archive/andrewferrier_email2pdf
1
0
Fork 1
mirror of https://github.com/andrewferrier/email2pdf.git synced 2025-03-18 14:03:00 +00:00
Code Issues Projects Releases Wiki Activity

Search for HTML first, then plain text. (closes ).

Browse source
This commit is contained in:
Andrew Ferrier 2014-09-20 12:51:54 +01:00
parent 1514749cdd
commit b677462103
1 changed files with 10 additions and 4 deletions

14
email2pdf
View file

@ -40,18 +40,24 @@ def main(argv):
data = inputHandle.read()
myEmail = email.message_from_string(data)
payload = find_html_depth_first(myEmail)
payload = find_depth_first(myEmail, "text/html")
if payload == False:
payload = find_depth_first(myEmail, "text/plain")
if payload == False:
print("ERROR: Cannot find an appropriate payload in email.", file=sys.stderr)
else:
payload = "<html><body><pre>\n" + payload + "\n</pre></body></html>"
p = Popen(['wkhtmltopdf', '-q', '--load-error-handling', 'ignore', '--load-media-error-handling', 'ignore', '-', outputFile], stdin=PIPE)
output = p.communicate(input = payload)
def find_html_depth_first(message):
def find_depth_first(message, content_type):
if message.is_multipart():
for part in message.get_payload():
value = find_html_depth_first(part)
value = find_depth_first(part, content_type)
if value != False:
return value
elif message.get_content_type() == 'text/html':
elif message.get_content_type() == content_type:
return message.get_payload(decode = True)
else:
return False