这个喜马拉雅的cookies要插在那个位置
如题，自己有喜马拉雅vip,想问一下在哪里添加一个vipcookies可以爬取vip音频。import requests
import bs4
import json
import os
import openpyxl
class Ximalaya():
def __init__(self):
self.url = 'https://www.ximalaya.com'
self.headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
# 关键字搜索,返回一个列表 的字典数据
def search(self, kw):
res = requests.get(self.url + "/search/" + kw, headers=self.headers)
bs = bs4.BeautifulSoup(res.text, "html.parser")
# bs1放的是标题和网址bs2放的是图片地址
bs1 = bs.find_all('a', class_="xm-album-title ellipsis-2")
bs2 = bs.find_all('a', class_="xm-album-cover")
# 图片
ls = []
for i in range(len(bs1)):
d = dict.fromkeys(("title", "albumId", "src", 'count'))
d['title'] = bs1['title']# 标题
d['albumId'] = bs1['href'].split('/')[-2]# 网址的albumId
d['src'] = "https:" + bs2.img['src']# 图片
d['count'] = bs2.find('div', class_='listen-count').span.text# 播放量
ls.append(d)
return ls
# 访问目标专辑的网页,然后获取所有的章节的列表字典数据+"p1/"
def get_album(self, albumId):
res = requests.get(f"{self.url}/revision/album/v1/getTracksList?albumId={albumId}&pageNum=1&sort=0&pageSize=30",
headers=self.headers)
js = json.loads(res.text)
# 获取总页数 分页计算总页数算法
pageSize = 1000
totalRecord = int(js['data']['trackTotalCount'])
totalPageNum = int((totalRecord + pageSize - 1) / pageSize)
ls = []
for i in range(totalPageNum):
res = requests.get(
f"{self.url}/revision/album/v1/getTracksList?albumId={albumId}&pageNum={i + 1}&sort=0&pageSize={pageSize}",
headers=self.headers)
js1 = json.loads(res.text)
js1 = js1['data']['tracks']
for item in js1:
d = dict.fromkeys(('title', 'trackId', 'playCount'))
d["title"] = item['title']# 标题
d["playCount"] = item['playCount']# 播放量
d["trackId"] = item['trackId']# 下载接口id
ls.append(d)
return ls
# 下载音频文件,返回下载结果 需要提供章节字典 和目录名
def donwn(self, section, sname):
try:
# 如果没有这个目录则创建一个目录
if os.path.isdir(sname) == False:
os.makedirs(sname)
sname = sname + r"/"
res = requests.get(f"https://www.ximalaya.com/revision/play/v1/audio?id={section['trackId']}&ptype=1",
headers=self.headers)
js = json.loads(res.text)
res = requests.get(js['data']['src'], headers=self.headers).content
with open(sname + section['title'] + ".m4a", 'wb') as file:
file.write(res)
print(section['title'] + " 下载成功!")
except:
print(section['title'] + " 下载失败!")
#将数据保存到excel表格中
def to_excel(self, sections, sname):
try:
wb = openpyxl.Workbook()
ws = wb.active# 获取工作表
ws.freeze_panes = 'B2'
#设置行宽 高width是字符数 height是像素
ws.row_dimensions.height = 25
ws.column_dimensions['A'].width = 50
ws.column_dimensions['B'].width = 90
ws.column_dimensions['C'].width = 20
ws.append(['title', 'm4aUrl', 'playCount'])
sname = sname + ".xlsx"
for item in sections:
res = requests.get(f"https://www.ximalaya.com/revision/play/v1/audio?id={item['trackId']}&ptype=1",
headers=self.headers)
js = json.loads(res.text)
print(item['title'], js['data']['src'], item['playCount'])
ws.append(, js['data']['src'], item['playCount']])
wb.save(sname)
print(f"保存到 {sname} 成功!")
except:
print(f"保存到 {sname} 失败!")
