Jednoduchý FB group Pyonieri -> @naPyVo bot splácaný za hodinu na koleně

pyvo.py

#!/usr/bin/python
# -*- coding: utf-8 -*-


import imaplib
import re
import base64
import quopri
import urllib
import redis
import tweepy


# redis
print 'Redis...'
redis_server = redis.Redis('localhost')


# twitter
print 'Twitter...'
consumer_key='j8LLDtko8lFxsHmjJi8w'
consumer_secret='PyzBJyiO2gmM8SK9aFkD0lm3OMHrYQAGepSAYWCZE'
access_token='293644462-tW11axCa3khtEESUH9DgySq5WJqnWZfUgJKEb4KZ'
access_token_secret='JFh0FxKr0ZrlDAnuKFqE7atVTRuMJt9Om65xRyVqA'

auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)


# login into my mailbox using username and password
print 'Gmail...'
mail = imaplib.IMAP4_SSL('imap.gmail.com')
mail.login('[email protected]', base64.b64decode('amUtbGkgbmFzZSBjaXNsbyAzOA=='))


# get all emails in selected label '✉ MAILING LISTS/✩ Pyonýři'
mail.select('&Jwk- MAILING LISTS/&Jyk- Pyon&AP0BWQ-i')
result, data = mail.search(None, 'ALL')

ids = data[0].split() # ids is a space separated string


# iterate over emails in order from the oldest to the newest
def generate_links(ids, redis_server):
    for email_id in ids:
        # check if present in redis
        if not redis_server.sadd('pyvo:tweeted', email_id):
            continue
    
        # get raw email data
        result, data = mail.fetch(email_id, '(RFC822)') # fetch the email body (RFC822) for the given ID
        raw_email = data[0][1] # here's the body, which is raw text of the whole email (including headers and alternate payloads)
        
        
        # get only plaintext part of the email
        plaintext_parts = [part for part in re.split(r'\n\-\-', raw_email) if re.search(r'Content\-Type: text\/plain', part)]
        if not plaintext_parts:
            continue
        plaintext = plaintext_parts[0]
        
        
        # separate headers and content
        headers, content = re.split(r'\r?\n\r?\n', plaintext, 1)
        encoding = re.search(r'Content\-Transfer\-Encoding: ([^\n]+)', headers, flags=re.I).group(1).strip()
        charset = re.search(r'charset=["\']?([\w\-_]+)', headers, flags=re.I).group(1).strip()
        

        # decode content    
        if encoding == 'quoted-printable':
            content = unicode(quopri.decodestring(content), charset).strip()
        else:
            continue
        
        
        # find author
        try:
            author = re.search(r'^([\w ]+) posted in Pyonieri', content, flags=re.I|re.U).group(1).strip()
        except AttributeError:
            continue
        
        
        # find link
        try:
            link = re.search(r'http://www\.facebook\.com/l/[^/]+/([^\s<,]+)', content).group(1).strip()
            if link.startswith('https'):
                link = urllib.unquote(link)
            else:
                link = 'http://' + link
        except AttributeError:
            continue


        yield (email_id, author, link)
        

# process links
print 'Processing...'
try:
    email_id, author, link = next(generate_links(ids, redis_server))
    try:
        print 'Tweeting... (%s: %s)' % (author, link)
        api.update_status(u'%s na http://on.fb.me/pyoneers sdílí něco zajímavého: %s' % (author, link))
        
    except tweepy.error.TweepError:
        print 'Tweeting failed.'
        redis_server.srem('pyvo:tweeted', email_id)
            
except StopIteration:
    print 'No more links available now.'