parser.py - master - EgorG23Bey/email_client

parser.py
143 строки3 KB
EgorG23
update impt
12 июл 2026, 23:51
12 июл 2026, 23:510663458
import re
from email import message_from_bytes
from email.header import decode_header
from bs4 import BeautifulSoup

from models import EmailMessage


def decode_mime_header(header):
    """
    Декодирует MIME-заголовки (например, тему письма).
    """

    if not header:
        return ""

    decoded = decode_header(header)

    result = ""

    for text, encoding in decoded:

        if isinstance(text, bytes):
            result += text.decode(encoding or "utf-8", errors="ignore")
        else:
            result += text

    return result


def extract_links(text: str) -> list[str]:
    """
    Извлекает все URL из текста.
    """

    pattern = r"https?://[^\s\"'>]+"

    return re.findall(pattern, text)


def html_to_text(html: str) -> str:
    """
    Превращает HTML в обычный текст.
    """

    soup = BeautifulSoup(html, "lxml")

    return soup.get_text(separator="\n", strip=True)


def parse_email(raw_email: bytes) -> EmailMessage:
    """
    Парсит письмо IMAP -> EmailMessage
    """

    msg = message_from_bytes(raw_email)

    sender = decode_mime_header(msg.get("From"))

    receiver = decode_mime_header(msg.get("To"))

    subject = decode_mime_header(msg.get("Subject"))

    date = decode_mime_header(msg.get("Date"))

    text = ""

    html = ""

    if msg.is_multipart():

        for part in msg.walk():

            content_type = part.get_content_type()

            disposition = str(part.get("Content-Disposition"))

            if "attachment" in disposition:
                continue

            try:

                payload = part.get_payload(decode=True)

                if payload is None:
                    continue

                charset = part.get_content_charset() or "utf-8"

                content = payload.decode(charset, errors="ignore")

            except Exception:
                continue

            if content_type == "text/plain":

                text += content

            elif content_type == "text/html":

                html += content

    else:

        payload = msg.get_payload(decode=True)

        charset = msg.get_content_charset() or "utf-8"

        content = payload.decode(charset, errors="ignore")

        if msg.get_content_type() == "text/html":

            html = content

        else:

            text = content

    if not text and html:

        text = html_to_text(html)

    links = extract_links(text)

    if html:

        soup = BeautifulSoup(html, "lxml")

        for a in soup.find_all("a", href=True):

            links.append(a["href"])

    links = list(set(links))

    return EmailMessage(
        sender=sender,
        receiver=receiver,
        subject=subject,
        text=text,
        html=html,
        links=links,
        date=date
    )