diff --git a/yhk.ipynb b/yhk.ipynb new file mode 100644 index 0000000..7b33cb7 --- /dev/null +++ b/yhk.ipynb @@ -0,0 +1,240 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "开始下载第1首音乐：勇气.mp3\n", + "\n", + "开始下载第2首音乐：可惜不是你.mp3\n", + "\n", + "开始下载第3首音乐：宁夏.mp3\n", + "\n", + "开始下载第4首音乐：接受.mp3\n", + "\n", + "开始下载第5首音乐：分手快乐.mp3\n", + "\n", + "开始下载第6首音乐：明明很爱你.mp3\n", + "\n", + "开始下载第7首音乐：爱久见人心.mp3\n", + "\n", + "开始下载第8首音乐：夜夜夜夜.mp3\n", + "\n", + "开始下载第9首音乐：可以的话.mp3\n", + "\n", + "开始下载第10首音乐：丝路.mp3\n", + "\n", + "开始下载第11首音乐：会过去的.mp3\n", + "\n", + "开始下载第12首音乐：爱你不是两三天.mp3\n", + "\n", + "开始下载第13首音乐：如果有一天.mp3\n", + "\n", + "开始下载第14首音乐：偶阵雨.mp3\n", + "\n", + "开始下载第15首音乐：无条件为你.mp3\n", + "\n", + "开始下载第16首音乐：慢慢来比较快.mp3\n", + "\n", + "开始下载第17首音乐：听不到.mp3\n", + "\n", + "开始下载第18首音乐：燕尾蝶.mp3\n", + "\n", + "开始下载第19首音乐：昨天.mp3\n", + "\n", + "开始下载第20首音乐：Fly Away.mp3\n", + "\n", + "开始下载第21首音乐：孤单北半球 (live).mp3\n", + "\n", + "开始下载第22首音乐：小手拉大手(Live).mp3\n", + "\n", + "开始下载第23首音乐：我喜欢.mp3\n", + "\n", + "开始下载第24首音乐：飘洋过海来看你.mp3\n", + "\n", + "开始下载第25首音乐：没有人像你.mp3\n", + "\n", + "开始下载第26首音乐：不想睡.mp3\n", + "\n", + "开始下载第27首音乐：情歌没有告诉你.mp3\n", + "\n", + "开始下载第28首音乐：大地之歌.mp3\n", + "\n", + "开始下载第29首音乐：瘦瘦的.mp3\n", + "\n", + "开始下载第30首音乐：还是好朋友.mp3\n", + "\n", + "开始下载第31首音乐：你会不会.mp3\n", + "\n", + "开始下载第32首音乐：一路两个人.mp3\n", + "\n", + "开始下载第33首音乐：一夜长大.mp3\n", + "\n", + "开始下载第34首音乐：她.mp3\n", + "\n", + "开始下载第35首音乐：第三者.mp3\n", + "\n", + "开始下载第36首音乐：最想环游的世界.mp3\n", + "\n", + "开始下载第37首音乐：美丽人生.mp3\n", + "\n", + "开始下载第38首音乐：纯真.mp3\n", + "\n", + "开始下载第39首音乐：我不害怕.mp3\n", + "\n", + "开始下载第40首音乐：彩虹.mp3\n", + "\n", + "开始下载第41首音乐：想都没想过.mp3\n", + "\n", + "开始下载第42首音乐：最快乐那一年.mp3\n", + "\n", + "开始下载第43首音乐：我就知道那是爱.mp3\n", + "\n", + "开始下载第44首音乐：漂洋过海来看你(Live).mp3\n", + "\n", + "开始下载第45首音乐：让爱转动整个宇宙.mp3\n", + "\n", + "开始下载第46首音乐：我还记得.mp3\n", + "\n", + "开始下载第47首音乐：有你在.mp3\n", + "\n", + "开始下载第48首音乐：向左转向右转.mp3\n", + "\n", + "开始下载第49首音乐：明天我要嫁给你了(Live).mp3\n", + "\n", + "开始下载第50首音乐：恋着多喜欢.mp3\n", + "\n", + "50首全部歌曲已经下载完毕！\n" + ] + } + ], + "source": [ + "import os\n", + "import re\n", + "import json\n", + "import requests\n", + "from lxml import etree\n", + "\n", + "\n", + "def download_songs(url=None):\n", + " if url is None:\n", + " url = 'https://music.163.com/#/playlist?id=2384642500'\n", + "\n", + " url = url.replace('/#', '').replace('https', 'http') # 对字符串进行去空格和转协议处理\n", + " # 网易云音乐外链url接口：http://music.163.com/song/media/outer/url?id=xxxx\n", + " out_link = 'http://music.163.com/song/media/outer/url?id='\n", + " # 请求头\n", + " headers = {\n", + " 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',\n", + " 'Referer': 'https://music.163.com/',\n", + " 'Host': 'music.163.com'\n", + " }\n", + " # 