2017-09-20 23:25:57 +02:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
|
# -*- coding: utf-8 -*-
|
2017-09-21 00:50:53 +02:00
|
|
|
import html
|
2017-09-20 23:25:57 +02:00
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from bot import admins
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def can_use_bot(update):
|
|
|
|
|
"""Returns True if user is an admin"""
|
|
|
|
|
if update.message.from_user.id in admins:
|
|
|
|
|
return True
|
|
|
|
|
else:
|
|
|
|
|
return False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_new_entries(entries, last_entry):
|
|
|
|
|
"""Returns all new entries from an entries dict up to the last new article"""
|
|
|
|
|
new_entries = []
|
|
|
|
|
for entry in entries:
|
|
|
|
|
if 'id' in entry:
|
|
|
|
|
if entry['id'] == last_entry:
|
|
|
|
|
return new_entries
|
|
|
|
|
else:
|
|
|
|
|
new_entries.append(entry)
|
|
|
|
|
else:
|
|
|
|
|
if entry['link'] == last_entry:
|
|
|
|
|
return new_entries
|
|
|
|
|
else:
|
|
|
|
|
new_entries.append(entry)
|
|
|
|
|
return new_entries
|
|
|
|
|
|
|
|
|
|
|
2017-09-21 00:50:53 +02:00
|
|
|
def remove_html_tags(rawhtml):
|
2017-09-20 23:25:57 +02:00
|
|
|
"""Removes HTML tags"""
|
|
|
|
|
cleanr = re.compile('<.*?>')
|
2017-09-21 00:50:53 +02:00
|
|
|
cleantext = re.sub(cleanr, '', rawhtml)
|
2017-09-20 23:25:57 +02:00
|
|
|
return cleantext
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def clean_rss(content):
|
|
|
|
|
"""Cleans content"""
|
2017-09-21 00:13:40 +02:00
|
|
|
content = content.replace('\n', ' ')
|
2018-02-25 23:19:12 +01:00
|
|
|
content = content.replace('←', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('[…]', '')
|
2018-02-25 23:19:12 +01:00
|
|
|
content = content.replace('[...]', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('[bilder]', '')
|
2017-09-20 23:57:58 +02:00
|
|
|
content = content.replace('[boerse]', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('[mehr]', '')
|
|
|
|
|
content = content.replace('[video]', '')
|
|
|
|
|
content = content.replace('...[more]', '')
|
|
|
|
|
content = content.replace('[more]', '')
|
|
|
|
|
content = content.replace('[liveticker]', '')
|
|
|
|
|
content = content.replace('[livestream]', '')
|
|
|
|
|
content = content.replace('[multimedia]', '')
|
2017-09-20 23:57:58 +02:00
|
|
|
content = content.replace('[sportschau]', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('[phoenix]', '')
|
|
|
|
|
content = content.replace('[swr]', '')
|
|
|
|
|
content = content.replace('[ndr]', '')
|
|
|
|
|
content = content.replace('[mdr]', '')
|
|
|
|
|
content = content.replace('[rbb]', '')
|
|
|
|
|
content = content.replace('[wdr]', '')
|
|
|
|
|
content = content.replace('[hr]', '')
|
|
|
|
|
content = content.replace('[br]', '')
|
|
|
|
|
content = content.replace('Click for full.', '')
|
|
|
|
|
content = content.replace('Read more »', '')
|
|
|
|
|
content = content.replace('Read more', '')
|
2017-09-20 23:57:58 +02:00
|
|
|
content = content.replace('...Read More', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('(more…)', '')
|
|
|
|
|
content = content.replace('View On WordPress', '')
|
|
|
|
|
content = content.replace('Continue reading →', '')
|
2018-02-25 23:19:12 +01:00
|
|
|
content = content.replace('» weiterlesen', '')
|
|
|
|
|
content = content.replace('Ein Kommentar.', '')
|
2018-09-15 18:29:12 +02:00
|
|
|
content = content.replace('Änderungen zeigen', '')
|
2019-01-03 22:46:55 +01:00
|
|
|
content = content.replace('(RSS generated with FetchRss)', '')
|
2017-09-20 23:25:57 +02:00
|
|
|
content = content.replace('-- Delivered by Feed43 service', '')
|
|
|
|
|
content = content.replace('Meldung bei www.tagesschau.de lesen', '')
|
|
|
|
|
content = content.replace('<', '<')
|
|
|
|
|
content = content.replace('>', '>')
|
2018-02-25 23:19:12 +01:00
|
|
|
content = re.sub('Nächstältere Version.*', '', content)
|
2018-09-15 18:29:12 +02:00
|
|
|
content = re.sub('Die Seite wurde neu angelegt.*', '', content)
|
|
|
|
|
content = re.sub('Weiterleitung nach.*erstellt.*', '', content)
|
2017-09-20 23:57:58 +02:00
|
|
|
content = re.sub('Der Beitrag.*erschien zuerst auf .+\.', '', content)
|
|
|
|
|
content = re.sub('The post.*appeared first on .+\.', '', content)
|
2017-09-20 23:25:57 +02:00
|
|
|
content = re.sub('http://www\.serienjunkies.de/.*\.html', '', content)
|
|
|
|
|
return content
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_content(content):
|
|
|
|
|
"""Sanitizes content and cuts it to 250 chars"""
|
2017-09-21 00:50:53 +02:00
|
|
|
content = clean_rss(remove_html_tags(html.unescape(content)).strip())
|
2017-09-20 23:25:57 +02:00
|
|
|
if len(content) > 250:
|
|
|
|
|
content = content[0:250] + '...'
|
|
|
|
|
return content
|
