From 4a52a71956a8d46fcb7294ac71734504bb09bcc2 Mon Sep 17 00:00:00 2001
From: S. Solomon Darnell
Date: Fri, 28 Mar 2025 21:52:21 -0500
Subject: two version of R2R are here

---
 R2R/r2r/parsers/media/pdf_parser.py | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100755 R2R/r2r/parsers/media/pdf_parser.py

(limited to 'R2R/r2r/parsers/media/pdf_parser.py')

diff --git a/R2R/r2r/parsers/media/pdf_parser.py b/R2R/r2r/parsers/media/pdf_parser.py
new file mode 100755
index 00000000..b60a9b33
--- /dev/null
+++ b/R2R/r2r/parsers/media/pdf_parser.py
@@ -0,0 +1,34 @@
+import string
+from io import BytesIO
+from typing import AsyncGenerator
+
+from r2r.base.abstractions.document import DataType
+from r2r.base.parsers.base_parser import AsyncParser
+
+
+class PDFParser(AsyncParser[DataType]):
+    """A parser for PDF data."""
+
+    def __init__(self):
+        try:
+            from pypdf import PdfReader
+
+            self.PdfReader = PdfReader
+        except ImportError:
+            raise ValueError(
+                "Error, `pypdf` is required to run `PyPDFParser`. Please install it using `pip install pypdf`."
+            )
+
+    async def ingest(self, data: DataType) -> AsyncGenerator[str, None]:
+        """Ingest PDF data and yield text from each page."""
+        if isinstance(data, str):
+            raise ValueError("PDF data must be in bytes format.")
+
+        pdf = self.PdfReader(BytesIO(data))
+        for page in pdf.pages:
+            page_text = page.extract_text()
+            if page_text is not None:
+                page_text = "".join(
+                    filter(lambda x: x in string.printable, page_text)
+                )
+                yield page_text
-- 
cgit v1.2.3