百度音乐爬虫代码_实现

import requests
import re
import json

# 模拟浏览器去下载mp3
# url = \'http://zhangmenshiting.qianqian.com/data2/music/e93d963095b109ff47de85f1b41ffdd1/522883870/522883870.mp3?xcode=23787929c9177917ed47f60d337fa3fd\'
# # 发送请求
# response = requests.get(url)
# # print(response.content)  # content 二进制数据
# # 持久化
# with open(\'test.mp3\', \'wb\') as f:
#     f.write(response.content)
# 下载mp3的id
# http://music.baidu.com/search?key=刘德华

def get_sids_by_name(name):
    url = \'http://music.baidu.com/search\'
    data = {
        \'key\': name
    }
    response = requests.get(url, params=data)
    response.encoding = \'utf-8\'
    html = response.text
    # print(html)
    ul = re.findall(r\'<ul.*</ul>\', html, re.S)[0]

    # print(ul)
    # 获取sid sid&quot;:551560464
    sids = re.findall(r\'sid&quot;:(\d+),\', ul, re.S)
    return sids


# 根据 song_id 下载mp3
def get_mp3_by_id(song_id):
    song_id = song_id

    api = \'http://tingapi.ting.baidu.com/v1/restserver/ting?method=baidu.ting.song.play&format=jsonp&callback=jQuery17205500581185420972_1513324047403&songid=%s&_=1513324048127\' % song_id
    response = requests.get(api)
    data = response.text
    data = re.findall(r\'\((.*)\)\', data)[0]
    # json
    data = json.loads(data)

    # print(data)
    # print(data[\'songinfo\'])
    title = data[\'songinfo\'][\'title\']
    mp3_url = data[\'bitrate\'][\'show_link\']
    # print(title, mp3_url)
    # 下载mp3
    mp3_data = requests.get(mp3_url).content
    # 持久化

    with open(\'%s.mp3\' % title, \'wb\') as f:
        f.write(mp3_data)

sids = get_sids_by_name(\'刘德华\')
for sid in sids:
    print(sid)
    get_mp3_by_id(sid)