mastotuit/mastotuit.py

import os
import feedparser
from bs4 import BeautifulSoup
from mastodon import Mastodon
import psycopg2
import sys
import time
import requests
import shutil
import tweepy
from tweepy import TweepError
import logging
import pdb

logger = logging.getLogger()

def write_image(image_url):

    if not os.path.exists('images'):
        os.makedirs('images')
    filename = image_url.split("/") [-1]
    r = requests.get(image_url, stream = True)
    r.raw.decode_content = True
    with open('images/' + filename, 'wb') as f:
        shutil.copyfileobj(r.raw, f)

    return filename

def create_api():
    
    auth = tweepy.OAuthHandler(api_key, api_key_secret)
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth, wait_on_rate_limit=True, 
        wait_on_rate_limit_notify=True)
    try:
        api.verify_credentials()
        logged_in = True
    except Exception as e:
        logger.error("Error creating API", exc_info=True)
        raise e
    logger.info("API created")
    return (api, logged_in)

def mastodon():

    # Load secrets from secrets file
    secrets_filepath = "secrets/secrets.txt"
    uc_client_id = get_parameter("uc_client_id",     secrets_filepath)
    uc_client_secret = get_parameter("uc_client_secret", secrets_filepath)
    uc_access_token = get_parameter("uc_access_token",  secrets_filepath)

    # Load configuration from config file
    config_filepath = "config/config.txt"
    mastodon_hostname = get_parameter("mastodon_hostname", config_filepath)

    # Initialise Mastodon API
    mastodon = Mastodon(
        client_id=uc_client_id,
        client_secret=uc_client_secret,
        access_token=uc_access_token,
        api_base_url='https://' + mastodon_hostname,
    )

    # Initialise access headers
    headers = {'Authorization': 'Bearer %s'%uc_access_token}

    return (mastodon, mastodon_hostname)

def db_config():

    # Load db configuration from config file
    db_config_filepath = "config/db_config.txt"
    feeds_db =  get_parameter("feeds_db", db_config_filepath)
    feeds_db_user =  get_parameter("feeds_db_user", db_config_filepath)
    feeds_url =  get_parameter("feeds_url", db_config_filepath)
    
    return (feeds_db, feeds_db_user, feeds_url)

def twitter_config():
    
    twitter_config_filepath = "config/keys_config.txt"
    api_key = get_parameter("api_key", twitter_config_filepath)
    api_key_secret = get_parameter("api_key_secret", twitter_config_filepath)
    access_token = get_parameter("access_token", twitter_config_filepath)
    access_token_secret = get_parameter("access_token_secret", twitter_config_filepath)

    return(api_key, api_key_secret, access_token, access_token_secret)

# Returns the parameter from the specified file
def get_parameter( parameter, file_path ):
    # Check if secrets file exists
    if not os.path.isfile(file_path):
        print("File %s not found, exiting."%file_path)
        sys.exit(0)

    # Find parameter in file
    with open( file_path ) as f:
        for line in f:
            if line.startswith( parameter ):
                return line.replace(parameter + ":", "").strip()

    # Cannot find parameter, exit
    print(file_path + "  Missing parameter %s "%parameter)
    sys.exit(0)

###############################################################################
# main

if __name__ == '__main__':

    #######################################################################
    #mastodon, mastodon_hostname = mastodon()
    
    feeds_db, feeds_db_user, feeds_url = db_config()

    api_key, api_key_secret, access_token, access_token_secret = twitter_config()
    
    logged_in = False

    try:

        newsfeeds = feedparser.parse(feeds_url)

    except:

        print(newsfeeds.status)
        sys.exit(0)

    for entry in newsfeeds.entries:

        publish = False
        with_images = False

        title = entry['summary']
        id = entry['id']
        link = entry['link']

        if len(entry.links) >= 2:

            with_images = True
            images_list = []
            images = len(entry.links) - 1

            i = 0
            while i < images:

                image_url = entry.links[i+1].href
                image_filename = write_image(image_url)
                images_list.append(image_filename)
                i += 1

        ###################################################################
        # check database if feed is already published

        try:

            conn = None
            
            conn = psycopg2.connect(database = feeds_db, user = feeds_db_user, password = "", host = "/var/run/postgresql", port = "5432")

            cur = conn.cursor()

            cur.execute('select link from feeds where link=(%s)', (link,))

            row = cur.fetchone()
            if row == None:
                publish = True

            cur.close()

        except (Exception, psycopg2.DatabaseError) as error:

            print(error)

        finally:

            if conn is not None:

                conn.close()

        ###########################################################

        if publish:

            soup = BeautifulSoup(title, 'html.parser')
            
            toot_text = soup.get_text()
            sub_str = 'http'
            find_link = toot_text.find(sub_str)
            if find_link != -1:
                toot_text = toot_text[:toot_text.index(sub_str)]

            links_lst = ''
            for links in soup.find_all('a'):
                links_lst += links.get('href') + ' '

            toot_text = f'{toot_text} {links_lst}'

            print("Tooting...")
            print(toot_text)

            if not logged_in:

                api, logged_in = create_api()
            
            if len(toot_text) < 280:

                try:

                    if with_images:

                        images_id_lst = []

                        i = 0
                        while i < len(images_list):

                            media = api.media_upload('images/' + images_list[i])
                            images_id_lst.append(media.media_id)
                            i += 1

                        api.update_status(status=toot_text, media_ids=images_id_lst)

                    else:

                        api.update_status(toot_text)

                except TweepError as err:
                    
                    print('\n')
                    sys.exit(err)
            
            else:

                if with_images:

                    toot_text1 = toot_text[:250].rsplit(' ', 1)[0] + ' (1/2)'
                    toot_text2 = toot_text[int(len(toot_text1)-6):] + ' (2/2)'

                else:

                    toot_text1 = toot_text[:275].rsplit(' ', 1)[0] + ' (1/2)'
                    toot_text2 = toot_text[int(len(toot_text1)-6):] + ' (2/2)'

                try:

                    if with_images:

                        images_id_lst = []

                        i = 0
                        while i < len(images_list):

                            media = api.media_upload('images/' + images_list[i])
                            images_id_lst.append(media.media_id)
                            i += 1

                        first_tweet = api.update_status(status=toot_text1)
                        api.update_status(status=toot_text2, in_reply_to_status_id=first_tweet.id, media_ids=images_id_lst)

                    else:

                        first_tweet = api.update_status(toot_text1)
                        api.update_status(toot_text2, in_reply_to_status_id=first_tweet.id)
                
                except TweepError as err:
                    
                    print('\n')
                    sys.exit(err)

            time.sleep(2)

            #########################################################

            insert_line = 'INSERT INTO feeds(link) VALUES (%s)'

            conn = None

            try:

                conn = psycopg2.connect(database = feeds_db, user = feeds_db_user, password = "", host = "/var/run/postgresql", port = "5432")

                cur = conn.cursor()

                cur.execute(insert_line, (link,))

                conn.commit()

                cur.close()

            except (Exception, psycopg2.DatabaseError) as error:

                print(error)

            finally:

                if conn is not None:

                    conn.close()
        else:

            print("Any new feeds")
            sys.exit(0)