Add new loader to load pdf as html content (#2607)

Adds a new pdf loader using the existing dependency on PDFMiner. 

The new loader can be helpful for chunking texts semantically into
sections as the output html content can be parsed via `BeautifulSoup` to
get more structured and rich information about font size, page numbers,
pdf headers/footers, etc. which may not be available otherwise with
other pdf loaders

tests/integration_tests/document_loaders/test_pdf.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 from langchain.document_loaders import (
     PDFMinerLoader,
+    PDFMinerPDFasHTMLLoader,
     PyMuPDFLoader,
     UnstructuredPDFLoader,
 )
@@ -31,6 +32,21 @@ def test_pdfminer_loader() -> None:
     assert len(docs) == 1
 
 
+def test_pdfminer_pdf_as_html_loader() -> None:
+    """Test PDFMinerPDFasHTMLLoader."""
+    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
+    loader = PDFMinerPDFasHTMLLoader(str(file_path))
+    docs = loader.load()
+
+    assert len(docs) == 1
+
+    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
+    loader = PDFMinerPDFasHTMLLoader(str(file_path))
+
+    docs = loader.load()
+    assert len(docs) == 1
+
+
 def test_pymupdf_loader() -> None:
     """Test PyMuPDF loader."""
     file_path = Path(__file__).parent.parent / "examples/hello.pdf"