# 主程序
import re
import time
 
from lxml import html
from tqdm import tqdm
 
from down_music import *
from music_info import *
 
etree = html.etree
baseurl_search = r'https://www.gequbao.com/s/'
baseurl_homepage = r'https://www.gequbao.com'
headers = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"}
 
 
def get_search_result(keyword):
    """获取原始搜索结果文本"""
    url_search = baseurl_search + keyword
    response = requests.get(url_search, headers=headers)
    if response.status_code == 200:
        return response.text
    else:
        print('响应状态码错误')
 
 
def get_urls(html_str: str):
    """利用正则提取网页链接"""
    pattern = r'<a href="(/music/\d+)" target'
    short_urls = re.findall(pattern, html_str)  # 短链接/music/402856
    urls = [baseurl_homepage + i for i in short_urls]  # 拼接完整链接
    return urls
 
 
def get_music_info(urls: list):
    """获取链接对应的链接字典"""
    url_info_dict = {}  # {url:{获取的info}...}
    for url in tqdm(urls, bar_format='{l_bar}{bar}| {n_fmt}/{total_fmt}'):
        spider = MusicInfo(url)
        info_dict = spider.get_info()
        url_info_dict[url] = info_dict
        time.sleep(0.2)
 
    return url_info_dict
 
 
def show_music_list(url_info_dict: dict):
    """显示带编号的歌曲列表"""
    for index, info_dict in enumerate(url_info_dict.values(), start=1):
        music_name = info_dict['music_name']
        print(index, music_name)
 
 
def down_music(url, info_dict):
    """下载歌曲"""
    spider = DownMusic(info_dict)
    # 检查是否正确下载，如果错误则重新获取链接
    if spider.is_error():
        print('下载链接已失效，尝试重新获取')
        re_spider = MusicInfo(url)
        re_info_dict = re_spider.get_info()
        return down_music(url, re_info_dict)
    else:
        print('完成下载')
 
 
def main():
    while True:
        keyword = input('输入歌名/歌手，回车后查询：').strip()
        html_str = get_search_result(keyword)
        urls = get_urls(html_str)
        url_info_dict = get_music_info(urls)
        show_music_list(url_info_dict)
 
        while True:
            number = int(input('输入歌曲编号，回车后下载歌曲（输入0返回搜索栏）：').strip())
            if number == 0:
                break
            select_url, select_info_dict = list(url_info_dict.items())[number - 1]
            down_music(select_url, select_info_dict)
 
 
if __name__ == '__main__':
    main()

# 该模块用于获取歌曲的封面、文件名、下载链接等信息
 
from playwright.sync_api import sync_playwright
 
 
class MusicInfo:
    def __init__(self, music_page: str):
        """
        :param music_page: str类型，歌曲页面链接
        """
        self._music_download_link = ''  # 歌曲下载链接
        self._cover_download_link = ''  # 封面下载链接
        self._lrc_download_link = ''  # 歌词下载链接
        self._music_name = ''  # 歌曲名
 
        self._goto_page(music_page)
 
    def _goto_page(self, music_page: str):
        """
        :param music_page: str类型，歌曲页面链接
        """
        with sync_playwright() as p:
            browser = p.chromium.launch(headless=True)
            page = browser.new_page()
            page.on('response', self._on_response)  # 响应请求
            page.goto(music_page)
            page.wait_for_load_state('networkidle')
            html = page.content()  # 获取页面源码
            browser.close()
 
        self._get_music_name_and_lrc(html)
 
    def _on_response(self, response):
        state = response.status  # 状态码
        url = response.url  # 链接
        # print(f'Statue {state}: {url}')
        # 酷我接口
        if 'kuwo' in url and '.mp3' in url:  # 提取歌曲下载链接
            self._music_download_link = url
        elif 'kuwo' in url and '.jpg' in url:  # 提取封面
            self._cover_download_link = url
        # 网易云接口
        elif 'music.126' in url and '.mp3' in url:  # 提取歌曲下载链接
            self._music_download_link = url
        elif 'music.126' in url and'.jpg' in url:  # 提取封面
            self._cover_download_link = url
 
