script to download audio clips from https://kg3.qq.com
tries to infer filename from title and falls back to using the song code.
this worked on january 8th, 2020; good luck getting it to work in the future!
Created
January 8, 2020 22:52
-
-
Save ohnx/f6a86591f90a8d4de8a06df8c515fe52 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const https = require('https'); | |
| const http = require('http'); | |
| const fs = require('fs'); | |
| // recommend only doing ~4-5 at a time max | |
| let i_start = 0, i_end = 4; | |
| let urls = [ | |
| ]; | |
| // part after https://kg3.qq.com/node/play?s= | |
| let codes = [ | |
| ]; | |
| let data = []; | |
| const playurl_regex = /playurl":"(http:\/\/...?.stream.kg.qq.com\/szkge-btfs\/[A-Za-z0-9?=&_.]+)"/g; | |
| const title_regex = /<title>(.*)- 全民K歌，KTV交友社区<\/title>/g; | |
| function download_file(src, dest, writeRaw) { | |
| let file = fs.createWriteStream(dest); | |
| if (writeRaw) { | |
| console.log('Saving raw HTML instead; find the player url yourself'); | |
| file.write(writeRaw); | |
| file.end(); | |
| return; | |
| } | |
| console.log(`Starting download of ${dest}`); | |
| http.get(src, function(res) { | |
| res.on('data', function(data) { | |
| file.write(data); | |
| }).on('end', function() { | |
| file.end(); | |
| console.log(`Finished download of ${dest}`); | |
| }); | |
| }); | |
| } | |
| urls.forEach((this_song, i) => { | |
| if (i < i_start || i > i_end) return; | |
| var this_song_id = codes[i]; | |
| data.push(''); | |
| https.get(this_song, { | |
| headers: { | |
| 'User-Agent': 'curl/7.64.0' // surprisingly, cURL as a user agent works... | |
| } | |
| }, (res) => { | |
| console.log(`${this_song_id} response code: ${res.statusCode}`); | |
| res.on('data', (c) => { | |
| data[i] += c; | |
| }); | |
| res.on('end', () => { | |
| // data is in data now | |
| var filename; | |
| for (let j = 0; j < 5; j++) { | |
| if (filename) break; | |
| title_regex.lastIndex = 0; | |
| filename = title_regex.exec(data[i]); | |
| } | |
| if (filename) {} | |
| else { | |
| console.log('for some reason ${this_song_id} failed to parse filename... oops!'); | |
| filename = [0, this_song_id]; | |
| } | |
| console.log(`${this_song_id} is ${filename[1]}.m4a`); | |
| var download_url; | |
| for (let j = 0; j < 5; j++) { | |
| if (download_url) break; | |
| playurl_regex.lastIndex = 0; | |
| download_url = playurl_regex.exec(data[i]); | |
| } | |
| if (filename && download_url) download_file(download_url[1], filename[1] + '.m4a'); | |
| else { | |
| console.log(`for some reason ${this_song_id} failed to parse download url... oops!`); | |
| download_file(null, this_song_id + '.html', data[i]); | |
| } | |
| }); | |
| }).on('error', (e) => { | |
| console.error(this_song + ': ' + e); | |
| }); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment