百度音乐----墨明棋妙试下

百度音乐----墨明棋妙
刚开始学习Python,试着写了些爬虫，刚开始爬取发现只能爬当前页，第二页和后面的歌曲id只能从网页看到，爬取深度应该不够，而加载第二页时地址栏的地址没有改变，观察第一页后面的XHR信息终于找到了后面页面的歌曲信息数据。

<marque>'http://music.taihe.com/data/user/getsongs?start='+str(i*15)+'&size=15&ting_uid=88012547'
#这个是最后能够爬所有歌曲的主要信息，学习中，大神绕过。分享下，给大家交流，侵联删

```javascript

import requests
import json,os
from lxml import etree

def get_html(url):
    headers = {'Accept-Encoding': 'gzip, deflate, br',
               'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
               'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'}
    response = requests.get(url, headers=headers)
    response.encoding = 'gzip'
    return response

def get_one_info(api_url):
    response = get_html(api_url)
    data = response.json()
    song_name = data['songinfo']['title']
    down_url = data["bitrate"]['file_link']
    return song_name, down_url

def new_path(name):#当前目录下创建新的name文件夹
    if os.path.exists(f'./{name}'):
        pass
    else:
        os.mkdir(f'{name}')
    return name

def down_one_music(path,song_name, down_url):
    r = get_html(down_url)
    with open(f'./{path}/{song_name}.mp3', 'wb')as f:
        f.write(r.content)
    print(f'{song_name}下载完成')

def get_list(url):
    r = get_html(url)
    data = r.json()
    orig_data = data['data']['html']
    tree = etree.HTML(orig_data)
    song_names = tree.xpath('//li/div/span/a/text()')
    song_ids = tree.xpath('//li/div/span/a/@href')
    return song_names, song_ids

def get_list_urls(num):  # 本次num=9
    list_urls = []
    for i in range(num):
        list_url = 'http://music.taihe.com/data/user/getsongs?start=' + str(i * 15) + '&size=15&ting_uid=88012547'
        list_urls.append(list_url)
    # print(list_urls,len(list_urls))
    return list_urls

if __name__ == '__main__':
    path = new_path('墨明棋妙') #创建墨明棋妙文件夹
    list_urls = get_list_urls(9)
    for list_url in list_urls:
        song_names, song_ids = get_list(list_url)
        for song_name, song_id in zip(song_names, song_ids):
            api_url = 'http://musicapi.taihe.com/v1/restserver/ting?method=baidu.ting.song.playAAC&format=jsonp&songid=' + song_id[
                                                                                                                           6:]
            song_name, down_url = get_one_info(api_url)
            down_one_music(path,song_name,down_url)
        print('本页下载完成')