joepie91/emailparser
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Skip a part if neither ascii nor windows-1252 decoding fallbacks succeed

Browse source
This commit is contained in:
Sven Slootweg 2012-05-28 02:40:31 +02:00
parent 1bc6105085
commit a0cc727a25
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
parse
View file

@ -114,7 +114,12 @@ for email_file in file_list:
try:
textbody = part.get_payload(decode=True).decode(get_charset(part))
except UnicodeDecodeError:
textbody = part.get_payload(decode=True).decode('windows-1252')
# This part is probably in windows-1252 encoding
try:
textbody = part.get_payload(decode=True).decode('windows-1252')
except UnicodeDecodeError:
# Ok, we really have no clue how to decode this, we'll just skip it...
continue
except LookupError:
pass
elif part.get_content_type() == "text/html" or part.get_content_type == "text/xhtml+xml" or part.get_content_type == "application/xhtml+xml":
@ -122,7 +127,12 @@ for email_file in file_list:
try:
htmlbody = part.get_payload(decode=True).decode(get_charset(part))
except UnicodeDecodeError:
htmlbody = part.get_payload(decode=True).decode('windows-1252')
# This part is probably in windows-1252 encoding
try:
htmlbody = part.get_payload(decode=True).decode('windows-1252')
except UnicodeDecodeError:
# Ok, we really have no clue how to decode this, we'll just skip it...
continue
except LookupError:
pass
else: