n",
+      "\n",
+      "page_content='This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.' metadata={'languages': ['eng'], 'parent_id': 'fdaa78d856f9d143aeeed85bf23f58f8', 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'NarrativeText', 'element_id': '3652b8458b0688639f973fe36253c992'}\n",
+      "\n",
+      "page_content='More information...' metadata={'category_depth': 0, 'link_texts': ['More information...'], 'link_urls': ['https://www.iana.org/domains/example'], 'languages': ['eng'], 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'Title', 'element_id': '793ab98565d6f6d6f3a6d614e3ace2a9'}\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_unstructured import UnstructuredLoader\n",
+    "\n",
+    "loader = UnstructuredLoader(web_url=\"https://www.example.com\")\n",
+    "docs = loader.load()\n",
+    "\n",
+    "for doc in docs:\n",
+    "    print(f\"{doc}\\n\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "ce01aa40",
@@ -546,7 +587,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

libs/partners/unstructured/langchain_unstructured/document_loaders.py

@@ -76,6 +76,25 @@ class UnstructuredLoader(BaseLoader):
             {'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-07-25T21:28:58', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}
 
 
+    Load URL:
+        .. code-block:: python
+
+            loader = UnstructuredLoader(web_url="https://www.example.com/")
+            print(docs[0])
+
+        .. code-block:: none
+
+            page_content='Example Domain' metadata={'category_depth': 0, 'languages': ['eng'], 'filetype': 'text/html', 'url': 'https://www.example.com/', 'category': 'Title', 'element_id': 'fdaa78d856f9d143aeeed85bf23f58f8'}
+
+        .. code-block:: python
+
+            print(docs[1])
+
+        .. code-block:: none
+
+            page_content='This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.' metadata={'languages': ['eng'], 'parent_id': 'fdaa78d856f9d143aeeed85bf23f58f8', 'filetype': 'text/html', 'url': 'https://www.example.com/', 'category': 'NarrativeText', 'element_id': '3652b8458b0688639f973fe36253c992'}
+
+
     References
     ----------
     https://docs.unstructured.io/api-reference/api-services/sdk
@@ -95,6 +114,7 @@ class UnstructuredLoader(BaseLoader):
         api_key: Optional[str] = None,
         client: Optional[UnstructuredClient] = None,
         url: Optional[str] = None,
+        web_url: Optional[str] = None,
         **kwargs: Any,
     ):
         """Initialize loader."""
@@ -124,6 +144,8 @@ class UnstructuredLoader(BaseLoader):
         self.partition_via_api = partition_via_api
         self.post_processors = post_processors
         self.unstructured_kwargs = kwargs
+        if web_url:
+            self.unstructured_kwargs["url"] = web_url
 
     def lazy_load(self) -> Iterator[Document]:
         """Load file(s) to the _UnstructuredBaseLoader."""

libs/partners/unstructured/tests/integration_tests/test_document_loaders.py

@@ -128,6 +128,17 @@ def test_loader_partitions_locally_and_applies_post_processors(
     assert docs[0].page_content.endswith("THE END!")
 
 
+@pytest.mark.local
+def test_url_loader() -> None:
+    docs = UnstructuredLoader(web_url="https://www.example.com/").load()
+
+    for doc in docs:
+        assert doc.page_content
+        assert doc.metadata["filetype"] == "text/html"
+        assert doc.metadata["url"] == "https://www.example.com/"
+        assert doc.metadata["category"]
+
+
 # -- API partition --