python爬取网易云音乐专辑图片+歌词

最新推荐文章于 2023-12-09 09:54:22 发布

转载最新推荐文章于 2023-12-09 09:54:22 发布 · 1.5k 阅读

4 ·

CC 4.0 BY-SA版权

原文链接：https://www.jianshu.com/p/dc4d31009340

文章标签：

#python

Python爬虫专栏收录该内容

678 篇文章

订阅专栏

思路
一开始的想法是全都直接根据歌单获取歌曲的ID，然后每首歌都按那个格式001.mp3\001.txt\001.png存下来
后来发现我好像做不到直接下mp3……因为在网页版一点会跳出来请在PC版下载（咦所以结果我也不知道怎么操作……）

然后计划就变成了 - 爬图片+歌词，命名成和音乐同个格式，然后按名字排序之后就可以用改名软件批量直接改成这个样子了（自以为很机智）
虽然本人对python的理解还停留在曾经因作业要求爬过一次的莎士比亚全集……

具体操作

美汤（程序员都是吃货系列

好像是评论比较难爬
然后没有追求的我就把这一块都去了……
http://www.jianshu.com/p/2b783f7914c6

先对着一个歌单把ID爬下来
然后再对着ID爬各种……（只能想到这样了）

http://www.bkjia.com/Pythonjc/1189598.html

歌曲
https://www.zhihu.com/question/41505181
python 下载mp3(这个例子是百度音乐的)
http://www.th7.cn/Program/Python/201507/499020.shtml

图片
http://www.tuicool.com/articles/6NVjAjr
http://www.th7.cn/Program/Python/201603/775611.shtml
http://www.cnblogs.com/Albert-Lee/p/6276847.html

歌词
https://juejin.im/entry/59185f37da2f60005dee09d3
http://www.cnblogs.com/Beyond-Ricky/p/6757954.html

具体实现

应该可以从如下代码中看到以上一些参考文献的痕迹（捂脸）
虽然拼凑痕迹有点明显orz反正能大概实现功能已经很满意了

读取歌单

# 爬取某歌单的所有歌曲ID
def getSongIdList():
 songIdList = []
 playListUrl = 'http://music.163.com/playlist?id=918802417'#空城 finished

 soup = BeautifulSoup(_session.get(playListUrl).content)
 ul = soup.find('ul', attrs={'class': 'f-hide'})
 for li in ul.findAll('li'):
     songId = (li.find('a'))['href'].split('=')[1]
     print  songId
     songIdList.append(songId)
 # 去一下重复的歌曲I
 songIdList = list(set(songIdList))
 return songIdList

歌曲名+歌手名

 url = BASE_URL + 'song?id=' + str(song.id)
 url.decode('utf-8')
 soup = BeautifulSoup(_session.get(url).content)
 strArr = soup.title.string.split(' - ')
 song.singer = strArr[1]
 name = strArr[0].encode('utf-8')

歌词

def get_lyric_by_music_id(music_id,songstr):#定义一个函数，通过音乐的id得到歌词
    lrc_url = 'http://music.163.com/api/song/lyric?' + 'id=' + str(music_id) + '&lv=1&kv=1&tv=-1'
    #lrc_url = BASE_URL + 'song?id=' + str(music_id)
    lyric=requests.get(lrc_url)
    json_obj=lyric.text
    #print(json_obj)
    j=json.loads(json_obj)
    file_atr = 'E:\\music\\' + songstr + '.txt'     
    f = open(file_atr,'wb')
    f.writelines(songstr.encode('utf8'))
    f.write('\n')
    try:#部分歌曲没有歌词，这里引入一个异常
        lrc=j['lrc']['lyric']
        pat=re.compile(r'\[.*\]')
        lrc=re.sub(pat,"",lrc)
        lrc=lrc.strip()
        #print type(lrc)
        f.writelines(lrc.encode('utf8'))
        f.close()
        return lrc
    except KeyError as e:
        f.writelines('No Available Lyric on CloudMusic')
        f.close()

专辑封面

def get_img(url,songstr):  ##保存图片
    #print '##正在读取图片##'
    #print url
    urlStream=urllib.urlopen(url)
    htmlString=urlStream.read()
    #print htmlString
    if( len(htmlString)!=0 ):
        patternString=r'http://p1.music.126.net/.*?.jpg'
        searchPattern=re.compile(patternString)
        imgUrlList=searchPattern.findall(htmlString)
    imgUrl =imgUrlList[0]
    #print imgUrl
    if( len(imgUrl)!= 0 ):
        urllib.urlretrieve(imgUrl,'E:\\music\\' + songstr + '.jpg')

