zwiegespraech_mit_gott.py

import requests
import re
import os

pages = (
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=0.html',
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=1.html',
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=2.html',
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=3.html',
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=4.html',
	'http://www.radioeins.de/programm/sendungen/modo1619/zwiegespraeche_mit/index.htm/page=5.html',
)

reDlPage = re.compile('<a href="([^"]+)" class="[^"]+" title="[^"]+">\[mehr\]</a>')
reDl = re.compile('data-media-ref="([^"]+)"')
reFile = re.compile('"_stream":"([^"]+)"')
reName = re.compile('/([^/\.]+)\.html$')

def download(url, file):
	r = requests.get(url, stream = True)
	with open(file, 'wb') as f:
		for chunk in r.iter_content(chunk_size=8 * 1024): 
			if chunk:
				f.write(chunk)
		f.flush()

for page in pages:
	r = requests.get(page)
	for m in reDlPage.finditer(r.text):
		url = m.group(1)
		m = reName.search(url)
		if not m:
			continue
		name = m.group(1)
		file = name+".mp3"
		r = requests.get('http://www.radioeins.de' + url)
		m = reDl.search(r.text)
		if not m:
			continue
		r = requests.get('http://www.radioeins.de' + m.group(1))
		m = reFile.search(r.text)
		if not m:
			continue
		if os.path.exists(file):
			print(file+" already exists. skipping.")
			continue
		download(m.group(1), name+".mp3")