请求页面的源码\n", + " res = requests.get(url=url, headers=headers).text\n", + "\n", + " tree = etree.HTML(res)\n", + " # 音乐列表\n", + " song_list = tree.xpath('//ul[@class=\"f-hide\"]/li/a')\n", + " # 如果是歌手页面\n", + " artist_name_tree = tree.xpath('//h2[@id=\"artist-name\"]/text()')\n", + " artist_name = str(artist_name_tree[0]) if artist_name_tree else None\n", + "\n", + " # 如果是歌单页面：\n", + " #song_list_tree = tree.xpath('//*[@id=\"m-playlist\"]/div[1]/div/div/div[2]/div[2]/div/div[1]/table/tbody')\n", + " song_list_name_tree = tree.xpath('//h2[contains(@class,\"f-ff2\")]/text()')\n", + " song_list_name = str(song_list_name_tree[0]) if song_list_name_tree else None\n", + "\n", + " # 设置音乐下载的文件夹为歌手名字或歌单名\n", + " folder = './' + artist_name if artist_name else './' + song_list_name\n", + "\n", + " if not os.path.exists(folder):\n", + " os.mkdir(folder)\n", + "\n", + " for i, s in enumerate(song_list):\n", + " href = str(s.xpath('./@href')[0])\n", + " song_id = href.split('=')[-1]\n", + " src = out_link + song_id # 拼接获取音乐真实的src资源值\n", + " title = str(s.xpath('./text()')[0]) # 音乐的名字\n", + " filename = title + '.mp3'\n", + " filepath = folder + '/' + filename\n", + " print('开始下载第{}首音乐：{}\\n'.format(i + 1, filename))\n", + "\n", + " try: # 下载音乐\n", + " #下载歌词\n", + " #download_lyric(title, song_id)\n", + "\n", + " data = requests.get(src).content # 音乐的二进制数据\n", + "\n", + " with open(filepath, 'wb') as f:\n", + " f.write(data)\n", + " except Exception as e:\n", + " print(e)\n", + "\n", + " print('{}首全部歌曲已经下载完毕！'.format(len(song_list)))\n", + "\n", + "\n", + "def download_lyric(song_name, song_id):\n", + " url = 'http://music.163.com/api/song/lyric?id={}&lv=-1&kv=-1&tv=-1'.format(song_id)\n", + " # 请求头\n", + " headers = {\n", + " 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',\n", + " 'Referer': 'https://music.163.com/',\n", + " 'Host': 'music.163.com'\n", + " # 'Origin': 'https://music.163.com'\n", + " }\n", + " # 请求页面的源码\n", + " res = requests.get(url=url, headers=headers).text\n", + " json_obj = json.loads(res)\n", + " lyric = json_obj['lrc']['lyric']\n", + " reg = re.compile(r'\\[.*\\]')\n", + " lrc_text = re.sub(reg, '', lyric).strip()\n", + "\n", + " print(song_name, lrc_text)\n", + "\n", + "\n", + "\n", + "\n", + "if __name__ == '__main__':\n", + " #music_list = 'https://music.163.com/#/playlist?id=2384642500' #歌曲清单\n", + " music_list = 'https://music.163.com/#/artist?id=8325' #歌手排行榜\n", + " # music_list = 'https://music.163.com/#/search/m/?order=hot&cat=全部&limit=435&offset=435&s=梁静茹' #搜索列表\n", + " download_songs(music_list)\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.1" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}