 
    def _get_music_name_and_lrc(self, html: str):
        """获取歌曲文件名"""
        html_lines = html.split('\n')
        for line in html_lines:
            # print(f'Line: {line}')
            if 'description' in line:  # 提取歌曲名称
                # <meta name="description" content="青花瓷-周杰伦.mp3免费在线下载播放,歌曲宝在线音乐搜索
                split1 = line.find('content=')
                split2 = line.find('.mp3')
                music_name = line[split1 + len('content=') + 1:split2]
                self._music_name = music_name
 
            elif 'btn-download-lrc' in line and 'href' in line:  # 提取歌词
                # <a id="btn-download-lrc" href="/download/lrc/1655094" class="btn btn-primary"
                split1 = line.find('href=')
                split2 = line.find(' class')
                short_lrc_url = line[split1 + len('href=') + 1:split2 - 1]
                lrc_download_link = 'https://www.gequbao.com' + short_lrc_url
                self._lrc_download_link = lrc_download_link
 
    def get_info(self):
        """返回信息"""
        info_dict = {
            'music_download_link': self._music_download_link,
            'cover_download_link': self._cover_download_link,
            'lrc_download_link': self._lrc_download_link,
            'music_name': self._music_name
        }
 
        return info_dict

# 该模块用于获取歌曲的封面、文件名、下载链接等信息
import os
 
import requests
from mutagen.id3 import ID3, APIC, USLT
 
 
class DownMusic:
    """下载歌曲"""
 
    def __init__(self, info_dict: dict):
        self._music_download_link = info_dict['music_download_link']
        self._cover_download_link = info_dict['cover_download_link']
        self._lrc_download_link = info_dict['lrc_download_link']
        self._music_name = info_dict['music_name']
 
        if self._music_download_link:  # 如果没有获取到歌曲链接，则不进行下一步
            result = self._down_music()  # 歌曲链接有有效期，过期后无法下载文件
            if result:
                self._is_error = False
                self._down_lrc()
                self._down_cover()
 
                self._join_music_metadata()
                self._delete_useless_file()
            else:
                self._is_error = True
        else:
            self._is_error = True
 
    def is_error(self):
        """测试运行是否出错"""
        return self._is_error
 
    def _down_music(self):
        """下载歌曲"""
        filename = self._music_name + '.mp3'
        result = self._download_file(self._music_download_link, filename)
        return result
 
    def _down_lrc(self):
        """下载歌词"""
        filename = self._music_name + '.lrc'
        self._download_file(self._lrc_download_link, filename)
 
    def _down_cover(self):
        """下载封面"""
        filename = self._music_name + '.jpg'
        self._download_file(self._cover_download_link, filename)
 
    def _join_music_metadata(self):
        """拼合歌曲文件"""
        file_music = self._music_name + '.mp3'
        file_lrc = self._music_name + '.lrc'
        file_cover = self._music_name + '.jpg'
 
        audio = ID3(file_music)
 
        # 添加封面
        with open(file_cover, 'rb') as f:
            cover = f.read()
        audio['APIC'] = APIC(
            encoding=3,  # utf-8
            mime='image/jpeg',  # image/jpeg或image/png
            type=3,  # cover image
            desc=u'Cover',
            data=cover
        )
 
        # 添加歌词
        with open(file_lrc, 'r', encoding='utf-8') as f:
            lyrics = f.read()
        audio['USLT'] = USLT(
            encoding=3,  # utf-8
            lang='chi',  # 歌词语言
            desc=u'Lyrics',
            text=lyrics
        )
 
        audio.save()
 
    def _delete_useless_file(self):
        """合并后删除无用文件"""
        file_lrc = self._music_name + '.lrc'
        file_cover = self._music_name + '.jpg'
 
        os.remove(file_lrc)
        os.remove(file_cover)
 
    @staticmethod
    def _download_file(url, filename):
        headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"
        }
        response = requests.get(url, headers=headers)
        with open(filename, 'wb') as f:
            f.write(response.content)
 
        if os.path.getsize(filename):
            return True
        else:
            return False