唱吧音乐爬取 &全民K歌爬取

唱吧音乐爬取

#导入框架
import requests
import re

#确定url
url = 'http://changba.com/u/461549830'
#请求
def changba(url):
	res = requests.get(url)
	if res.status_code == 200:
		res_html = res.text
		# print(res.text)
		
		#匹配歌曲链接
		reg1 = '<a href="(/s/.{22})" style="color:#999;display:block;" target="_blank">' 									
		media = re.findall(reg1, res_html)
		# print(media)
		media_mid = []
		for i in range(len(media)):
			media_mid.append('http://changba.com'+media[i])
		print(media_mid)

		#匹配歌曲名称
		reg2 = '^style="color:#999;display:block;" target="_blank">\n\t*([\u4e00-\u9fa5]{1,20})\t*<div class="userPage-work-detail">$'
		reg2 = '(.*)<div class="userPage-work-detail">'
		name = re.findall(reg2, res_html)
		song_name = []
		for i in range(len(name)):
			song_name.append(name[i].strip())
		print(song_name)

		reg3 = 'http://\w{4,20}.changba.com/\d{10}.mp3'
		for i in range(len(media_mid)):
			result = requests.get(media_mid[i]).text
			MP3_html = re.findall(reg3,result)
			print(MP3_html)
			if(MP3_html):
				MP3 = requests.get(MP3_html[0])
				if MP3.status_code ==200:
					with open(song_name[i]+'.mp3','wb') as f:
						f.write(MP3.content)
				else:
					continue
changba(url)

全民K歌音乐爬取

from urllib import request
import re
import os
import json
#个人主页地址
url = "https://kg.qq.com/node/personal?uid=6a9d9a81222830833c"
 
html = request.urlopen(url).read().decode('utf-8')
data = re.findall(r'"ugclist":.*?],', html)#获取页面中数据json，处理有点糙，不过能用哈
ugclists = data[0][10:-1]

print(len(data[0]))
for ugclist in json.loads(ugclists):#json.loads把字符串转json，以前没使过Python，这里好像说是什么dict的，也就是key=>value的数据格式，很好理解
    print(ugclist['shareid'])#这个数据很关键是每首曲子的id值
    print(ugclist['title'])#每首歌的名字
    title = ugclist['title']
    shareid = ugclist['shareid']
    data_url = "http://cgi.kg.qq.com/fcgi-bin/fcg_get_play_url?shareid=" + shareid #通过解析获取到的文件地址及拼接形式，也就是这个曲子的文件下载地址
    # 设置保存歌曲的路径，否则会保存到程序当前路径
    path = r'C:/Users/HUAWEI/Desktop/le'  # 路径前的r是保持字符串原始值的意思，就是说不对其中的符号进行转义
    file = path + title + '.m4a'
    is_set = os.path.exists(file)#这里做了简单的文件存在与否的判断，这样以后再执行，文件不会丢失或增多，或覆盖或重复爬取
    # 如果文件存在则跳过
    if is_set == False:
        request.urlretrieve(data_url, path + title + '.m4a')  # 使用request.urlretrieve直接将所有远程链接数据下载到本地

import urllib.request
import requests
import re

path = "C://Users//HUAWEI//Desktop//kgqq//"

url = "https://kg.qq.com/node/personal?uid=6a9d9a81222830833c"
#伪装浏览器用户
headers = {'User-Agent':'User-Agent:Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)'}
req = urllib.request.Request(url,headers=headers)

#执行请求获取响应信息
res = urllib.request.urlopen(req)

# 从响应对象中读取信息并解码
html = res.read().decode("utf-8")

# print(len(html))
#使用正则解析出歌曲链接
pat = '<a href="(.*?)" .*? target="_blank">(.*?)</a>'
dlist = re.findall(pat,html)

# 遍历输出结果
# for v in dlist:
#     print(v[1]+":"+v[0])

# 匹配歌曲链接
pat_music = 'http://[a-z][a-z].stream.kg.qq.com.*.m4a.*?"'
    
for url in dlist:
    music = urllib.request.Request(url[0],headers=headers)
    res = urllib.request.urlopen(music)
    music_html = res.read().decode("utf-8")
    mus = re.findall(pat_music,music_html)
    if mus:
        MP3 = requests.get(mus[0])
        with open(path+url[1]+".mp3","wb") as f:
            f.write(MP3.content)
            if MP3.content:
                print(url[1]+":"+url[0])
            else:
                print(url[1]+":"+url[0]+"write error!")