if __name__ == "__main__":
while True:
xmly = Ximalaya()
while True:
try:
kw = input("请输入您想搜索的关键字:(书名或者作者)\r\n")
ls = xmly.search(kw)
for i, item in enumerate(ls):
txt = f"{i + 1}-{item['title']}-{item['count']}"
print(txt)
xh = input(f"请输入您想要下载的专辑的序号:1-{len(ls)}返回上一步请输入'#'键\r\n")
# 如果输入了#号键则继续循环问..不是则跳出循环
if xh != '#':
try:
xh = int(xh) - 1
break
except:
print("输入有误!回到开始位置")
except:
print("关键字有误,或者没找到!")
print("正在遍历所有的章节,这需要些时间.......")
# 根据用户选的序号来选择遍历哪个有声书的所有章节
sections = xmly.get_album(ls["albumId"])
for i, item in enumerate(sections):
print(i + 1, item['title'])
ts = input(
f" 有几种交互方式,请参考!\r\n1.请输入需要下载的章节序号:1-{len(sections)} 支持范围下载 例如输入:10-100\r\n2.如果您要全部都下载,请输入'#'键\r\n3.如果您要全部打印到excel表格里请输入'e'键\r\n4.退出按x键\r\n")
name = ls["title"]
if ts == "#":# 全部下载
for item in sections:
xmly.donwn(item, name)
else:
if '-' in ts:# 范围下载
min, max = ts.split('-')
for i in range(int(min), int(max) + 1):
xmly.donwn(sections, name)
elif ts == 'e':# 将数据保存到excel表格里
xmly.to_excel(sections, name)
elif ts=='x':
break
else:# 按序号下载
xmly.donwn(sections, name)
ts=input("还要继续输入'j'键,退出输入任意键")
if ts!='j':
break
我自己在head这儿添加cookeis，好像没效果，还是我的cookie方式错语，求指导。谢谢！
应该是格式问题吧
self.headers = {
"user-agent" : "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
"cookie" : "你的cookie",
} 虽然无法解答楼主的问题，但是很感谢楼主分享了源码。。。。。。。。拿这个试了下，没用VIPcookie，就下载免费的音频，碰到一个问题，创建文件的时候，会有失败，原因在sname中有‘|’,无法创建文件夹和文件，名称不规范，所以失败了，可以改进下把这个split切割了，现在能下载成功了
# 下载音频文件,返回下载结果 需要提供章节字典 和目录名
def donwn(self, section, sname):
sname = sname.split('|')
try:
# 如果没有这个目录则创建一个目录
if os.path.isdir(sname) == False:
os.makedirs(sname)#文件名有不符合创建标准的就会失败
sname = sname + r"/"
res = requests.get(f"https://www.ximalaya.com/revision/play/v1/audio?id={section['trackId']}&ptype=1",
headers=self.headers)
#print(res)
js = json.loads(res.text)
res = requests.get(js['data']['src'], headers=self.headers).content
with open(sname + section['title'].split('|') + ".m4a", 'wb') as file:
file.write(res)
print(section['title'] + " 下载成功!")
except:
print(section['title'] + " 下载失败!")
