phyks/bmc
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

catch PDFNotImplementedErrors

Browse Source
This commit is contained in:
Bryan Bishop 2013-02-11 10:03:28 -06:00
parent 5fbeedd76b
commit 05669229c4
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
modules/papers.py
View File

@ -101,7 +101,11 @@ def download(phenny, input, verbose=True):
data = response.content data = response.content
if "pdf" in response.headers["content-type"]: if "pdf" in response.headers["content-type"]:
data = pdfparanoia.scrub(StringIO(data)) try:
data = pdfparanoia.scrub(StringIO(data))
except:
# this is to avoid a PDFNotImplementedError
pass
# grr.. # grr..
title = title.encode("ascii", "ignore") title = title.encode("ascii", "ignore")
@ -256,7 +260,11 @@ def download_url(url):
path = os.path.join("/home/bryan/public_html/papers2/paperbot/", title + extension) path = os.path.join("/home/bryan/public_html/papers2/paperbot/", title + extension)
if extension in [".pdf", "pdf"]: if extension in [".pdf", "pdf"]:
content = pdfparanoia.scrub(StringIO(content)) try:
content = pdfparanoia.scrub(StringIO(content))
except:
# this is to avoid a PDFNotImplementedError
pass
file_handler = open(path, "w") file_handler = open(path, "w")
file_handler.write(content) file_handler.write(content)