Update app.py

app.py

@@ -1,24 +1,61 @@
 from bs4 import BeautifulSoup
 from flask import Flask, request, jsonify
 import requests
-
-from flask_cors import CORS 
+import re
+import json
+from flask_cors import CORS
 from apscheduler.schedulers.background import BackgroundScheduler
 from datetime import datetime
 
 app = Flask(__name__)
-CORS(app)  
+CORS(app)
 
-# 缓存数据及更新时间
+# Cache data and update time
 cached_results_soaring = []
 cached_results_hot = []
 cached_results_newSongs = []
 cached_results_popular = []
 last_update_time = None
 
-def song(url):
-    """从 QQ 音乐榜单页面爬取歌曲信息"""
+def parse_time(time_str):
+    if not time_str:
+        return "00:00.000"
+    
+    time_str = time_str.strip('[]')
+    time_parts = time_str.split(':')
+    if len(time_parts) == 2:
+        minutes = time_parts[0]
+        seconds = time_parts[1]
+        if '.' not in seconds:
+            seconds = seconds + '.000'
+        elif len(seconds.split('.')[1]) == 2:
+            seconds = seconds + '0'
+        return f"{minutes}:{seconds}"
+    
+    return "00:00.000"
+
+def convert_lyrics(input_str):
+    """Convert lyrics format"""
+    lyrics = []
+    lines = input_str.split('\n')
+    
+    for line in lines:
+        if not line.strip():
+            continue
+            
+        match = re.match(r'\[(\d{2}:\d{2}\.\d{2})\](.*)', line)
+        if match:
+            time_str, content = match.groups()
+            formatted_time = parse_time(time_str)
+            lyrics.append({
+                "name": content.strip(),
+                "time": formatted_time
+            })
     
+    return {"lyric": lyrics}
+
+def song(url):
+    """Crawl song information from QQ Music rankings page"""
     headers = {
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
         "Referer": "https://y.qq.com/",
@@ -27,35 +64,24 @@ def song(url):
 
     results = []
     try:
-        
-        # 发送请求
         response = requests.get(url, headers=headers)
         response.encoding = 'utf-8'
-        
-        # 使用 BeautifulSoup 解析页面
         soup = BeautifulSoup(response.text, 'html.parser')
-        
-        # 查找所有歌曲列表项
         song_items = soup.select("ul.songlist__list li")
 
         for item in song_items[:10]:
             try:
-                # 提取歌曲名称
                 song_name_span = item.select_one("span.songlist__songname_txt")
                 song_name = song_name_span.text.strip()
 
-                # 提取歌手名称
                 artist_div = item.select_one("div.songlist__artist")
                 artist_name = artist_div.text.strip()
 
-                # 提取 mid
                 song_link = song_name_span.find('a', class_='')
-                
                 mid = "default_mid"
                 if song_link and song_link.get('href'):
                     mid = song_link['href'].split('/')[-1]
 
-                # 提取图片链接
                 img_link = song_name_span.find('a', class_='songlist__cover')
                 if img_link and img_link.get('href'):
                     imgsrc = img_link['href'].split('/')[-1]
@@ -74,58 +100,50 @@ def song(url):
                         "muId": 1
                     })
             except Exception as e:
-                print(f"处理歌曲项时出错: {e}")
+                print(f"Error processing song item: {e}")
                 continue
 
     except Exception as e:
-        print(f"爬取过程中出错: {e}")
+        print(f"Error during crawling: {e}")
         return []
 
-    # 更新缓存数据及更新时间
     if results:
-        print(f"数据已更新：{last_update_time}")   
+        print(f"Data updated: {last_update_time}")   
     return results
 
-
 def schedule_music_fetch():
-    """设置每天早上 8 点定时任务"""
+    """Schedule daily task at 8 AM"""
     scheduler = BackgroundScheduler()
-    
 
     def run_tasks():
-        global cached_results_soaring, cached_results_hot, cached_results_newSongs,  cached_results_popular, last_update_time
-        # 依次运行每个任务
+        global cached_results_soaring, cached_results_hot, cached_results_newSongs, cached_results_popular, last_update_time
         cached_results_soaring = song("https://y.qq.com/n/ryqq/toplist/62")
         cached_results_hot = song("https://y.qq.com/n/ryqq/toplist/26")
         cached_results_newSongs = song("https://y.qq.com/n/ryqq/toplist/27")
         cached_results_popular = song("https://y.qq.com/n/ryqq/toplist/4")
-        last_update_time =  datetime.now()
-
+        last_update_time = datetime.now()
 
-    # 设置定时任务，每天 8 点执行 run_tasks
     scheduler.add_job(run_tasks, 'cron', hour=8, minute=0)
-
     scheduler.start()
-    print("定时任务已启动，爬取时间为每天早上 8 点。")
+    print("Scheduled task started, crawling time is 8 AM daily.")
 
