更新QQ音乐/QQ音乐.py

QQ音乐/QQ音乐.py

+#Time：2020/04/26
+#author：渔戈
+import requests
+import json
+import re
+import os
+import time
+# 词云
+import jieba.analyse #结巴分析，#pip install jieba
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+from wordcloud import ImageColorGenerator # 获取图片像素值
+from matplotlib.image import imread #读取图片 #pip install matplotlib
+
+
+
+headers = {
+    "origin": "https://y.qq.com",
+    "pragma": "no-cache",
+    "referer": "https://y.qq.com/portal/search.html",
+    "sec-fetch-mode": "cors",
+    "sec-fetch-site": "same-site",
+    "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36",
+}
+
+datas = []
+
+
+'''读取音乐id'''
+def start_url():
+    global path
+    global name
+    global singer
+    num = 20
+    name = input('请输入歌名：')
+    path = f'F:\\接单\\qq音乐\\{name}'
+    if not os.path.isdir(path):  # 判断有没有这个路径
+        os.mkdir(path)
+    url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp?p=1&n=%d&w=%s' % (num, name)
+    # 搜索音乐
+    response = requests.get(url, headers=headers)
+    html = response.text
+    html = html[9:]
+    html = html[:-1]
+    '''获取音乐id'''
+    js = json.loads(html)
+    songlist = js['data']['song']['list']
+    for song in songlist:
+        songid = song['songid'] #id
+        songmid = song['songmid'] #mid
+        names = song['songname']#歌曲名
+        singer = song['singer'][0]['name_hilight'] #演唱者
+        print('歌名:',names,'演唱者:',singer,'歌曲id:',songid,'歌曲mid:',songmid)
+
+'''获取音乐链接'''
+def getVkey():
+    items = []
+    global name
+    global songid
+    guid = '2240306200'
+    uin = '123456789'
+    print('开始获取资源')
+    ''' 获取vkey，和purl'''
+    names = name
+    songid =input('请输入你所要下载歌曲的id：')
+    songmid = input('请输入所要下载歌曲的mid：')
+    items.append([names,songid,songmid])
+    keyUrl = 'https://u.y.qq.com/cgi-bin/musicu.fcg?&data={"req":{"param":{"guid":" %s"}},"req_0":{"module":"vkey.GetVkeyServer","method":"CgiGetVkey","param":{"guid":"%s","songmid":["%s"],"uin":"%s"}},"comm":{"uin":%s}}'%(guid,guid,songmid,uin,uin)
+    response = requests.get(keyUrl, headers=headers)
+    if response.status_code == 200:
+        keyjs = json.loads(response.text)
+        '''获取链接：如C400004WZXOc20rcug.m4a?guid=2240306200&vkey=8E83E45B2B4D236F6758F8814E43446CABC516DC057C0F95EAA46637FD2FA536465922C416CDB9E619FBF8BCF42642184AE8BA8B2C4A9BF1&uin=6273&fromtag=66'''
+        purl = keyjs['req_0']['data']['midurlinfo'][0]['purl']
+        # 拼凑资源url
+        url = 'http://dl.stream.qqmusic.qq.com/' + purl
+        datas.append((name, url))  # 存储音乐名称和链接
+        print('获取的音乐链接如下:')
+        print(url)
+        print('资源地址获取成功')
+    return items
+
+'''下载音乐'''
+def downloadMusic():
+    global path
+    path =path
+    print('正在下载音乐，请骚等...')
