studentstories.py

import requests
from bs4 import BeautifulSoup
import os

def get_episode(url):
    res = requests.get(url).text
    soup = BeautifulSoup(res, 'lxml')

    mp3_href = soup.find(string='Herunterladen').parent['href']
    mp3_url = base_url + mp3_href
    mp3_name = mp3_href.split('/')[-1]
    if not os.path.exists(os.getcwd() + '/' + mp3_name):
        get_content(mp3_url, mp3_name)
    
    pdf_href = soup.find(id='podcastSprachenDesScripts').find(string='deutsch').parent['href']
    pdf_url = base_url + pdf_href
    pdf_name = mp3_name.replace('mp3', 'pdf')
    if not os.path.exists(os.getcwd() + '/' + pdf_name):
        get_content(pdf_url, pdf_name)
    return

def get_content(url, name):
    res = requests.get(url)
    with open(name, 'wb') as f:
        f.write(res.content)
    return


root_dir = os.getcwd() + '/studentstories'
if not os.path.exists(root_dir):
    os.mkdir(root_dir)
os.chdir(root_dir)

base_url = 'http://www.studentstories.de/'

res = requests.get('http://www.studentstories.de/alle-folgen.html')
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'lxml')
episodes = soup.find_all('div', class_='views-field-title')

for e in episodes[:10]:
    dir_name = e.find('a').string
    if not os.path.exists(os.getcwd() + '/' + dir_name):
        os.mkdir(dir_name)
    os.chdir(dir_name)

    href = e.find('a')['href']
    url = base_url + href
    get_episode(url)
    os.chdir(root_dir)