From 357e268e963c869102f4f9e8de01ab85cf8d6daf Mon Sep 17 00:00:00 2001
From: Bryan Bishop <kanzure@gmail.com>
Date: Sat, 9 Feb 2013 07:41:50 -0600
Subject: [PATCH] use pdfparanoia to remove watermarks

---
 modules/papers.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/modules/papers.py b/modules/papers.py
index e4f67a4..22b88bd 100644
--- a/modules/papers.py
+++ b/modules/papers.py
@@ -9,6 +9,8 @@ import requests
 import lxml.etree
 from StringIO import StringIO
 
+import pdfparanoia
+
 def download(phenny, input, verbose=True):
     """
     Downloads a paper.
@@ -202,6 +204,7 @@ def download_url(url):
                     new_response = requests.get(pdf_url, headers={"User-Agent": "time-machine/1.0"})
                     new_content = new_response.content
                     if "pdf" in new_response.headers["content-type"]:
+                        new_content = pdfparanoia.scrub(new_content)
                         extension = ".pdf"
                 except Exception:
                     pass
@@ -244,6 +247,9 @@ def download_url(url):
 
     path = os.path.join("/home/bryan/public_html/papers2/paperbot/", title + extension)
 
+    if extension in [".pdf", "pdf"]:
+        content = pdfparanoia.scrub(content)
+
     file_handler = open(path, "w")
     file_handler.write(content)
     file_handler.close()