参考链接 浏览器 f12 network网络里面查看各种请求和返回
0、请求 URL: https://www.ximalaya.com/revision/album?albumId=19753959
请求方法: GET 获取专辑总音频数，可知页数
{
"ret": 200,
"msg": "æå",
"data": {
"mainInfo": {
"albumStatus": 1,
"showApplyFinishBtn": false,
"showEditBtn": false,
"showTrackManagerBtn": false,
"showInformBtn": true,
"cover": "//imagev2.xmcdn.com/group42/M0A/0B/62/wKgJ9FrV-22TLLQLAABoJqGyCDw207.jpg",
"albumTitle": "JimmyShowåç±³ç§ - 访è°ä¸æ "
}
"tracksInfo": {
"trackTotalCount": 38,
"sort": 1,
"tracks": [
{
"index": 38,
"trackId":1111,,,,
}
]
}
}
}1、获取专辑list
请求 URL: https://www.ximalaya.com/revision/album/v1/getTracksList?albumId=19753959&pageNum=1
请求方法: GET
{
"ret": 200,
"data": {
"currentUid": 163357056,
"albumId": 19753959,
"trackTotalCount": 38,
"sort": 1,
"tracks": [
{
"index": 38,
"trackId": 147521319,
"isPaid": false,
"tag": 0,
"title": "039 Why Horses Can't Wear Flip Flops",
"playCount": 1729,
"showLikeBtn": true,
"isLike": false,
"showShareBtn": true,
"showCommentBtn": true,
"showForwardBtn": true,
"createDateFormat": "1å¹´å",
"url": "/ertong/19753959/147521319",
"duration": 1508,
"isVideo": false,
"videoCover": null,
"isVipFirst": false,
"breakSecond": 385,
"length": 1508
},.....
],
"pageNum": 1,
"pageSize": 30,
"superior": [],
"lastPlayTrackId": 147521319
}2、请求 URL: https://www.ximalaya.com/revision/track/trackPageInfo?trackId=147521319
请求方法: GET
无啥用
3、 请求 URL: https://www.ximalaya.com/revision/play/v1/audio?id=147521319&ptype=1
请求方法: GET 获取m4a地址
{
"ret": 200,
"data": {
"trackId": 147521319,
"canPlay": true,
"isPaid": false,
"hasBuy": true,
"src": "https://fdfs.xmcdn.com/group52/M03/0C/45/wKgLcFwhqOCgYeGHALpHth2twRw024.m4a",
"albumIsSample": false,
"sampleDuration": 0,
"isBaiduMusic": false,
"firstPlayStatus": true
}
}
ximalaya_m4a_download.py.txt
喜马拉雅接口.txt
# -*- coding: utf-8 -*-
"""
Created on Sun Apr 5 11:58:25 2020
@author: 54861
"""
import requests
import math
import os
import re
import time
headers = {
#'Referer': start_url, # 注意加上referer
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
"""
获取总视频数
参数：albumID 专辑ID
"""
def get_album_number(albumID):
url = "https://www.ximalaya.com/revision/album?albumId="+str(albumID)
resp = requests.get(url,headers = headers)
result = resp.json()
if result['ret'] == 200:
cover = result['data']['mainInfo']['cover']
albumTitle = result['data']['mainInfo']['albumTitle']
count = result['data']['tracksInfo']['trackTotalCount']
else:
cover=''
albumTitle=''
count = 0
return cover,albumTitle,count
"""
获取一页音频信息
参数：albumID 专辑ID
参数：pageNum ！！页码1开始！！
"""
def get_track_list(albumID, pageNum):
trackList = []
url = "https://www.ximalaya.com/revision/album/v1/getTracksList?albumId="+str(albumID)+"&pageNum="+str(pageNum)
resp = requests.get(url,headers = headers)
result = resp.json()
if result['ret'] == 200:
tracks = result['data']['tracks']
for track in tracks:
trackList.append({'trackId':track['trackId'],'title':track['title']})
return trackList
"""
获取音频下载地址
参数：trackID 音频ID
"""
def get_track_url(trackID):
url = "https://www.ximalaya.com/revision/play/v1/audio?id="+str(trackID)+"&ptype=1"
resp = requests.get(url,headers = headers)
result = resp.json()
if result['ret'] == 200:
src = result['data']['src']
if len(src) > 0:
return src
"""
下载音频
参数：url 音频下载地址
参数：file 文件本地路径
"""
def download_track(url,file):
resp = requests.get(url, headers = headers, stream = True)
with open(file, 'wb') as f:
for data in resp.iter_content(chunk_size = 1024):
if data: f.write(data)
"""
从一个字符串得到符合windows要求的文件名
"""
def good_win_filename(title):
rstr = r"[\/\\\:\*\?\"\<\>\|]" # '/ \ : * ? " < > |'
new_title = re.sub(rstr, "_", title) # 替换为下划线
return new_title
if __name__ == '__main__':
#albumIds = []
#albumIds = [5943599,3179138,13742743,403231]
for albumId in albumIds:
print ("start downloading:" + str(albumId)+" of"+str(albumIds))
coverUrl,albumTitle,total = get_album_number(albumId)
dir = 'ximalaya_m4a/'
if not os.path.exists(dir):#创建专辑文件夹
os.makedirs(dir)
dir = 'ximalaya_m4a/'+str(albumId)+"_"+good_win_filename(albumTitle)+'/'
if not os.path.exists(dir):#创建专辑文件夹
os.makedirs(dir)
download_track("http:"+coverUrl,dir+"cover"+coverUrl[coverUrl.rindex('.'):])#下载封面
pageCount = math.ceil( total/30)
i = 1
for pageNum in range(0,pageCount):
time.sleep(1)#防止短语音文件下载过快，被服务器断开链接
trackList = get_track_list(albumId,pageNum+1)
for track in trackList:
trackUrl = get_track_url(track['trackId'])
time.sleep(1)#防止短语音文件下载过快，被服务器断开链接
if trackUrl:
ext = trackUrl[trackUrl.rindex('.'):]
file_path = dir + good_win_filename(track['title']) + ext
print ('downloading file:'+str(i)+" of "+str(total)+', page '+str(pageNum+1)+" of "+str(pageCount)+"\n"+ trackUrl + "\n"+track['title'])
download_track(trackUrl, file_path)
i = i + 1
print("\n\n"+str(i-1)+" files downed in:"+dir)