def get_snippets_from_person(me, top_emailer):
all_snippets_from_person = []
for filename in os.listdir(args.emails_path):
e1 = email_lib.read_email(args.emails_path + filename)
if is_email_valid(e1, me, top_emailer):
for snippet in get_snippets(e1, top_emailer):
snippet.filename = filename
all_snippets_from_person.append(snippet)
# Randomly select N snippets
random.shuffle(all_snippets_from_person)
if args.num_snippets <= len(all_snippets_from_person):
some_snippets = all_snippets_from_person[0:args.num_snippets]
else:
print "Not enough snippets."
some_snippets = all_snippets_from_person
return some_snippets
def read_all_files(path):
emails = []
for filename in os.listdir(path):
emails.append(email_lib.read_email(path + filename))
return emails
from collections import Counter
parser = argparse.ArgumentParser(description='Find the top N people that ' + \
'you email most frequently.')
# It's important to have your email address because you want to add a name to
# the "top emailers" if they directly email with you (e.g. no mailing lists).
parser.add_argument('your_email', help='your email address')
parser.add_argument('-p', '--emails_path',
default='processed_emails/',
help='the path to the directory with all the emails')
parser.add_argument('-n', '--num_people', type=int, default=20,
help='the number of people to get')
args = parser.parse_args()
top_people = Counter()
for filename in os.listdir(args.emails_path):
e1 = email_lib.read_email(args.emails_path + filename)
if args.your_email == e1.from_address:
for to_address in e1.to_addresses:
top_people[to_address] += 1
# if you're in the from and the to, don't add yourself twice
elif args.your_email in e1.to_addresses:
top_people[e1.from_address] += 1
for person, count in top_people.most_common(args.num_people):
print person + ', ' + str(count)
