[爬虫篇]Python爬虫之爬取网页音频_爬虫怎么下载已经找到的声频

for data_id_1,data_name_1 in data\_id\_name\_code\_page\_1:
    audio_DATA = f"https://www.ximalaya.com/revision/play/v1/audio?id={data\_id\_1}&ptype=1" #---->接收data_id至url数据包
    time.sleep(0.1)
    print("正在下载--->%s"%data_name_1)
    audio_DATA_get = requests.get(url=audio_DATA,headers=headers)
    audio_DATA_get_text = audio_DATA_get.text
    audio_DATA_download_url = re.findall('"src":"(.\*?)"',audio_DATA_get_text) #提取下载链接
    print(audio_DATA_download_url[0])
    download_data_url = audio_DATA_download_url[0]
    try:
        open_downloda_data_url = urllib.request.urlopen(download_data_url)
    except:
        print(download_data_url,"---->ERROR！")
    read_download_data_url = open_downloda_data_url.read()
    def download\_data():
        with open("%s.mp3"%data_name_1,"wb") as writes:
            writes.write(read_download_data_url)
    download\_data()

download_1()

def download_2():
for data_id_2,data_name_2 in data_id_name_code_page_2:
audio_DATA = f"https://www.ximalaya.com/revision/play/v1/audio?id={data_id_2}&ptype=1"
time.sleep(0.1)
print(“正在下载—>%s”%data_name_2)
audio_DATA_get = requests.get(url=audio_DATA,headers=headers)
audio_DATA_get_text = audio_DATA_get.text
audio_DATA_download_url = re.findall(‘“src”:“(.*?)”’,audio_DATA_get_text)
print(audio_DATA_download_url)
download_data_url = audio_DATA_download_url[0]
try:
open_download_data_url = urllib.request.urlopen(download_data_url)
except:
print(download_data_url,“---->ERROR！”)
read_download_data_url = open_download_data_url.read()
def download_data():
with open(“%s.mp3”%data_name_2,“wb”) as writes:
writes.write(read_download_data_url)
download_data()
download_2()

### 第四步


以上就是这段代码的主要实现，最后使用print()函数提示音频下载完成。


### 完整代码

import random
import time
import requests
import urllib.request
import re
book_url = “https://www.ximalaya.com/album/22088719”

user_agent = [
“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3”,
“Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0”,
“Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.3”,
“Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.3”,
“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.101 Safari/537.36 Edg/91.0.864.54”
]

headers = {“User-Agent” :random.choice(user_agent)}# 采用user-agent随机反爬机制
url_get_ximalaya = requests.get(headers=headers,url=book_url)
url_get_ximalaya_webcode = url_get_ximalaya.text

def with_url_get_ximalaya_webcode():
with open(“url_get_ximalaya_webcode.txt”,“a”,encoding=“utf-8”) as w:
w.write(url_get_ximalaya_webcode)
with_url_get_ximalaya_webcode()

data_id_name_code_page_1 = re.findall(‘“trackId”😦\d+),“isPaid”:false,“tag”:0,“title”:“(.*?)”’,url_get_ximalaya_webcode)# 1集------>29集
data_id_name_code_page_2 = re.findall(‘“trackId”😦\d+),“trackName”:“(.*?)”’,url_get_ximalaya_webcode)# 21集------>120集

print(“加载列表清单…”)
time.sleep(2)

def download_1():
for data_id_1,data_name_1 in data_id_name_code_page_1:
audio_DATA = f"https://www.ximalaya.com/revision/play/v1/audio?id={data_id_1}&ptype=1" #---->接收data_id至url数据包
time.sleep(0.1)
print(“正在下载—>%s”%data_name_1)
audio_DATA_get = requests.get(url=audio_DATA,headers=headers)
audio_DATA_get_text = audio_DATA_get.text
audio_DATA_download_url = re.findall(‘“src”:“(.*?)”’,audio_DATA_get_text) #提取下载链接
print(audio_DATA_download_url[0])
download_data_url = audio_DATA_download_url[0]
try:
open_downloda_data_url = urllib.request.urlopen(download_data_url)
except:
print(download_data_url,“---->ERROR！”)
read_download_data_url = open_downloda_data_url.read()
def download_data():
with open(“%s.mp3”%data_name_1,“wb”) as writes:
writes.write(read_download_data_url)
download_data()
#print(data_name)
#print(audio_DATA)
download_1()
def download_2():
for data_id_2,data_name_2 in data_id_name_code_page_2:
audio_DATA = f"https://www.ximalaya.com/revision/play/v1/audio?id={data_id_2}&ptype=1"
time.sleep(0.1)
print(“正在下载—>%s”%data_name_2)
audio_DATA_get = requests.get(url=audio_DATA,headers=headers)
audio_DATA_get_text = audio_DATA_get.text
audio_DATA_download_url = re.findall(‘“src”:“(.*?)”’,audio_DATA_get_text)
print(audio_DATA_download_url)
download_data_url = audio_DATA_download_url[0]
try:
open_download_data_url = urllib.request.urlopen(download_data_url)
except:
print(download_data_url,“---->ERROR！”)
read_download_data_url = open_download_data_url.read()
def download_data():
with open(“%s.mp3”%data_name_2,“wb”) as writes:

最后

不知道你们用的什么环境，我一般都是用的Python3.6环境和pycharm解释器，没有软件，或者没有资料，没人解答问题，都可以免费领取（包括今天的代码），过几天我还会做个视频教程出来，有需要也可以领取~

给大家准备的学习资料包括但不限于：

Python 环境、pycharm编辑器/永久激活/翻译插件

python 零基础视频教程

Python 界面开发实战教程

Python 爬虫实战教程

Python 数据分析实战教程

python 游戏开发实战教程

Python 电子书100本

Python 学习路线规划

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

需要这份系统化学习资料的朋友，可以戳这里无偿获取

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！