用python爬取酷狗音乐
用python爬取某狗音乐
（此文为小左1120原创，转载请标明出处，如违规请联系作者立刻删除）
此文为python爬虫文章，讲了用python爬取某狗里的歌名并下载（包括vip）后面带exe
由于本人爬虫经验不足，代码可能会粗糙，有bug，麻烦大佬加个微信QQ一起学吧！代码失效了也给我通知一声
微信：aicoder-XZ
QQ：2583188733
老规矩
配置好python
配置好pycharm
再安装依赖的模块：
点这里（感谢大神hy_696的文章）(ps:在他给的网站里看一下最新版本，不要下载，在https://mirrors.huaweicloud.com/geckodriver找到刚看的最新版本，进去后下载，这样又快又稳定）
接下来，按下win+R输入cmd-回车！在黑窗口里输入
pip install requests
打开pycharm，
新建项目，（不会的话点这里）
进去后，右键文件夹，
输入个你喜欢的名字，回车！
开始写代码吧！
先打开浏览器
访问某狗音乐下载（不要用ie）
随便搜索搜索看看网址
以《癞蛤蟆》为例
网址是
https://music.liuzhijin.cn/?name=癞蛤蟆&type=kugou
所以搜索的格式是
https://music.liuzhijin.cn/?name=歌曲名&type=kugou
好，咱先爬：
from selenium import webdriver
import time
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
browser = webdriver.Firefox()
browser.get(url)
这个网站有一点问题，底下有个载入更多，不能直接全部加载，
没有事的。。
按下F12
在出来的控制台的左上角点这个按钮
点击载入更多
ok，浏览器会定位到这样一条元素，
<div class="aplayer-more">载入更多div>
右击-复制-完整的XPath（火狐是XPath）
好
from selenium import webdriver
import time
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
browser = webdriver.Firefox()
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("你的XPath").click()
except:
break
我的是/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]
所以就是
from selenium import webdriver
import time
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
browser = webdriver.Firefox()
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]").click()
except:
break
一切就绪，获取网页源代码
html = browser.page_source
控制台上看一看
看到一大堆li
挑一个（我搜索的Mojito）
<li>
<span class="aplayer-list-cur" style="background: #0e90d2;">span>
<span class="aplayer-list-index">2span>
<span class="aplayer-list-title">Mojitospan>
<span class="aplayer-list-author">许66span>
li>
<li>
<span class="aplayer-list-cur" style="background: #0e90d2;">span>
<span class="aplayer-list-index">3span>
<span class="aplayer-list-title">Mojitospan>
<span class="aplayer-list-author">音乐之声-SongTastespan>
li>
经过阅读知道
<li>
<span class="aplayer-list-cur" style="background: #0e90d2;">span>
<span class="aplayer-list-index">歌曲排名span>
<span class="aplayer-list-title">歌曲名span>
<span class="aplayer-list-author">歌手span>
li>
呵呵呵，我们用正则表达式提取一下，顺便封装成方法
#coding:utf-8
from selenium import webdriver
import time,re
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
def geturl(url):
browser = webdriver.Firefox()
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]").click()
except:
break
return browser.page_source
html = geturl(url)
a111 = '''
(.*?)
(.*?)
'''
a11='''
(.*?)
(.*?)
'''
a='''
(.*?)
(.*?)
'''
a1=re.findall(a111,html)
b1 = re.findall(a11,html)
b2=re.findall(a,html)
data = a1+b1+b2
加上选择
#coding:utf-8
from selenium import webdriver
import time,re
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
def geturl(url):
browser = webdriver.Firefox()
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]").click()
except:
break
return browser.page_source
html = geturl(url)
a111 = '''
(.*?)
(.*?)
'''
a11='''
(.*?)
(.*?)
'''
a='''
(.*?)
(.*?)
'''
a1=re.findall(a111,html)
b1 = re.findall(a11,html)
b2=re.findall(a,html)
data = a1+b1+b2
song = 0
for i in data:
print(i)
num = input(">>")
for i in data:
if (str(i[0])==num):
song = i
url = "https://music.liuzhijin.cn/?name=" + song[1]+' - '+song[2] + "&type=kugou"
print(geturl(url))
看下载链接的位置的代码是
<span class="am-input-group-btn">
<a id="j-src-btn" class="am-btn am-btn-default" target="_blank" href="(.*?)" download="(.*?)">
<i id="j-src-btn-icon" class="am-icon-download"></i>
</a>
</span>
我们通过搜索歌曲名 - 歌手来搜索并下载
#coding:utf-8
from selenium import webdriver
import time,re,requests
name = input(">")
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
def geturl(url):
browser = webdriver.Firefox()
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]").click()
except:
break
return browser.page_source
html = geturl(url)
a111 = '''
(.*?)
(.*?)
'''
a11='''
(.*?)
(.*?)
'''
a='''
(.*?)
(.*?)
'''
a1=re.findall(a111,html)
b1 = re.findall(a11,html)
b2=re.findall(a,html)
data = a1+b1+b2
song = 0
for i in data:
print(i)
num = input(">>")
for i in data:
if (str(i[0])==num):
song = i
url1 = "https://music.liuzhijin.cn/?name=" + song[1]+' - '+song[2] + "&type=kugou"
a7='''
'''
html1=geturl(url1)
a8 = re.findall(a7,html1)
r = requests.get(a8[0][0])
with open(a8[0][1], "wb") as code:
code.write(r.content)
接下来是优化环节：
我发现，用这东西乱蹦浏览器，我们使用无头模式，再加一个循环
完整代码
#coding:utf-8
from selenium import webdriver
import time,re,requests
while True:
name = input("输入你想下载的歌曲名并按下回车（不输入并按下回车退出）:")
if (name==''):
break
else:
url = "https://music.liuzhijin.cn/?name=" + name + "&type=kugou"
def geturl(url):
options = webdriver.FirefoxOptions()
options.add_argument('-headless')
browser = webdriver.Firefox(options=options)
browser.get(url)
time.sleep(3)
while True:
try:
browser.find_element_by_xpath("/html/body/section/div[1]/div/form[2]/div[4]/div/div[4]").click()
except:
break
temp = browser.page_source
browser.close()
return temp
html = geturl(url)
a111 = '''
(.*?)
(.*?)
'''
a11='''
(.*?)
(.*?)
'''
a='''
(.*?)
(.*?)
'''
a1=re.findall(a111,html)
b1 = re.findall(a11,html)
b2=re.findall(a,html)
data = a1+b1+b2
song = 0
for i in data:
print(i)
num = input("请输入序号：")
for i in data:
if (str(i[0])==num):
song = i
url1 = "https://music.liuzhijin.cn/?name=" + song[1]+' - '+song[2] + "&type=kugou"
a7='''
'''
html1=geturl(url1)
a8 = re.findall(a7,html1)
r = requests.get(a8[0][0])
with open(a8[0][1], "wb") as code:
code.write(r.content)
使用示例：
exe文件下载地址：https://www.jianguoyun.com/p/DcMuR8YQs7rYCBjy1rED
-小左1120
这个程序费了我2天时间，求求你们点个赞，关个注呗