Code, der jahrelang für https://twitter.com/hstbot lief, zur Ausführung per crontab. Verwendet python-twitter 3.3.1. WTFPL

efa.py

import requests
import twitter
#import sys
from datetime import datetime
import logging
import xml.etree.ElementTree as ET

logging.basicConfig(filename='efa.log',level=logging.INFO)
tweet_length = 280
hashtags = "#VRR"
tweet_length -= len(hashtags)

knownfile = 'known-efa.txt'

payload = {'language':'de',
           'itdLPxx_transpCompany':'vrr',
           'filterPublicationStatus':'current',
           'filterOMC_PlaceID':'5914000:29',
#           'itdLPxx_selOperator':'HST', nicht gut wegen 00 Sonstige
           'filterProviderCode':'HST',
           'AIXMLReduction':['removeStops','removeLines','removeValidity','removePublication','removeCreationTime','removeExpirationTime','removeSourceSystem']}
r = requests.get('http://openservice-test.vrr.de/static02/XML_ADDINFO_REQUEST',payload)
root = ET.fromstring(r.content)

#tree = ET.parse(sys.argv[1])
#root = tree.getroot()

with open(knownfile,encoding='utf-8') as file:
    known = file.read().splitlines()

api = twitter.Api(consumer_key='X',
                  consumer_secret='X',
                  access_token_key='X',
                  access_token_secret='X')
#print(api.VerifyCredentials())

ci = 0
titles = []
for itdATI in root.iter('itdAdditionalTravelInformation'):
    ci += 1
    infoID = itdATI.attrib['infoID']
    infolinktext = itdATI[0].find('infoLinkText').text
    # war vorher mit infoID statt text

    titles.append(infolinktext)
    if infolinktext in known:
        continue

    timespan = "("+itdATI[0][0][-1].find('value').text+")"
    #link = itdATI[0].find('infoLinkURL').text   # URL mit IP schlecht bei Twitter
    link = "https://efa.vrr.de/vrr/XSLT_ADDINFO_REQUEST?itdLPxx_addInfoDetailView="+infoID

    rest_length = tweet_length - len(timespan) - len(link)

    smstext = ""

    if itdATI[0].find('infoText').find('outputClientText').find('smsText') is not None:
        smstext = itdATI[0].find('infoText').find('outputClientText')[0].text
    
    if len(infolinktext) <= rest_length:
        outputtext = infolinktext
    elif len(smstext) <= rest_length and len(smstext) != 0:
        outputtext = smstext
    else:
        outputtext = infolinktext[0:(rest_length-3)]+"..."

    rest_length -= len(outputtext)

    tweet = "#"+outputtext+" "+timespan+" "+link+" "+hashtags # Hashtag am Anfang weil der Ortsname dort ist

    try:
        status = api.PostUpdate(tweet)
    except Exception as e:
        logging.warning(str(datetime.now())+str(e))

    #print(rest_length,tweet)

    logging.info(str(datetime.now())+" "+infoID+" "+str(rest_length)+"\n\n"+tweet+"\n\n")

with open(knownfile, 'w', encoding='utf-8') as file:
    if ci > 0:
        file.write('\n'.join(titles)+'\n')
    else:
        file.write('n\n')

news.py

import requests
import twitter
import logging
#import sys
from datetime import datetime

logging.basicConfig(filename='news.log',level=logging.INFO)
tweet_length = 280
hashtags = "#Hagen #VRR"
tweet_length -= len(hashtags)

knownfile = 'known-news.txt'

r = requests.get('https://www.strassenbahn-hagen.de/?type=1008')
root = r.json()

#tree = ET.parse(sys.argv[1])
#root = tree.getroot()

with open(knownfile) as file:
    known = file.read().splitlines()
nowknown = []

api = twitter.Api(consumer_key='X',
                  consumer_secret='X',
                  access_token_key='X',
                  access_token_secret='X')
#print(api.VerifyCredentials())

for item in (root['items'] or []):
    guid = str(item['id'])
    nowknown.append(guid)

    if guid in known:
        continue
    #else:
    #    with open(knownfile, 'a') as file:
    #        file.write(guid+'\n')

    link = item['url']
    title = item['title'].strip() + ": "

    rest_length = tweet_length - len(title) - (bool(link)*23) - 2

    item['text'] = item['text'].strip()
    text_part = item['text'][:rest_length]
    if len(text_part) < len(item['text']):
        text_part = text_part[:-2] + "…"
    title += text_part

    tweet = title+" "+link+" "+hashtags

    try:
        status = api.PostUpdate(tweet)
        # print(tweet + "\n" + str(len(tweet)))
    except Exception as e:
        logging.warning(str(datetime.now())+str(e))

    logging.info(str(datetime.now())+" "+guid+" "+str(rest_length)+"\n\n"+tweet+"\n\n")

# neu:
with open(knownfile, 'w', encoding='utf-8') as file:
    file.write('\n'.join(nowknown)+'\n')

ticker.py

import requests
import twitter
#import sys
from datetime import datetime
import logging
from bs4 import BeautifulSoup
import xml.etree.ElementTree as ET

logging.basicConfig(filename='ticker.log',level=logging.INFO)
tweet_length = 280
hashtags = "#Hagen #VRR"
orte = ["MVG","VER","Dortmund","Schwerte","Iserlohn","Wiblingwerde","Breckerfeld","Ennepetal","Gevelsberg","Wetter","Herdecke","Kierspe"]
website = "http://www.strassenbahn-hagen.de"
tweet_length -= (len(website)+ 1 + len(hashtags))

knownfile = 'known-ticker.txt'

r = requests.get('http://www.strassenbahn-hagen.de/ticker_rss.xml')
root = ET.fromstring(r.content)

