Generate a list of radiostations from http://wiki.ubuntuusers.de/internetradio/stationen#Radiosender-Deutschland and save it in json for a synology DSM

.py

from __future__ import unicode_literals
from bs4 import BeautifulSoup
from urllib import urlretrieve
import re
import json
import mechanize

class Browser(mechanize.Browser):
    ''' Browser

     Erbt von Mechanize.Browser.
    '''
    def __init__(self):
        mechanize.Browser.__init__(self)
        self.addheaders = [
            ('User-agent',
                'Mozilla/5.0 (X11; U; Linux i686; en-US;\
                        rv:1.9.0.1) Gecko/2008071615 \
                        Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
        self.set_handle_equiv(True)
        self.set_handle_redirect(True)
        self.set_handle_referer(True)


_conf = dict(
    URL="http://wiki.ubuntuusers.de/internetradio/stationen#Radiosender-Deutschland")
## Get rid of comments




br = Browser()
def get_radiostations():
    soup = BeautifulSoup(br.open(_conf['URL']).read(), 'html.parser')
    for div in  soup.findAll("div", { "class" : "section_2" }):
        a = div.find("a", {"class": "external"})
        try:
            _title = a.contents
        except AttributeError as e:
            #print (e.message)
            continue
        pre = div.find("pre")
        try:
            _url = [line.split('#')[0].split('\n')[0]
                     for line in pre 
                     if "http://" in line]
        except TypeError as e:
            #print (e.message)
            continue
        try:
            yield((_title, _url))
        except IndexError:
            continue

stations = []
total = 0
for station in get_radiostations():
    stations.append( dict(
        bitrate=None,
        desc = "",
        name = "".join(station[0]).encode('utf-8'),
        url = "".join(station[1]).encode('utf-8')
        ))
    total += 1
    
with open ("/tmp/userdef.json", "w") as wfile:
    wfile.write(json.dumps(dict(
                total = total, 
                stations = stations),
                           sort_keys=True, 
                           indent=4, 
                           separators=(',', ': ')))
#print (json.dumps(dict(total = total, stations = stations),sort_keys=True, indent=4, separators=(',', ': ')))