完整代码

import requests
from selenium import webdriver
from bs4 import BeautifulSoup
import os, json
import base64
import warnings
import re,urllib,uuid
'''
遇到不懂的问题？Python学习交流群：1136201545满足你的需求，资料都已经上传群文件，可以自行下载！
'''

warnings.filterwarnings("ignore")
BASE_URL = 'http://music.163.com/'
_session = requests.session()
localPath='d://pythonPath'



def createFileWithFileName(localPathParam,fileName):
    totalPath=localPathParam+'//'+fileName
    if not os.path.exists(totalPath):
        file=open(totalPath,'a+')
        file.close()

class Song(object):
 def __lt__(self, other):
     return self.commentCount > other.commentCount

# 爬取某歌单的所有歌曲ID
def getSongIdList():
 songIdList = []
 playListUrl = 'http://music.163.com/playlist?id=918802417'#空城 finished

 soup = BeautifulSoup(_session.get(playListUrl).content)
 ul = soup.find('ul', attrs={'class': 'f-hide'})
 for li in ul.findAll('li'):
     songId = (li.find('a'))['href'].split('=')[1]
     print  songId
     songIdList.append(songId)
 # 去一下重复的歌曲I
 songIdList = list(set(songIdList))
 return songIdList



# 获取歌曲信息
def matchSong(songId):
 song = Song()
 song.id = songId
 return song

def get_lyric_by_music_id(music_id,songstr):#定义一个函数，通过音乐的id得到歌词
    lrc_url = 'http://music.163.com/api/song/lyric?' + 'id=' + str(music_id) + '&lv=1&kv=1&tv=-1'
    #lrc_url = BASE_URL + 'song?id=' + str(music_id)
    lyric=requests.get(lrc_url)
    json_obj=lyric.text
    #print(json_obj)
    j=json.loads(json_obj)
    file_atr = 'E:\\music\\' + songstr + '.txt'

    f = open(file_atr,'wb')
    f.writelines(songstr.encode('utf8'))
    f.write('\n')
    try:#部分歌曲没有歌词，这里引入一个异常
        lrc=j['lrc']['lyric']
        pat=re.compile(r'\[.*\]')
        lrc=re.sub(pat,"",lrc)
        lrc=lrc.strip()
        #print type(lrc)
        f.writelines(lrc.encode('utf8'))
        f.close()
        return lrc
    except KeyError as e:
        f.writelines('No Available Lyric on CloudMusic')
        f.close()

def get_img(url,songstr):  ##保存图片
    #print '##正在读取图片##'
    #print url
    urlStream=urllib.urlopen(url)
    htmlString=urlStream.read()
    #print htmlString
    if( len(htmlString)!=0 ):
        patternString=r'http://p1.music.126.net/.*?.jpg'
        searchPattern=re.compile(patternString)
        imgUrlList=searchPattern.findall(htmlString)
    imgUrl =imgUrlList[0]
    #print imgUrl
    if( len(imgUrl)!= 0 ):
        urllib.urlretrieve(imgUrl,'E:\\music\\' + songstr + '.jpg')


# 设置歌曲的信息
def setSongInfo(song):
 url = BASE_URL + 'song?id=' + str(song.id)
 url.decode('utf-8')
 soup = BeautifulSoup(_session.get(url).content)
 strArr = soup.title.string.split(' - ')
 song.singer = strArr[1]
 name = strArr[0].encode('utf-8')
 song.name = name
 songstr = strArr[0]+ ' - '+ strArr[1]
 songstr = songstr.replace('/',' ')
 song.lrc = get_lyric_by_music_id(song.id,songstr)
 song.img = get_img(url,songstr)


# 获取符合条件的歌曲列表
def getSongList():
 print ' ##正在爬取歌曲编号... ##'
 songIdList = getSongIdList()
 print ' ##爬取歌曲编号完成，共计爬取到' + str(len(songIdList)) + '首##'
 songList=[]
 for id in songIdList[0:]:
  song = matchSong(id)
  if None != song:
   setSongInfo(song)
   songList.append(song)
   print '成功匹配一首{名称:', song.name, ' - ', song.singer,  '}'

#  print ' ##爬取完成，符合条件的的共计' + str(len(songList)) + '首##'
 return songList

def main():
 songList = getSongList()



if __name__ == '__main__':
 main()

运行过程

[外链图片转存失败(img-47MjNNQ3-1566302376843)(https://upload-images.jianshu.io/upload_images/13406307-a1dec35e4ec7df1b?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)]

结果

~~（这里我很怂的把歌手名去掉了因为斜杠的问题解决不掉）~~
[外链图片转存失败(img-BzCkZ8HE-1566302376843)(https://upload-images.jianshu.io/upload_images/13406307-35414fe7ff93d3aa?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)]

迷之操作

格式工厂转图片格式 + 拖把更名器改名……
[外链图片转存失败(img-2Ja1G5m3-1566302376843)(https://upload-images.jianshu.io/upload_images/13406307-5d1252d2187dcf6d?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)]

我想知道这个失败是什么鬼……

[外链图片转存失败(img-2Y2odihY-1566302376844)(https://upload-images.jianshu.io/upload_images/13406307-98f58cef10adbe9c?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)]