Petit script python codé à l'arrache pour récupérer les urls directes des podcasts France Inter et France Culture à partir de leur page descriptive.

get_url.py

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

import codecs, locale, os, sys
sys.stdout = codecs.getwriter('utf-8')(sys.stdout)

import httplib
import urllib2 
from cookielib import CookieJar

import re
import urlparse
import json

"""
http://www.franceinter.fr/emission-la-bas-si-jy-suis-julian-assange-cyberterroriste-2

récupérer http://www.franceinter.fr/player/reecouter?play=590616

(http://www.franceinter.fr/player/reecouter?play=590616)

contient iframe http://www.franceinter.fr/player/export-reecouter?content=590616

<object id='flash_player' classid='clsid:D27CDB6E-AE6D-11cf-96B8-444553540000' codebase='http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0' WIDTH='389' HEIGHT='33'>
      <param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf?playerUrl=/sites/all/modules/rf/rf_player/swf/maxi_player.swf&type=aod&startTime=0&endTime=0&basePathConfig=/&nextId=&prevId=&idCurrent=590488&urlAOD=sites/default/files/sons/2013/03/s12/NET_FI_f36dfa39-b5d1-4fa5-a892-b97075c918b6.mp3&infos=[{"media_name":"julian-assange-cyberterroriste","media_genre":"Autres","dom_id":"299099206552","media_section3":"France Inter","media_section2":"aod","media_section1":"emission","media_section4":"la-bas-si-jy-suis","media_section5":"20130320","media_length":3325,"send_type":"","domaine":""}]' />

wget -O julian.mp3 "http://www.franceinter.fr/sites/default/files/sons/2013/03/s12/NET_FI_f36dfa39-b5d1-4fa5-a892-b97075c918b6.mp3"
"""

def download(url):
    print url

    cj = CookieJar()
    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
    opener.addheaders = [ 
        ('Content-type', 'application/x-www-form-urlencoded'),
        ('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'),
        ('Accept', 'text/plain, image/jpeg')
        ]

    try:
        netloc = urlparse.urlsplit(url).netloc # www.franceculture.fr ou www.franceinter.fr

        resp = opener.open(url)
        c = resp.read().decode('utf-8')

        RE_CODE = re.compile(r'href="/player/reecouter\?play=(?P<code>\d+)', re.UNICODE)
        m = RE_CODE.search(c)
        code = int(m.group('code'))
        print code

        url = 'http://%s/player/export-reecouter?content=%s' % (netloc, code)
        print url

        resp = opener.open(url)
        c = resp.read().decode('utf-8')

        RE_PARAMS = re.compile(r"<param name='movie'[^>]+>", re.UNICODE)
        m = RE_PARAMS.search(c)
        i = m.group().find('?')
        j = m.group().find(']')
        params = m.group(0)[i+1:j+1]
        d = dict(urlparse.parse_qsl(params))
        infos = json.loads(d['infos'])[0]

        print 'wget -O %s-%s-%s.mp3 "http://%s/%s"' % (
            infos['media_section4'],
            infos['media_section5'],
            infos['media_name'],
            netloc,
            d['urlAOD'])
    except:
        raise
        return 1

    return 0

download(sys.argv[1])