コード例 #1
0
ファイル: receiveEmail3.py プロジェクト: suparngp/letswikit
def getEmail():
    user = "******"
    pwd = "wikitrocks"

    # connecting to the gmail imap server
    m = imaplib.IMAP4_SSL("imap.gmail.com")
    m.login(user, pwd)
    # m.select("[Gmail]/INBOX") # here you a can choose a mail box like INBOX instead
    # m.select("[Gmail]/All Mail")
    m.select("inbox")
    # use m.list() to get all the mailboxes

    resp, items = m.search(None,
                           "UNSEEN")  # you could filter using the IMAP rules here (check http://www.example-code.com/csharp/imap-search-critera.asp)
    items = items[0].split()

    if len(items) == 0:
        return

    # Get last email
    text = ""
    resp, data = m.fetch(items[-1],
                         "(RFC822)")  # fetching the mail, "`(RFC822)`" means "get the whole stuff", but you can ask for headers only, etc
    raw_email = data[0][1]  # getting the mail content
    # mail = email.message_from_string(email_body) # parsing the mail content to get a mail object

    m.close()
    m.logout()
    text = raw_email
    # with io.open("file", "+w") as file:
    #     file.write(email.message_from_bytes(raw_email))
    #     return
    #
    # Parse email
    parser = MailParser(text)
    results = parser.parse_thread()
    question = results.question

    print(results.json())

    # Run NLP
    keywords = nlp.keywords_from_text(question.content)
    messages = nlp.compute_tf_idf(question, results.messages)
    results.messages = messages
    es.store_thread(results)
    print("All saved");
コード例 #2
0
ファイル: runner.py プロジェクト: suparngp/letswikit
def result_email(file_name):
    with io.open(file_name) as file:
        text = file.read()

    parser = MailParser(text)
    results = parser.parse_thread()
    question = results.question
    keywords = nlp.keywords_from_text(question.content)
    messages = nlp.compute_tf_idf(question, results.messages)
    results.messages = messages
    # print(results)

    # es.store_articles([question] + messages
    es.store_thread(results)

    for m in messages:
        print(jsonpickle.encode(m))
コード例 #3
0
ファイル: mail_parser.py プロジェクト: suparngp/letswikit
    def parse_messages(self, message):
        emails = [e.strip() for e in re.split(r'On.+wrote:|From:.+', message) if
                  "Begin forwarded message:" not in e.strip() and "Forwarded message" not in e]
        froms = re.findall(r'On.+wrote:|From:.+', message)

        froms = froms
        messages = []
        for i in range(0, len(emails)):
            message = Message()

            meta = self.parse_meta_v3(froms[i] + "\n" + emails[i])


            # print(message.content)
            # print("+++++++++++++++++++++++++++++++++")
            if meta is not None:
                message.sender_name = meta["name"]
                message.sender_address = meta["email"]
                message.time = meta["time"]
            messages.append(message)

            lines = emails[i].splitlines()
            email = []
            for line in lines:
                if line.strip() == "":
                    continue
                if line.startswith(('From', 'To', 'Sent', 'Date', 'Subject', 'Cc', 'Received')):
                    # print(line)
                    email = []
                # elif line.strip().lower() == message.sender_name.lower() or line.strip().lower() == message.sender_name.split()[0].lower():
                elif line.strip().lower() in message.sender_name.lower():
                    email.append(line)
                    break
                else:
                    email.append(line)

            # message.content = re.sub(r'(From|To|Sent|Date|Subject|Cc|Received):.+', '', emails[i], re.MULTILINE).strip()
            message.content = "\n".join(email)
            message.keywords = nlp.keywords_from_text(message.content)
        messages.reverse()
        return messages