Github/guess-filename.py
2
0
Fork 1
mirror of https://github.com/novoid/guess-filename.py.git synced 2026-02-16 05:14:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

PDF exception handling now for all exceptions

Browse source
This commit is contained in:
Karl Voit 2017-12-24 16:52:48 +01:00
parent a696c07310
commit a60331bd22
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
guessfilename.py
View file

@ -651,17 +651,17 @@ class GuessFilename(object):
try:
pdffile = PyPDF2.PdfFileReader(open(filename, "rb"))
# use first and second page of content only:
if pdffile.getNumPages() > 1:
content = pdffile.pages[0].extractText() + pdffile.pages[1].extractText()
elif pdffile.getNumPages() == 1:
content = pdffile.pages[0].extractText()
else:
logging.error('Could not determine number of pages of PDF content! (skipping content analysis)')
return False
except:
logging.error('Could not read PDF file content. Skipping its content.')
return False
# use first and second page of content only:
if pdffile.getNumPages() > 1:
content = pdffile.pages[0].extractText() + pdffile.pages[1].extractText()
elif pdffile.getNumPages() == 1:
content = pdffile.pages[0].extractText()
else:
logging.error('Could not determine number of pages of PDF content! (skipping content analysis)')
return False
if len(content) == 0:
logging.warning('Could read PDF file content but it is empty (skipping content analysis)')