community[minor]: Add ScrapingAnt Loader Community Integration (#24514)

Added [ScrapingAnt](https://scrapingant.com/) Web Loader integration.
ScrapingAnt is a web scraping API that allows extracting web page data
into accessible and well-formatted markdown.

Description: Added ScrapingAnt web loader for retrieving web page data
as markdown
Dependencies: scrapingant-client
Twitter: @WeRunTheWorld3

---------

Co-authored-by: Oleg Kulyk <oleg@scrapingant.com>

libs/community/langchain_community/document_loaders/__init__.py

@@ -411,6 +411,9 @@ if TYPE_CHECKING:
     from langchain_community.document_loaders.scrapfly import (
         ScrapflyLoader,
     )
+    from langchain_community.document_loaders.scrapingant import (
+        ScrapingAntLoader,
+    )
     from langchain_community.document_loaders.sharepoint import (
         SharePointLoader,
     )
@@ -666,6 +669,7 @@ _module_lookup = {
     "S3DirectoryLoader": "langchain_community.document_loaders.s3_directory",
     "S3FileLoader": "langchain_community.document_loaders.s3_file",
     "ScrapflyLoader": "langchain_community.document_loaders.scrapfly",
+    "ScrapingAntLoader": "langchain_community.document_loaders.scrapingant",
     "SQLDatabaseLoader": "langchain_community.document_loaders.sql_database",
     "SRTLoader": "langchain_community.document_loaders.srt",
     "SeleniumURLLoader": "langchain_community.document_loaders.url_selenium",
@@ -870,6 +874,7 @@ __all__ = [
     "S3DirectoryLoader",
     "S3FileLoader",
     "ScrapflyLoader",
+    "ScrapingAntLoader",
     "SQLDatabaseLoader",
     "SRTLoader",
     "SeleniumURLLoader",

libs/community/langchain_community/document_loaders/scrapingant.py

@@ -0,0 +1,66 @@
+"""ScrapingAnt Web Extractor."""
+
+import logging
+from typing import Iterator, List, Optional
+
+from langchain_core.document_loaders import BaseLoader
+from langchain_core.documents import Document
+from langchain_core.utils import get_from_env
+
+logger = logging.getLogger(__file__)
+
+
+class ScrapingAntLoader(BaseLoader):
+    """Turn an url to LLM accessible markdown with `ScrapingAnt`.
+
+    For further details, visit: https://docs.scrapingant.com/python-client
+    """
+
+    def __init__(
+        self,
+        urls: List[str],
+        *,
+        api_key: Optional[str] = None,
+        scrape_config: Optional[dict] = None,
+        continue_on_failure: bool = True,
+    ) -> None:
+        """Initialize client.
+
+        Args:
+            urls: List of urls to scrape.
+            api_key: The ScrapingAnt API key. If not specified must have env var
+                SCRAPINGANT_API_KEY set.
+            scrape_config: The scraping config from ScrapingAntClient.markdown_request
+            continue_on_failure: Whether to continue if scraping an url fails.
+        """
+        try:
+            from scrapingant_client import ScrapingAntClient
+        except ImportError:
+            raise ImportError(
+                "`scrapingant-client` package not found,"
+                " run `pip install scrapingant-client`"
+            )
+        if not urls:
+            raise ValueError("URLs must be provided.")
+        api_key = api_key or get_from_env("api_key", "SCRAPINGANT_API_KEY")
+        self.client = ScrapingAntClient(token=api_key)
+        self.urls = urls
+        self.scrape_config = scrape_config
+        self.continue_on_failure = continue_on_failure
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Fetch data from ScrapingAnt."""
+
+        scrape_config = self.scrape_config if self.scrape_config is not None else {}
+        for url in self.urls:
+            try:
+                result = self.client.markdown_request(url=url, **scrape_config)
+                yield Document(
+                    page_content=result.markdown,
+                    metadata={"url": result.url},
+                )
+            except Exception as e:
+                if self.continue_on_failure:
+                    logger.error(f"Error fetching data from {url}, exception: {e}")
+                else:
+                    raise e

libs/community/tests/unit_tests/document_loaders/test_imports.py

@@ -142,6 +142,7 @@ EXPECTED_ALL = [
     "S3DirectoryLoader",
     "S3FileLoader",
     "ScrapflyLoader",
+    "ScrapingAntLoader",
     "SQLDatabaseLoader",
     "SRTLoader",
     "SeleniumURLLoader",