#tree = ET.parse(sys.argv[1])
#root = tree.getroot()

with open(knownfile,encoding='utf-8') as file:
    known = file.read().splitlines()

api = twitter.Api(consumer_key='X',
                  consumer_secret='X',
                  access_token_key='X',
                  access_token_secret='X')
#print(api.VerifyCredentials())

ci = 0
orig_content = []
tweets = []
for item in root.iter('item'):
    ci += 1
    content = " ".join(item[-1].text.split())
    orig_content.append(content)
    if content in known:
        continue
    title = ""
    if item.find('title').text is not None:
        title = BeautifulSoup(" ".join(item.find('title').text.split()).strip(), "lxml").text.strip()

    teile = content.split('<br>')
    map(str.strip, teile)

    ausgabe = ""
    ausgegeben = False
    bepunktet = False
    komma = ""

    for teil in teile:
        for unterteil in teil.split(". "): # potenzielles todo: anderes als punkt, hm
            if unterteil.find("keine Einschränkungen") < 0 and unterteil not in [""," ","\n"] and not (unterteil[0].lower() == "l" and ":" in [unterteil[-1],unterteil[-2]]):
                if teil.find(". ") > -1:
                    if bepunktet == False:
                        ausgabe += komma+unterteil.strip()
                        if ausgabe[-1] not in [".","!",";"]:
                            ausgabe += "."
                        ausgabe += " "
                        ausgegeben = True
                        bepunktet = True
                    else:
                        ausgabe += unterteil.strip()
                        if ausgabe[-1] not in [".","!",";"]:
                            ausgabe += "."
                        ausgabe += " "
                        ausgegeben = True
                        bepunktet = True
                else:
                    if bepunktet:
                        ausgabe += unterteil.strip()
                        ausgegeben = True
                        bepunktet = False
                    else:
                        ausgabe += komma+unterteil.strip()
                        ausgegeben = True
            if ausgegeben:
                if ausgabe[-1] in [".",",",")","!",";"]:
                    komma = " "
                else:
                    komma = ", "

    for ort in orte:
        ausgabe = ausgabe.replace(ort,"#"+ort)
    # todo: abgeschnittene hashtags soll es nicht geben
    # todo: kein #Dortmunder Str. etc.

    tweet = title+"\n"+ausgabe.strip()
    if tweet.count(" Linie ") > 3:
        tweet = tweet.replace(" Linie ","\nLinie ")

    tweetsplit = []
    if len(tweet) <= tweet_length:
        tweet += (" " + website + " " + hashtags)
        tweets.append([tweet])
        print(tweet)
    else:
        r = range(0, len(tweet), tweet_length-4)
        # todo: text pro tweet, insbesondere alle nach dem ersten, maximieren! ### 3 zu 4 geaendert
        for ri in r:
            if ri == r[-1]:
                tweetsplit.append("…"+tweet[ri:ri+tweet_length-4] + " " + website)
            elif ri == r[0]:
                tweetsplit.append(tweet[ri:ri+tweet_length-4] + "… " + website + " " + hashtags)
            else:
                tweetsplit.append("…"+tweet[ri:ri+tweet_length-4] + "… " + website)
            print(tweetsplit[-1])
        tweets.append(tweetsplit)

for x in tweets:
    ti = 0
    lastid = 0
    if len(x) == 1:
        try:
            status = api.PostUpdate(x[0])
        except Exception as e:
            logging.warning(str(datetime.now())+" "+str(e)+"\nContent:\n"+content+"\n")
        logging.info(str(datetime.now())+"\n\n"+x[0]+"\n\n")
    elif len(x) > 1:
        for tw in x:
            try:
                if ti == 0:
                    status = api.PostUpdate(tw)
                    lastid = status.id
                else:
                    status = api.PostUpdate(tw, in_reply_to_status_id=lastid)
                    lastid = status.id
            except Exception as e:
                logging.warning(str(datetime.now())+" x["+str(ti)+"] "+str(e)+"\nContent:\n"+content+"\n")
            ti += 1
        logging.info(str(datetime.now())+"\n\n"+"\n".join(x)+"\n\n")

with open(knownfile, 'w', encoding='utf-8') as file:
    if ci > 0:
        file.write('\n'.join(orig_content)+'\n')
    else:
        file.write('n\n')

wtfpl

Copyright © 2017～2020 Kevin Arutyunyan
This work is free. You can redistribute it and/or modify it under the
terms of the Do What The Fuck You Want To Public License, Version 2,
as published by Sam Hocevar. See http://www.wtfpl.net/ for more details.

            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
                    Version 2, December 2004

 Copyright (C) 2004 Sam Hocevar <[email protected]>

 Everyone is permitted to copy and distribute verbatim or modified
 copies of this license document, and changing it is allowed as long
 as the name is changed.

            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION

  0. You just DO WHAT THE FUCK YOU WANT TO.