+    for i in datas:
+        url = i[1]
+        response = requests.get(url,headers=headers)
+        music = response.content
+        name = i[0] + '.mp3'
+        # print(name)#查看文件名
+        with open(path+f'\\{name}', 'wb') as f:
+            f.write(music)
+            print('下载成功')
+            f.close()
+
+
+'''获取评论信息'''
+def get_music_comment(items):
+    global name
+    global path
+    path=path
+    name =name
+    comment_list = []
+    page = int(input('请输入所要获取的评论页数:'))
+    for i in range(0,page):
+        try:
+            time.sleep(2)
+            for item in items:
+                topid = item[1]        # id号
+                mid = item[2]          # mid号
+                header = {
+                    "referer": f"https://y.qq.com/n/yqq/song/{mid}.html",       # referer需要变换mid参数  不然无返回数据
+                    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.106 Safari/537.36",
+                }
+                url = "https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg?g_tk_new_20200303=744858319&g_tk=744858319&loginUin=123456789&hostUin=0&format=json&inCharset=utf8&outCharset=GB2312&notice=0&platform=yqq.json&needNewCode=0&cid=205360772&reqtype=2&biztype=1&topid={}&cmd=8&needmusiccrit=0&pagenum={}&pagesize=25&lasthotcommentid=song_237270257_1152921504841432379_1574944849_1152921504647110724_1587615596&domain=qq.com&ct=24&cv=10101010" .format(topid,i)
+                response = requests.get(url=url,headers=header)
+                print('正在获取第{}页链接'.format(i+1))
+                print(response.url)
+                datas = response.json()['comment']['commentlist']
+                for data in datas:
+                    nick = data['nick']  # 评论者
+                    comments = data['rootcommentcontent']  # 评论信息
+                    com_data = nick + ':' + comments
+                    comment_list.append(com_data)
+                    print(nick,':',comments)
+                    with open(path + f'\\{name}评论.txt', 'a', encoding='utf-8') as f:
+                        f.write(com_data)  # 写入评论信息
+        except Exception as e:
+            continue
+    f.close()
+    return comment_list
+
+
+'''词云图'''
+def wordcloud(comment_list):
+    print('正在生成词云图:')
+    global name
+    global path
+    path =path
+    name =name
+    comment = ''.join(comment_list)     # 将列表变成字符串数据
+
+    back_img = imread("小老虎.jpg")  # 读取图片
+    img_colors = ImageColorGenerator(back_img)  # 生成图片的像素值
+
+    tags = jieba.analyse.extract_tags(comment, topK=1000, withWeight=True, allowPOS=())  # 使用结巴分析提取标签
+    data = {item[0]: item[1] for item in tags}  # tags是数组形式，把数组转为词频字典
+
+    word_cloud = WordCloud(font_path="c:\windows\Fonts\simhei.ttf",  # 字体，本电脑c盘下的黑体，这样才能显示中文
+                           background_color="white",  # 图片的背景颜色
+                           max_words=1000,  # 字体个数，不超过上面选取的个数
+                           max_font_size=100,  # 字体大小
+                           width=1920,  # 图片像素宽
+                           mask=back_img,  # 使用图片蒙板，上面读取图片的像素
+                           height=1080).generate_from_frequencies(data)  # 传入上面的词频结果
+
+    wc_color = word_cloud.recolor(color_func=img_colors)  # 替换默认的字体颜色
+
+    plt.figure(figsize=(12, 12))  # 创建一个图形实例，设置画布大小
+    plt.imshow(word_cloud, interpolation='bilinear')  # 插值='双线性'
+    plt.axis("off")  # 不显示坐标尺寸
+    word_cloud.to_file(path+f'\\{name}.png')  # 保存图片
+    plt.show()
+    print('词云图生成成功！')
+
+'''歌词'''
+def lyric(items):
+    for i in items:
+        id = str(i[1])  # id   用于添加进歌词请求参数中
+        name = i[0]  # 歌名
+        mid = i[2] #mid
+        # print(id,song_name)
+        headers = {
+            "origin": "https://y.qq.com",
+            "pragma": "no-cache",
+            "referer": f"https://y.qq.com/n/yqq/song/{mid}.html",
+            "sec-fetch-mode": "cors",
+            "sec-fetch-site": "same-site",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36",
+        }
+        url = 'https://c.y.qq.com/lyric/fcgi-bin/fcg_query_lyric_yqq.fcg?nobase64=1&musicid={}&-=jsonp1&g_tk_new_20200303=744858319&g_tk=744858319&loginUin=123456789&hostUin=0&format=json&inCharset=utf8&outCharset=utf-8&notice=0&platform=yqq.json&needNewCode=0'.format(id)
+        response = requests.get(url, headers=headers)
+        try:
+            lyric = response.json()['lyric']  # 歌词
+            lyric = re.sub('\[.*?\]', '\n', lyric)  # re.sub替换掉多余的列表数据
+            lyric = re.sub('[ 
G.E.M./T-Ma ]', '', lyric).strip()  # 替换掉多余字符，去掉空白行
+            print('已成功获取到音乐歌词：')
+            print(lyric)
+            with open(path + f'\\{name}' + '.txt', 'w', encoding='utf-8') as f:
+                f.write(lyric)  # 写入歌词
+                f.close()
+        except Exception as e:
+            print('歌词获取失败：{}'.format(e))
+if __name__ == '__main__':
+    start_url()
+    items=getVkey()
+    downloadMusic()
+    comment_list=get_music_comment(items)
+    wordcloud(comment_list)
+    lyric(items)