dont fail parsing parts of the pdf

2016-01-25 15:51:54 +05:30 · 2016-01-25 15:51:54 +05:30 · c03f72b47c
commit c03f72b47c
parent bfa29b469d
1 changed files with 8 additions and 3 deletions
--- a/oml/media/pdf.py
+++ b/oml/media/pdf.py
@ -131,7 +131,10 @@ def info(pdf):
            toc = parse_tableofcontents(pdfreader)
            if toc:
                data['tableofcontents'] = toc
-            info = pdfreader.getDocumentInfo()
+            try:
+                info = pdfreader.getDocumentInfo()
+            except:
+                info = None
            if info:
                for key in info:
                    if info[key]:
@ -144,8 +147,10 @@ def info(pdf):
                            data[key[1:].lower()] = value
                        except:
                            pass
-
-            xmp = pdfreader.getXmpMetadata()
+            try:
+                xmp = pdfreader.getXmpMetadata()
+            except:
+                xmp = None
            if xmp:
                for key in dir(xmp):
                    if key.startswith('dc_'):