import re
import threading

import requests
from bs4 import BeautifulSoup
import json
import os


def fixname(filename):  # 用正则表达式去除windows下的特殊字符，这些字符不能用在文件名
    intab = r'[*?/\|.:><""'']'
    filename = re.sub(intab, " ", filename)
    return filename


def mk_filename(filename):  # 检查文件夹是否存在，如果不存在就新建文件夹
    filename1 = filename + "\\"
    if not os.path.exists(filename1):
        os.mkdir(filename1)
    return filename1


def music_data_list(url):  # 提取music数据信息
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36"
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find("div", class_="g-wrap12")
    name = bsre.find("textarea")
    return json.loads(name.text)


def pyer_music_data_list(url):  # 提取歌手页面music数据信息
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36"
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find("div", class_="f-cb")
    name = bsre.find("textarea")
    return json.loads(name.text)


def mu_download(url, filename):  # 下载排行榜歌曲
    filename1 = mk_filename(filename)
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36"
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    data2 = music_data_list(url)
    for i in range(len(data2)):
        mu_name = fixname(data2[i]["name"])
        mu_id = data2[i]["id"]
        mu_play = data2[i]["artists"][0]["name"]
        # print("music:", mu_name, "ID:", mu_id, "play:", mu_play)
        i_url = 'http://music.163.com/song/media/outer/url?id=' + str(mu_id)
        mu_data = requests.get(url=i_url, headers=headers).content
        try:
            with open(filename1 + str(mu_name) + "-" + str(mu_play) + '.mp3', mode='wb') as f:
                f.write(mu_data)
                print(mu_name + "-" + mu_play + '.mp3', '下载成功')
            with open('log\\log.txt', "a", encoding="utf-8") as f:
                f.write(mu_name + "---" + mu_play + '.mp3' + '下载成功\n')
        except:
            print(mu_name + "-" + mu_play + '.mp3', '下载失败')
            with open('log\\log.txt', "a", encoding="utf-8") as f:
                f.write(mu_name + "-" + mu_play + '.mp3' + '下载失败5\n')


def mu_player_download(url, path, filename):  # 下载歌手歌曲
    filename1 = mk_filename(path + filename)
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36"
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    data2 = pyer_music_data_list(url)
    for i in range(len(data2)):
        mu_name = fixname(data2[i]["name"])
        mu_id = data2[i]["id"]
        mu_play = data2[i]["artists"][0]["name"]
        if not os.path.exists(filename1 + str(mu_name) + "-" + str(mu_play) + '.mp3'):
            # print("music:", mu_name, "ID:", mu_id, "play:", mu_play)
            i_url = 'http://music.163.com/song/media/outer/url?id=' + str(mu_id)
            mu_data = requests.get(url=i_url, headers=headers).content
            try:
                with open(filename1 + str(mu_name) + "-" + str(mu_play) + '.mp3', mode='wb') as f:
                    f.write(mu_data)
                    print(mu_name + "-" + mu_play + '.mp3', '下载成功')
                with open('log\\log.txt', "a", encoding="utf-8") as f:
                    f.write(mu_name + "---" + mu_play + '.mp3' + '下载成功\n')
            except:
                print(mu_name + "-" + mu_play + '.mp3', '下载失败')
                with open('log\\log.txt', "a", encoding="utf-8") as f:
                    f.write(mu_name + "-" + mu_play + '.mp3' + '下载失败5\n')
        else:
            print(filename1 + str(mu_name) + "-" + str(mu_play) + '.mp3', "----------------------------这首歌已经存在了\n")

def top_data_list(url):             #处理排行榜数据
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36"
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find_all("p", class_="name")
    top_re = re.findall("href\=\"\/discover\/toplist\?id\=(.*?)\"\>(.*?)\<\/a\>", str(bsre))
    url_list = []
    for i in top_re:
        url_t = "https://music.163.com/discover/toplist?id=" + i[0]
        url_list.append((url_t, i[1]))
    return url_list


def mc_data_list(url):              #处理歌手分类
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36" 
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find_all("div", class_="g-wrap4 n-sgernav")
    mc_re = re.findall("href=\"\/discover\/artist\/cat\?id\=(.*?)\"\>(.*?)\<\/a\>", str(bsre))
    url_list = []
    for i in mc_re:
        url_t = "https://music.163.com/discover/artist/cat?id=" + i[0]
        url_list.append((url_t, i[1]))
    #print(url_list)
    return url_list


def az_data_list(url):              #处理歌手排序数据
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36" 
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find_all("ul", class_="n-ltlst f-cb")
    az_re = re.findall("\<a class=\"\" href=\"\/discover\/artist\/cat\?id=.*?&amp;initial=(.*?)\"", str(bsre))
    #print(az_re)
    #mc = mc_data_list("https://music.163.com/discover/artist")
    url_list = []
    for i in az_re:
        # url_t = "https://music.163.com/discover/artist/cat?id=1001&initial=0" + i[0]
        url_t = str(url) + "&initial=" + str(i)
        url_list.append(url_t)
    #print(url_list)
    return url_list


def player_data_list(url):          #处理歌手ID
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36" 
                      " (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"
    }
    req = requests.get(url=url, headers=headers)
    bs = BeautifulSoup(req.text, "html.parser")
    bsre = bs.find_all("div", class_="m-sgerlist")
    mc_re = re.findall("\<a class=\"nm nm-icn f-thide s-fc0\" href=\".*?\/artist\?id=(.*?)\" title=\"(.*?)\"\>(.*?)\<\/a\>", str(bsre))
    url_list = []
    for i in mc_re:
        url_t = "https://music.163.com/artist?id=" + i[0]
        url_list.append((url_t, i[2]))
    #print(url_list)
    return url_list


def music_pyer_data_list():
    pass


def top_down():
    url_top = "https://music.163.com/discover/toplist?id=5453912201"
    aaa = top_data_list(url_top)
    print(len(top_data_list(url_top)))
    a = 0
    for i in aaa:
        a = a + 1
        print(a, i[1])
    for i in aaa:
        mu_download(i[0], i[1])


def pyer_down():
    mc_list = mc_data_list("https://music.163.com/discover/artist")
    print(mc_list)
    try:
        for i in mc_list:

                az_list = az_data_list(i[0])

                mu_path = mk_filename(fixname(i[1]))

                try:
                    for q in az_list:
                        play_list = player_data_list(q)
                        print(play_list)
                        try:
                            threads = []
                            for w in play_list:
                               # if not os.path.exists(mu_path+w[1]):
                                    threads.append(threading.Thread(target=mu_player_download, args=(w[0], mu_path, w[1])))
                                    # print(mu_path + w[1])
                                    # mu_player_download(w[0], mu_path, w[1])
                                    # print(w[0], w[1])
                              #  else:
                               #     print(mu_path + w[1])
                               #     continue
                            for thread in threads:
                                thread.start()
                            for thread in threads:
                                thread.join()
                            print(threads)
                        except:
                            print("三级出错")
                except:
                    print("二级出错")

    except:
        print("顶级出错")



def main():
    pyer_down()


if __name__ == '__main__':
    main()
    #top_down()
    #www = mc_data_list("https://music.163.com/discover/artist")
    #az_data_list("https://music.163.com/discover/artist/cat?id=1001")
    #for i in www:
        #qqq = az_data_list(i[0])
        #print(qqq)
   # player_data_list("https://music.163.com/discover/artist/cat?id=1001&initial=67")