| 1 |
import os |
| 2 |
import sys |
| 3 |
import tempfile |
| 4 |
import mimetypes |
| 5 |
import webbrowser |
| 6 |
|
| 7 |
# Import the email modules we'll need |
| 8 |
from email import policy |
| 9 |
from email.parser import BytesParser |
| 10 |
|
| 11 |
|
| 12 |
def magic_html_parser(html_text, partfiles): |
| 13 |
"""Return safety-sanitized html linked to partfiles. |
| 14 |
|
| 15 |
Rewrite the href="cid:...." attributes to point to the filenames in partfiles. |
| 16 |
Though not trivial, this should be possible using html.parser. |
| 17 |
""" |
| 18 |
raise NotImplementedError("Add the magic needed") |
| 19 |
|
| 20 |
|
| 21 |
# In a real program you'd get the filename from the arguments. |
| 22 |
with open('outgoing.msg', 'rb') as fp: |
| 23 |
msg = BytesParser(policy=policy.default).parse(fp) |
| 24 |
|
| 25 |
# Now the header items can be accessed as a dictionary, and any non-ASCII will |
| 26 |
# be converted to unicode: |
| 27 |
print('To:', msg['to']) |
| 28 |
print('From:', msg['from']) |
| 29 |
print('Subject:', msg['subject']) |
| 30 |
|
| 31 |
# If we want to print a preview of the message content, we can extract whatever |
| 32 |
# the least formatted payload is and print the first three lines. Of course, |
| 33 |
# if the message has no plain text part printing the first three lines of html |
| 34 |
# is probably useless, but this is just a conceptual example. |
| 35 |
simplest = msg.get_body(preferencelist=('plain', 'html')) |
| 36 |
print() |
| 37 |
print(''.join(simplest.get_content().splitlines(keepends=True)[:3])) |
| 38 |
|
| 39 |
ans = input("View full message?") |
| 40 |
if ans.lower()[0] == 'n': |
| 41 |
sys.exit() |
| 42 |
|
| 43 |
# We can extract the richest alternative in order to display it: |
| 44 |
richest = msg.get_body() |
| 45 |
partfiles = {} |
| 46 |
if richest['content-type'].maintype == 'text': |
| 47 |
if richest['content-type'].subtype == 'plain': |
| 48 |
for line in richest.get_content().splitlines(): |
| 49 |
print(line) |
| 50 |
sys.exit() |
| 51 |
elif richest['content-type'].subtype == 'html': |
| 52 |
body = richest |
| 53 |
else: |
| 54 |
print("Don't know how to display {}".format(richest.get_content_type())) |
| 55 |
sys.exit() |
| 56 |
elif richest['content-type'].content_type == 'multipart/related': |
| 57 |
body = richest.get_body(preferencelist=('html')) |
| 58 |
for part in richest.iter_attachments(): |
| 59 |
fn = part.get_filename() |
| 60 |
if fn: |
| 61 |
extension = os.path.splitext(part.get_filename())[1] |
| 62 |
else: |
| 63 |
extension = mimetypes.guess_extension(part.get_content_type()) |
| 64 |
with tempfile.NamedTemporaryFile(suffix=extension, delete=False) as f: |
| 65 |
f.write(part.get_content()) |
| 66 |
# again strip the <> to go from email form of cid to html form. |
| 67 |
partfiles[part['content-id'][1:-1]] = f.name |
| 68 |
else: |
| 69 |
print("Don't know how to display {}".format(richest.get_content_type())) |
| 70 |
sys.exit() |
| 71 |
with tempfile.NamedTemporaryFile(mode='w', delete=False) as f: |
| 72 |
f.write(magic_html_parser(body.get_content(), partfiles)) |
| 73 |
webbrowser.open(f.name) |
| 74 |
os.remove(f.name) |
| 75 |
for fn in partfiles.values(): |
| 76 |
os.remove(fn) |
| 77 |
|
| 78 |
# Of course, there are lots of email messages that could break this simple |
| 79 |
# minded program, but it will handle the most common ones. |