Télécharger les mp3 et les pochettes des albums Danakil qui sont disponibles en streaming sur leur site danakil.fr, et ajouter les tags en ID3

README.md

Téléchagement des mp3 de danakil (avec les pochettes)

Dépendances

* Python 2 * mutagen (bibliothèque pour la gestion des tags audio en python)

Utilisation

sur une debian-like (Ubuntu par exemple):
sudo apt-get install python-mutagen
python danakil.py

danakil.py

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

from xml.dom import minidom
import urllib, os.path, threading
from mutagen.mp3 import EasyMP3

generic_xml_url = "http://player.believe.fr/getPlayerInfo.php?action=getfullinfo&lang=fr&upc=%s&version=5"
first_upc = "3661585684183"

def getTag(domElement, tagName):
	try:
		return domElement.getElementsByTagName(tagName)[0].firstChild.nodeValue
	except:
		return ""

def download_track(track_dom, album):
	title = getTag(track_dom, "longTitle") or getTag(track_dom, "title") or "Chanson " + getTag(track_dom, "track")[0]
	tracknumber = getTag(track_dom, "track")
	url = getTag(track_dom, "fulltrack") or getTag(track_dom, "totalTrack") or getTag(track_dom, "splitfile")

	print (u"%s : téléchargement de %s..." % (album["name"], title))
	filename = title.replace("/", "|") + os.path.splitext(url)[-1]

	if not os.path.exists(filename):
		filename, message = urllib.urlretrieve(url=url, filename=filename)

	audio = EasyMP3(filename)
	audio["title"] = title
	audio["artist"] = audio["author"] = album["artist"]
	audio["genre"] = album["genre"]
	audio["date"] = album["date"]
	audio["tracknumber"] = tracknumber
	audio["album"] = album["name"]
	audio["website"] = album["url"]
	audio.save()
	print (u"\t%s téléchargé" % title)

generic_album = generic_xml_url % first_upc
generic_album_dom = minidom.parse(urllib.urlopen(generic_xml_url%first_upc))

for album_dom in generic_album_dom.getElementsByTagName("albums")[0].getElementsByTagName("album"):
	if album_dom.parentNode.tagName == u"albums" :
		upc = getTag(album_dom, "upc")
		album_dom = minidom.parse(urllib.urlopen(generic_xml_url % upc))
		cur_album = {
			"name" : getTag(album_dom, "longTitle"),
			"artist" : getTag(album_dom, "artist"),
			"genre" : getTag(album_dom, "textGenre"),
			"cover" : getTag(album_dom, "cover"),
			"date" : getTag(album_dom, "digitalReleaseDate"),
			"url" : getTag(album_dom, "linkToArtist")
		}

		urllib.urlretrieve(url=cur_album["cover"], filename=cur_album['name']+".jpg")

		for track_dom in album_dom.getElementsByTagName("track"):
			if track_dom.parentNode.tagName  == u"tracks":
				threading.Thread(target=download_track, args=(track_dom,cur_album)).start()