#!/usr/bin/env python
# -*- coding: utf-8 -*-

#Archive.org
from internetarchive import get_item
from os import walk
from os import path
import re
import json,codecs


#urls = {'http://anno.onb.ac.at/cgi-content/anno-plus?aid=e0i&datum=1925&size=45'}


import BeautifulSoup
from urllib2 import urlopen




prefix = 'wget "http://radioarkivo.com/arkivujo/rai-'
#20040516
import datetime
date_1 = datetime.date(2004,06,19)
#e(start_date, "%m/%d/%y")

for i in range(500):
    date_1 = date_1 - datetime.timedelta(days=1)
    month = date_1.strftime('%m')
    year = date_1.strftime('%Y')
    day = date_1.strftime('%d')
    print prefix+year+month+day+".mp3"+'"'

cc
output = codecs.open("radioarkivo.txt", "w", "utf-8")
for i in range(0,56):
    url = 'http://www.ameriko.org/eo/rhc/feed?page='+str(i)
    print url
    html = urlopen(url).read()
    soup = BeautifulSoup.BeautifulSoup(html)
    #print soup
    items = soup.findAll('item')
    for item in items:
        try:
            mp3 = item.enclosure['url']
            print mp3
            output.write('wget '+mp3)
        except:
            print 'No ENCLOSURE'
            print item
        
output.close()


b
#print soup
#boccat = soup.find("dl", "boccat")
def getText(url):
    #print url
    url = 'https://web.archive.org' + url
    #html = urlopen(url).read()
    print url
    #soup = BeautifulSoup.BeautifulSoup(html)
    #print soup
    #reg = re.compile(r'Temo:')
    #elements = [e for e in soup.find_all('a') if reg.match(e.text)]
    #print elements
    return url



for i in range(1,2):
    output.write('\n')
    output.write('\n#-----------------------------')
    url = 'https://web.archive.org/web/20070224064915/http://www.radioarkivo.org/plenlisto.php/'+str(1)
    print url
    html = urlopen(url).read()
    soup = BeautifulSoup.BeautifulSoup(html)

    span = soup.find("span","forta")
    titles = span.parent
    table =  span.parent.parent.parent
    _alltr = table.findAll("tr")

    

    for tr in _alltr:
        _alltd = tr.findAll("td")
        if len(_alltd) == 4:
            date, link, lenght, priskribo = _alltd 
            #print _alltd
            #print priskribo.text
            if '(plu)' in priskribo.text:
                    s =  str(priskribo)
                    match = re.search(r'href=[\'"]?([^\'" >]+)', s)
                    if match:
                        legu_link = match.group(1)
                        #print legu_link
                        priskribo = getText(legu_link)
            else:
                priskribo = priskribo.text
            print date.text,'|', link.text,'|', lenght.text,'|', priskribo         
            output.write('#'+date.text)
            output.write('\n')
            output.write('#'+priskribo)
            output.write('\n')
            output.write('#'+lenght.text)
            output.write('\n')
            output.write('wget '+link.text)
        


output.close()

#print 'results', td
#albumyears = []
#for result in td:
    #print result
    #fields = result.th.findAll("td")
    #print fields
    #
    #albumyears.append(result.a.text)

#print "years = ["+",".join(albumyears) + "]"
#return albumyears
#label = soup.find("label",page_name)