From 3eba14e973b800419e24fc29df8173e1fc2550d9 Mon Sep 17 00:00:00 2001
From: deanchanter <deanchanter@gmail.com>
Date: Tue, 29 Apr 2025 09:06:46 -0400
Subject: [PATCH] adding pdf support

---
 mcpdoc/main.py | 22 ++++++++++++++++++++--
 pyproject.toml |  1 +
 uv.lock        | 14 ++++++++++++++
 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/mcpdoc/main.py b/mcpdoc/main.py
index 278f99e..6d32815 100644
--- a/mcpdoc/main.py
+++ b/mcpdoc/main.py
@@ -7,7 +7,7 @@
 from markdownify import markdownify
 from mcp.server.fastmcp import FastMCP
 from typing_extensions import NotRequired, TypedDict
-
+from pypdf import PdfReader
 
 class DocSource(TypedDict):
     """A source of documentation for a library or a package."""
@@ -21,6 +21,17 @@ class DocSource(TypedDict):
     description: NotRequired[str]
     """Description of the documentation source (optional)."""
 
+def extract_text_from_pdf(pdf_file) -> str:
+    """Extract text content from a PDF file."""
+    try:
+        reader = PdfReader(pdf_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+        return text.strip()
+    except Exception as e:
+        raise ValueError(f"Failed to extract text from PDF: {str(e)}")
+
 
 def extract_domain(url: str) -> str:
     """Extract domain from URL.
@@ -213,7 +224,14 @@ async def fetch_docs(url: str) -> str:
             try:
                 response = await httpx_client.get(url, timeout=timeout)
                 response.raise_for_status()
-                return markdownify(response.text)
+                if url.endswith(".txt"):
+                    return  response.text
+                elif url.endswith(".md"):
+                    return markdownify(response.text)
+                elif url.endswith(".pdf"):
+                    return extract_text_from_pdf(io.BytesIO(response.content))
+                else:
+                    return markdownify(response.text)
             except (httpx.HTTPStatusError, httpx.RequestError) as e:
                 return f"Encountered an HTTP error: {str(e)}"
 
diff --git a/pyproject.toml b/pyproject.toml
index 7e6f899..939a39e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,6 +9,7 @@ dependencies = [
     "httpx>=0.28.1",
     "markdownify>=1.1.0",
     "mcp[cli]>=1.4.1",
+    "pypdf>=5.4.0",
     "pyyaml>=6.0.1",
 ]
 
diff --git a/uv.lock b/uv.lock
index 9dd00bb..80b1189 100644
--- a/uv.lock
+++ b/uv.lock
@@ -265,6 +265,7 @@ dependencies = [
     { name = "httpx" },
     { name = "markdownify" },
     { name = "mcp", extra = ["cli"] },
+    { name = "pypdf" },
     { name = "pyyaml" },
 ]
 
@@ -284,6 +285,7 @@ requires-dist = [
     { name = "httpx", specifier = ">=0.28.1" },
     { name = "markdownify", specifier = ">=1.1.0" },
     { name = "mcp", extras = ["cli"], specifier = ">=1.4.1" },
+    { name = "pypdf", specifier = ">=5.4.0" },
     { name = "pyyaml", specifier = ">=6.0.1" },
 ]
 
@@ -436,6 +438,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8a/0b/9fcc47d19c48b59121088dd6da2488a49d5f72dacf8262e2790a1d2c7d15/pygments-2.19.1-py3-none-any.whl", hash = "sha256:9ea1544ad55cecf4b8242fab6dd35a93bbce657034b0611ee383099054ab6d8c", size = 1225293 },
 ]
 
+[[package]]
+name = "pypdf"
+version = "5.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f9/43/4026f6ee056306d0e0eb04fcb9f2122a0f1a5c57ad9dc5e0d67399e47194/pypdf-5.4.0.tar.gz", hash = "sha256:9af476a9dc30fcb137659b0dec747ea94aa954933c52cf02ee33e39a16fe9175", size = 5012492 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0b/27/d83f8f2a03ca5408dc2cc84b49c0bf3fbf059398a6a2ea7c10acfe28859f/pypdf-5.4.0-py3-none-any.whl", hash = "sha256:db994ab47cadc81057ea1591b90e5b543e2b7ef2d0e31ef41a9bfe763c119dab", size = 302306 },
+]
+
 [[package]]
 name = "pytest"
 version = "8.3.5"