spider.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-
#
#   Author  :   cold
#   E-mail  :   wh_linux@126.com
#   Date    :   14/01/15 15:55:30
#   Desc    :   从豆瓣FM指定频道下载音乐
#
""" 从豆瓣FM上下载音乐
依赖命令:
    curl

依赖第三方库:
    $ easy_install tornadohttpclient mutagen

Update:
    2014-01-16     使用mutagen为音乐添加ID3信息(豆瓣下载的音乐这些信息貌似被去掉了)
"""
from __future__ import print_function

import os
import json
import random

from tornadohttpclient import TornadoHTTPClient

from mutagen.mp3 import MP3
from mutagen.easyid3 import EasyID3

client = TornadoHTTPClient()


def edit_mp3_tag(path, info):
    valid_key = ["title", "artist", "album"]
    dinfo = {key : value for key, value in info.items() if key in valid_key}
    id3info = MP3(path, ID3 = EasyID3)
    for key, val in dinfo.items():
        id3info[key] = val
    id3info.save()

def download(args):
    cmd = u'curl -o "{0}" "{1}"'.format(*args[:2])
    try:
        os.system(cmd.encode("utf-8"))
        info = args[2]
        edit_mp3_tag(args[0], info)
    except UnicodeError:
        print(cmd)

def handle_response(resp):
    data = json.loads(resp.body)

    file_map = []
    for each in data.get("song"):
        file_name = u"{0}.{1}".format(each.get("title"), each.get("url").split(".")[-1])
        file_name = file_name.replace("/", "-")
        print(file_name)
        if os.path.exists(file_name):
            continue
        file_map.append((file_name, each.get("url").replace("\/", "/"), each))

    map(download, file_map)
    fetch(data["song"][0]["sid"], "s")

def fetch(sid = "", type="n"):
    url = "http://douban.fm/j/mine/playlist"
    gd = 27 # 古典
    hy = 1  # 华语
    params = {"type":type, "sid":sid, "pt":0.0, "channel":hy,
              "pb":64, "from":"mainsite",
              "r":hex(random.randrange(0x0000000000, 0xffffffffff))[2:]}

    client.get(url, params, callback = handle_response)

if __name__ == "__main__":
    fetch()
    client.start()