import urllib3 from bs4 import BeautifulSoup import hashlib import sqlite3 import time from sqlite3 import Error # configure this to your needs xml_out = "/home/micha/websites/exitnode.net/htdocs/ard_teletext.xml" db = r"/home/micha/bla.db" def create_conn(db_file): conn = None try: conn = sqlite3.connect(db_file) return conn except Error as e: print(e) return conn def create_tables(conn): sql_create_tafeln_table = """CREATE TABLE IF NOT EXISTS tafeln ( unixtime int NOT NULL, hash text PRIMARY KEY, tafel int, description text, title text ); """ try: c = conn.cursor() c.execute(sql_create_tafeln_table) return conn except Error as e: print(e) def insert_tafel(conn, tafel): sql = ''' INSERT INTO tafeln(unixtime,hash,tafel,description,title) VALUES(?,?,?,?,?) ''' try: c = conn.cursor() c.execute(sql, tafel) conn.commit() return c.lastrowid except Error as e: err = e def get_tafeln(conn): sql = ''' SELECT description,title from tafeln order by unixtime desc limit 20 ''' try: c = conn.cursor() c.execute(sql) rows = c.fetchall() return rows except Error as e: print(e) def store_tafel(conn, tafel): link = "http://www.ard-text.de/mobil/"+str(tafel) http = urllib3.PoolManager() r = http.request('GET', link) soup = BeautifulSoup(r.data, 'html.parser') desc = soup.find('div', class_='std') title = soup.find('h1') if desc is not None: if title is not None: title = title.text.replace("