Add password to PyPDR loader and parser (#6908)

Add password to PyPDR loader and parser

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>

langchain/document_loaders/parsers/pdf.py

@@ -1,5 +1,5 @@
 """Module contains common parsers for PDFs."""
-from typing import Any, Iterator, Mapping, Optional
+from typing import Any, Iterator, Mapping, Optional, Union
 
 from langchain.document_loaders.base import BaseBlobParser
 from langchain.document_loaders.blob_loaders import Blob
@@ -9,12 +9,15 @@ from langchain.schema import Document
 class PyPDFParser(BaseBlobParser):
     """Loads a PDF with pypdf and chunks at character level."""
 
+    def __init__(self, password: Optional[Union[str, bytes]] = None):
+        self.password = password
+
     def lazy_parse(self, blob: Blob) -> Iterator[Document]:
         """Lazily parse the blob."""
         import pypdf
 
         with blob.as_bytes_io() as pdf_file_obj:
-            pdf_reader = pypdf.PdfReader(pdf_file_obj)
+            pdf_reader = pypdf.PdfReader(pdf_file_obj, password=self.password)
             yield from [
                 Document(
                     page_content=page.extract_text(),

langchain/document_loaders/pdf.py

@@ -7,7 +7,7 @@ import time
 from abc import ABC
 from io import StringIO
 from pathlib import Path
-from typing import Any, Iterator, List, Mapping, Optional
+from typing import Any, Iterator, List, Mapping, Optional, Union
 from urllib.parse import urlparse
 
 import requests
@@ -100,7 +100,9 @@ class PyPDFLoader(BasePDFLoader):
     Loader also stores page numbers in metadatas.
     """
 
-    def __init__(self, file_path: str) -> None:
+    def __init__(
+        self, file_path: str, password: Optional[Union[str, bytes]] = None
+    ) -> None:
         """Initialize with file path."""
         try:
             import pypdf  # noqa:F401
@@ -108,7 +110,7 @@ class PyPDFLoader(BasePDFLoader):
             raise ImportError(
                 "pypdf package not found, please install it with " "`pip install pypdf`"
             )
-        self.parser = PyPDFParser()
+        self.parser = PyPDFParser(password=password)
         super().__init__(file_path)
 
     def load(self) -> List[Document]: