爬取喜马拉雅免费有声小说

import requests
import re
from bs4 import BeautifulSoup
import json
import math

'''
写文件

'''


def json_sanalyzes(legal):

    contents ={}
    for i in legal:
        li=[]
        for k  in i:
            contents['name']=k['trackName']
            contents['src'] =k['src']
            yield contents



   # return contents
    #
    #


def dump_load(url,id):
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'
    }
    res = requests.get(url,headers=header)
    while res.status_code!=200:
        continue
    else:
        counts = res.text
        supers=BeautifulSoup(counts,"html.parser")
        res=supers.find("h2",class_="rC5T")
        ressss=re.findall(r"<h2 class="rC5T">专辑里的声音(<!-- -->(d+)<!-- -->)",str(res))[0]#获取小说总条数
        n=math.ceil(int(ressss)/30) # 区分页漂移量
        for i in range(n):#循环请求要爬取的页面url  每页爬取30条
            url ="https://www.ximalaya.com/revision/play/album?albumId=%s&pageNum=%d&sort=-1&pageSize =30"%(id,i+1)
            contens_rs = requests.get(url,headers=header)
            while contens_rs.status_code!=200:
                continue
            else:
                rescsa=json.loads(contens_rs.content.decode())
                yield rescsa['data']['tracksAudioPlay']   #采用yield 生成器 

if __name__=="__main__":
    import  os
    id  = 12642314 #小说id
    url = "https://www.ximalaya.com/youshengshu/%d/"%id #请求要访问小说页面的主页面
     #dump_load(url,id)
    response = json_sanalyzes(dump_load(url,id))# 获取小说每页列表并解析出 音频地址 和 小说单张名称
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'
    }
    for i in response: # 循环下载小说内容
        dump_cont = requests.get(i['src'], headers=header)  
        while dump_cont.status_code!=200:
              continue
        else:
            p = "D:/untitled2/venv/theand/小说/" # 小说存放地址 
            if os.path.exists(p) == False:      # 判断小说地址是否存在  不存在
                os.mkdir(p)    #则创建目录
            b_name =i['name'].replace('"'," ").replace('"'," ")
            path_paths = p + b_name + ".mp3"  #拼接小说单张字节名称
            path_p = path_paths.replace(' ', '')
            with open(str(path_p), "wb") as f:  #写入文件音频
                f.write(requests.get(i['src']).content)