Пример использования python-processor для преобразования Email в RSS фид.

do-rss-feed-for-org-mode.py

#!env/bin/python3
import re
import logging
import os

from html2text import html2text
from processor import run_pipeline, sources, outputs
from twiggy_goodies.setup import setup_logging

# Что тут есть?
# один только процессинг индекса и перекладывание тасков в org-mode
# чтобы работало, надо установить hy из репозитория:
# git+git://github.com/hylang/hy.git@5af86d691d9caad52bff83b681e8891333a09889
# [email protected]:six8/pytailer.git
# tailer
# jsail

def markdown2org(text):
    def remove_newlines(text):
        return text.replace('\n', '')

    def repl(m):
        url = remove_newlines(m.group('url'))
        text = remove_newlines(m.group('text'))
        if text:
            pattern = '[[{url}][{text}]]'
        else:
            pattern = '[[{url}]]'
        return pattern.format(
            url=url, text=text)

    text = re.sub(r'!?\[(?P<text>.*?)\]\((?P<url>.*?)\)',
                  repl,
                  text,
                  flags=re.DOTALL)
    return text


def remove_unnecessary_text(text):
    text = re.sub(r'Download the official Twitter app.*',
                  '', text)
    text = re.sub(r'Sent from my.*', '', text)
    text = re.sub(r'^\W+$', r'', text, flags=re.MULTILINE)
    text = re.sub(r'\n+', r'\n', text)
    return text


def swap_twitter_subject(subject, body):
    """If subject starts from 'Tweet from...'
    then we need to get first meaning line from the body."""

    if subject.startswith('Tweet from'):
        lines = body.split('\n')
        for idx, line in enumerate(lines):
            if re.match(r'.*, ?\d{2}:\d{2}]]', line) is not None:
                try:
                    subject = lines[idx + 1]
                except IndexError:
                    pass
                break
    return subject, body


def mail_to_rss(item):
    headers = item['headers']
    html_body = item.get('html-body')
    if html_body:
        body = html2text(html_body)
    else:
        body = item.get('plain-body')

    body = markdown2org(body)
    body = remove_unnecessary_text(body)
    subject, body = swap_twitter_subject(
        headers.get('subject', 'Untitled'), body)

    return dict(title=subject,
                date=headers['date'],
                body=body)

def add_TODO_to_title(item):
    return dict(item, title=u'TODO ' + item['title'])


for_any_message = lambda msg: True

NAME = 'rss-feed-for-org-mode'
setup_logging('logs/' + NAME + '.log')
os.environ['PROCESSOR_DB'] = NAME + '.db'

try:
    logging.info('Starting')

    run_pipeline(
        sources.imap("imap.gmail.com",
                     "svet*",
                     "******",
                     "Autoprocessing/OrgModeInbox"),
        [mail_to_rss, add_TODO_to_title, outputs.rss('rss-feed.xml',
                                                     limit=100)])

    logging.info('Done')
except:
    logging.exception('Unhandled exception')