 @app.route('/star')
 def star():
-    global cached_results_soaring, cached_results_hot, cached_results_newSongs,  cached_results_popular, last_update_time
+    global cached_results_soaring, cached_results_hot, cached_results_newSongs, cached_results_popular, last_update_time
     cached_results_soaring = song("https://y.qq.com/n/ryqq/toplist/62")
     cached_results_hot = song("https://y.qq.com/n/ryqq/toplist/26")
     cached_results_newSongs = song("https://y.qq.com/n/ryqq/toplist/27")
     cached_results_popular = song("https://y.qq.com/n/ryqq/toplist/4")
-    last_update_time =  datetime.now()
+    last_update_time = datetime.now()
     return jsonify({
-        "data": "数据已更新",
-        "updata time": last_update_time
+        "data": "Data updated",
+        "update_time": last_update_time
     })
 
 @app.route('/fetch_music_soaring', methods=['GET'])
 def fetch_music_route_soaring():
-    """提供缓存的 QQ 音乐榜单数据"""
     if not cached_results_soaring:
-        return jsonify({"message": "数据尚未准备好，请先访问/star 更新数据"}), 503
+        return jsonify({"message": "Data not ready, please visit /star first to update data"}), 503
     
     return jsonify({
         "last_update_time": last_update_time.strftime("%Y-%m-%d %H:%M:%S"),
@@ -134,9 +152,8 @@ def fetch_music_route_soaring():
 
 @app.route('/fetch_music_hot', methods=['GET'])
 def fetch_music_route_hot():
-    """提供缓存的 QQ 音乐榜单数据"""
     if not cached_results_hot:
-        return jsonify({"message": "数据尚未准备好，请先访问/star 更新数据"}), 503
+        return jsonify({"message": "Data not ready, please visit /star first to update data"}), 503
     
     return jsonify({
         "last_update_time": last_update_time.strftime("%Y-%m-%d %H:%M:%S"),
@@ -145,9 +162,8 @@ def fetch_music_route_hot():
 
 @app.route('/fetch_music_newSongs', methods=['GET'])
 def fetch_music_route_newSongs():
-    """提供缓存的 QQ 音乐榜单数据"""
     if not cached_results_newSongs:
-        return jsonify({"message": "数据尚未准备好，请先访问/star 更新数据"}), 503
+        return jsonify({"message": "Data not ready, please visit /star first to update data"}), 503
     
     return jsonify({
         "last_update_time": last_update_time.strftime("%Y-%m-%d %H:%M:%S"),
@@ -156,15 +172,41 @@ def fetch_music_route_newSongs():
 
 @app.route('/fetch_music_popular', methods=['GET'])
 def fetch_music_route_popular():
-    """提供缓存的 QQ 音乐榜单数据"""
     if not cached_results_popular:
-        return jsonify({"message": "数据尚未准备好，请先访问/star 更新数据"}), 503
+        return jsonify({"message": "Data not ready, please visit /star first to update data"}), 503
     
     return jsonify({
         "last_update_time": last_update_time.strftime("%Y-%m-%d %H:%M:%S"),
         "data": cached_results_popular
     })
+
+@app.route('/get_lyrics', methods=['GET'])
+def get_lyrics():
+    mid = request.args.get('mid')
+    if not mid:
+        return jsonify({"error": "Missing mid parameter"}), 400
+
+    target_url = f"https://c.y.qq.com/lyric/fcgi-bin/fcg_query_lyric_new.fcg?songmid={mid}&format=json&nobase64=1"
+    headers = {
+        "Referer": "https://y.qq.com/portal/player.html"
+    }
+
+    try:
+        response = requests.get(target_url, headers=headers)
+        response.raise_for_status()
+        data = response.json()
+        matched_lyrics = data.get('lyric')
+        
+        if not matched_lyrics:
+            return jsonify({"error": f"No lyrics found for mid: {mid}"}), 404
+            
+        result_json = convert_lyrics(matched_lyrics)
+        return jsonify(result_json)
+    except requests.RequestException as e:
+        return jsonify({"error": "Failed to get lyrics", "details": str(e)}), 500
+    except (KeyError, ValueError):
+        return jsonify({"error": "Unexpected data format from server"}), 500
+
 if __name__ == '__main__':
-    # 启动 Flask 应用时初始化定时任务
     schedule_music_fetch()
-    app.run(debug=True,host='0.0.0.0',port=5734)
+    app.run(debug=True, host='0.0.0.0', port=5734)