aerostat_downloader.py

#!/usr/bin/env python3.3
#
# hedgeven@linux.com, 2014
#
# Distributed under the MIT License.
# (See accompanying file LICENSE or copy at
#  http://opensource.org/licenses/MIT)
#
#
# Script for downloading Aerostat podcasts (and maybe other podcasts)
# To fill the ID3 tag need the eyeD3 
# Usage:
# ./aerostat_downloader.py [start:end]
#

from urllib.request import urlopen
from xml.etree import ElementTree as ET
import re, os, sys

work_dir = "Downloads/Aerostat"
xml_url = "http://aerostat.rpod.ru/rss.xml"


def download(url,file_name):

    u = urlopen(url)
    f = open(file_name, 'wb')
    meta = u.info()
    file_size = int(meta.get("Content-Length"))
    print("Downloading: "+file_name, end="\t")
    
    file_size_dl = 0
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break
    
        file_size_dl += len(buffer)
        f.write(buffer)
        status = r"[%3.2f%%]" % (file_size_dl * 100. / file_size)
        status = status + chr(8)*(len(status)+1)
        print(status, end=" ")
    
    f.close()
    print()

def main(argv):

    pod_min=1
    pod_max=0
    if len(argv)>0:
        args = re.findall('\d+', argv[0])
        try:
            pod_min=int(args[0])
            pod_max=int(args[1])
        except:
            pass

    root = ET.parse(urlopen(xml_url)).getroot()
    items = root.findall('channel')[0].findall('item')
    pod_list={}
    for item in items:
        index=int(re.findall('\d+', item.find('title').text)[0])
        pod_list[index] ={}
        pod_list[index]['title'] = item.find('title').text
        pod_list[index]['author'] = item.find('author').text
        pod_list[index]['url'] = item.find('enclosure').attrib['url']
    if pod_max==0 or pod_min>pod_max:
        pod_max=len(pod_list)
    if not os.path.exists(work_dir):
        os.mkdir(work_dir) 
    for item in sorted(pod_list)[pod_min-1:pod_max]:
        author=pod_list[item]['author']
        title=re.sub('"', '', pod_list[item]['title'])
        filename=title+'.mp3'
        url=pod_list[item]['url']
        download(url,work_dir+'/'+filename)
        os.system("eyeD3 --set-encoding=utf8 --to-v2.4 --remove-v1 --remove-comments -a "\
                   +author+" -A "+author+" -t '"+title+"' -n "+str(item)+" '"+work_dir+"/"\
                   +filename+"' >/dev/null")

if __name__ == "__main__":
    main(sys.argv[1:])

for item in items:
index = int(re.findall('\d+', item.find('title').text)[0])
pod_list[index] ={}
pod_list[index]['title'] = item.find('title').text
pod_list[index]['author'] = item.find('author').text
pod_list[index]['url'] = item.find('enclosure').attrib['url']

Спасибо, поправил.

Для автоматической корректировки тегов нужно наличие программы eyeD3