这是吾爱破解上的一段源码，发帖人说改下cookie就能下载VIP，楼主可以参考下
import requests
from lxml import etree
import os
import time
import json
def Get_ID_Name(url, headers):
Contents_IDS = []
r = requests.get(url, headers=headers)
print(r)
r.encoding = r.apparent_encoding
html = etree.HTML(r.text)
Titles = html.xpath('//div[@class="sound-list _Qp"]/ul/li/div/a/@title')
Contents_lists = html.xpath('//div[@class="sound-list _Qp"]/ul/li/div/a/@href')
for Contents_list in Contents_lists:
links_Cache = str(Contents_list).split('/')[-1]
JsonURL = 'https://www.ximalaya.com/revision/play/v1/audio?id={}&ptype=1'.format(links_Cache)
Contents_IDS.append(JsonURL)
return Titles, Contents_IDS
def Json_Get_links(Contents_IDS, headers):
Itemlists = []
n = 0
for Contents_ID in Contents_IDS:
contents = {}
time.sleep(1.5)
r1 = requests.get(Contents_ID, headers=headers)
r1.encoding = r1.apparent_encoding
results = json.loads(r1.text)
id = results['data']['trackId']
m4alinks = results['data']['src']
contents['ID'] = id
contents['M4aLinks'] = m4alinks
Itemlists.append(contents)
n += 1
print('已采集{}个链接！'.format(n))
# print(Itemlists)
return Itemlists
def DownLoadM4A(Itemlists, filename):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3775.400 QQBrowser/10.6.4208.400',
# 'If-None-Match': '"llN9ISnSdOkEmb835lC9NQ_j47Kl"',
# 'Host': 'fdfs.xmcdn.com',
}
if not os.path.exists('./XMLYFM'):
os.mkdir('./XMLYFM')
count = 0
for filename1, Itemlist in zip(filename, Itemlists):
srclinks = Itemlist['M4aLinks']
print(srclinks)
r2 = requests.get(srclinks, headers=headers)
print(r2)
# print(r2.raise_for_status())
with open('./XMLYFM/' + str(filename1) + '.m4a', 'wb')as f:
f.write(r2.content)
count += 1
print('已下载{}个音频文件！'.format(count))
print("{}个音频文件已全部下载完成！".format(count))
if __name__ == '__main__':
print('正在加载...')
url = 'https://www.ximalaya.com/gerenchengzhang/29391994/'#更换URL下载页面内所有链接
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3775.400 QQBrowser/10.6.4208.400',
'Cookie': '_xmLog=xm_kecz048az1wpks; s&e=8dc4e1b92c46d738b6942a843f86a855; x_xmly_traffic=utm_source%253A%2526utm_medium%253A%2526utm_campaign%253A%2526utm_content%253A%2526utm_term%253A%2526utm_from%253A; Hm_lvt_4a7d8ec50cfd6af753c4f8aee3425070=1598542624; Hm_lpvt_4a7d8ec50cfd6af753c4f8aee3425070=1598543278; s&a=B%0F%08W%0BR%1DZL%0C[Y%0AXL[%1CQVWX%02CWM%01WY%0F[NVV%5CCRBT@OK^XYBXLS',
# 'Referer': 'https://www.ximalaya.com/gerenchengzhang/29391994/',
# 'Host': 'www.ximalaya.com'
}
data1 = Get_ID_Name(url, headers)
IDlinks = data1
fileName = data1
DownLoadM4A(Json_Get_links(IDlinks, headers), fileName)
疾风怪盗 发表于 2020-8-28 00:21
这是吾爱破解上的一段源码，发帖人说改下cookie就能下载VIP，楼主可以参考下
下载时暂时还会出错，我等会有空在研究。 miku520 发表于 2020-8-27 22:45
应该是格式问题吧
self.headers = {
"user-agent" : "Mozilla/5.0 (Windows NT 10.0; WOW64) ...
按照你的方法添加cookies进去，下载vip音频还是失败的，不知道是不是我添加的喜马拉雅cookies方式不对，不知道喜马拉雅的cookies是要全部添加进去还是只要添加1&_token=后面的。 ChinaLee 发表于 2020-8-28 15:47
按照你的方法添加cookies进去，下载vip音频还是失败的，不知道是不是我添加的喜马拉雅cookies方式不对， ...
也有可能是楼上的 cookie 失效了 liuzhengyuan 发表于 2020-8-28 19:44
也有可能是楼上的 cookie 失效了
自己的cookie,刚捉的，网站还登陆着，不知道是不是cookie填写的方式不对，是只要填1&_token=后面的还是全部都要，三种都试了好像还是不行。不知道怎么回事。 ChinaLee 发表于 2020-8-28 19:49
自己的cookie,刚捉的，网站还登陆着，不知道是不是cookie填写的方式不对，是只要填1&_token=后面的还是全 ...
全都要，cookie 放 headers 里
页:
[1]