community: support advanced text extraction options for pdf documents (#20265)

**Description:** 
- Updated constructors in PyPDFParser and PyPDFLoader to handle
`extraction_mode` and additional kwargs, aligning with the capabilities
of `PageObject.extract_text()` from pypdf.

- Added `test_pypdf_loader_with_layout` along with a corresponding
example text file to validate layout extraction from PDFs.

**Issue:** fixes #19735 

**Dependencies:** This change requires updating the pypdf dependency
from version 3.4.0 to at least 4.0.0.

Additional changes include the addition of a new test
test_pypdf_loader_with_layout and an example text file to ensure the
functionality of layout extraction from PDFs aligns with the new
capabilities.

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>

libs/community/langchain_community/document_loaders/parsers/pdf.py

@@ -6,6 +6,7 @@ import warnings
 from typing import (
     TYPE_CHECKING,
     Any,
+    Dict,
     Iterable,
     Iterator,
     Mapping,
@@ -27,6 +28,7 @@ if TYPE_CHECKING:
     import pdfplumber.page
     import pypdf._page
     import pypdfium2._helpers.page
+    from pypdf import PageObject
     from textractor.data.text_linearization_config import TextLinearizationConfig
 
 
@@ -83,10 +85,17 @@ class PyPDFParser(BaseBlobParser):
     """Load `PDF` using `pypdf`"""
 
     def __init__(
-        self, password: Optional[Union[str, bytes]] = None, extract_images: bool = False
+        self,
+        password: Optional[Union[str, bytes]] = None,
+        extract_images: bool = False,
+        *,
+        extraction_mode: str = "plain",
+        extraction_kwargs: Optional[Dict[str, Any]] = None,
     ):
         self.password = password
         self.extract_images = extract_images
+        self.extraction_mode = extraction_mode
+        self.extraction_kwargs = extraction_kwargs or {}
 
     def lazy_parse(self, blob: Blob) -> Iterator[Document]:  # type: ignore[valid-type]
         """Lazily parse the blob."""
@@ -98,11 +107,23 @@ class PyPDFParser(BaseBlobParser):
                 "`pip install pypdf`"
             )
 
+        def _extract_text_from_page(page: "PageObject") -> str:
+            """
+            Extract text from image given the version of pypdf.
+            """
+            if pypdf.__version__.startswith("3"):
+                return page.extract_text()
+            else:
+                return page.extract_text(
+                    extraction_mode=self.extraction_mode, **self.extraction_kwargs
+                )
+
         with blob.as_bytes_io() as pdf_file_obj:  # type: ignore[attr-defined]
             pdf_reader = pypdf.PdfReader(pdf_file_obj, password=self.password)
+
             yield from [
                 Document(
-                    page_content=page.extract_text()
+                    page_content=_extract_text_from_page(page=page)
                     + self._extract_images_from_page(page),
                     metadata={"source": blob.source, "page": page_number},  # type: ignore[attr-defined]
                 )