Check PDF is from the RSC before cleaning

2013-05-13 21:01:52 +01:00 · 2013-05-13 21:01:52 +01:00 · c673d77ec6
parent 18140d838d
commit c673d77ec6
1 changed files with 28 additions and 25 deletions
--- a/pdfparanoia/plugins/rsc.py
+++ b/pdfparanoia/plugins/rsc.py
@ -35,6 +35,9 @@ class RoyalSocietyOfChemistry(Plugin):
            #"Table of Contents for this issue",
        ]

+        # Confirm the PDF is from the RSC
+        if "pubs.rsc.org" in content:
+            
            # parse the pdf into a pdfminer document
            pdf = parse_content(content)