change file save path

courses/Attachment.py

@@ -0,0 +1,10 @@
+class Attachment:
+    def __init__(self, attachment_id, course_id, name, content, url):
+        self.id = attachment_id
+        self.course_id = course_id
+        self.name = name
+        self.content = content
+        self.url = url
+
+    def __repr__(self):
+        return f"Attachment(id={self.id}, course_id={self.course_id}, name={self.name}, url={self.url})"

courses/Course.py

@@ -0,0 +1,27 @@
+from courses.Attachment import Attachment
+
+
+class Course:
+    def __init__(self, course_id, title, attachments=None):
+        self.id = course_id
+        self.title = title
+        self.attachments = attachments if attachments else []
+
+    def add_attachment(self, attachment):
+        self.attachments.append(attachment)
+
+    def __repr__(self):
+        return f"Course(id={self.id}, title={self.title}, attachments={self.attachments})"
+
+
+# 使用示例
+# 创建附件实例
+attachment1 = Attachment(attachment_id=1, course_id=101, name='Lesson 1', url='http://example.com/lesson1.mp3')
+attachment2 = Attachment(attachment_id=2, course_id=101, name='Lesson 2', url='http://example.com/lesson2.mp3')
+
+# 创建课程实例，并添加附件
+course = Course(course_id=101, title='Introduction to Python')
+course.add_attachment(attachment1)
+course.add_attachment(attachment2)
+
+print(course)

courses/parse_course.py

@@ -1,4 +1,6 @@
 import json
+import logging
+import os
 from pathlib import Path
 
 import requests
@@ -7,19 +9,16 @@ from pydub import AudioSegment
 
 def get_course_id(date_file_path):
     with open(date_file_path, encoding="UTF-8") as file:
-        # courses = json.load(f)
-        json_data = file.read()
+        course_json_data = file.read()
         # 解析JSON数据
-        data = json.loads(json_data)
-
+        data = json.loads(course_json_data)
         # 初始化一个空数组来存储id值
-        ids = []
-
+        course_ids = []
         # 遍历items列表
         for item in data['data']['items']:
             # 提取id并添加到数组中
-            ids.append(item['id'])
-        return ids
+            course_ids.append(item['id'])
+        return course_ids
 
 
 # 通过request来爬取课程信息json数据
@@ -68,24 +67,32 @@ def get_audio(audio_data):
     # 准备下载和合并MP3文件
     output_title = data["data"]["title"].replace(".", "_").replace("/", "_")  # 替换文件名中不允许的字符
     output_filename = Path(f"{output_title}.mp3")
+    save_file_path = os.path.join(output_title, output_filename)
     temp_mp3_files = [Path(f"{idx}.mp3") for idx in range(len(mp3_urls))]
 
+    # 创建对应title的文件夹
+    if not os.path.exists(output_title):
+        os.makedirs(output_title)
+        logging.info("Folder created")
+    else:
+        logging.info("Folder already exists")
+
     # 下载每个MP3文件
     for url, filename in zip(mp3_urls, temp_mp3_files):
         download_mp3(url, filename)
 
     # 合并MP3文件
-    merge_mp3_files(temp_mp3_files, output_filename)
+    merge_mp3_files(temp_mp3_files, save_file_path)
 
     # 清理临时文件
     for file in temp_mp3_files:
         file.unlink()
 
-    print(f"All MP3 files have been downloaded, merged into {output_filename}, and temporary files have been removed.")
+    logging.info(f"All MP3 files have been downloaded, merged into {output_filename}, and temporary files have been removed.")
 
 
 if __name__ == '__main__':
-    ids = get_course_id('course_data.json')
+    ids = get_course_id('all/course.json')
     token = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhdWQiOiIxMDAwMDgzNDciLCJleHAiOjE3MTkxODk0ODQsImp0aSI6IjU3ZTJhMzdmLTMyZGEtNGQ2My1hZjQxLTY5NTRlNmU1OTg2MiIsImlhdCI6MTcxNjUxMTA4NCwiaXNzIjoiYXBwdXNlciIsInVpZCI6ImJlMmViOGIyLTFhOTItNGVmMC05ZDAwLTA1YTlkN2E2OWRiMiIsInNjaGVtZSI6Imp3dGhzIiwic2lkIjoiMWI4ZjE1ZTItYjQ5ZC00MmRmLWEwNDUtZmQxYTUwNzI5ZjkxIn0.IO7C2gtsi8lMdrOgWGNuxK-t2zzmDPvmI4BqISHeZEI"
     json_data = request_date(ids[0], token)
     get_audio(json_data)

courses/the truth of wealth/get_course_ids.py

@@ -1,18 +0,0 @@
-import json
-
-with open('course_data.json', encoding="UTF-8") as file:
-    # courses = json.load(f)
-    json_data = file.read()
-    # 解析JSON数据
-    data = json.loads(json_data)
-
-    # 初始化一个空数组来存储id值
-    ids = []
-
-    # 遍历items列表
-    for item in data['data']['items']:
-        # 提取id并添加到数组中
-        ids.append(item['id'])
-
-    # 打印结果
-    print(ids)

requirements.txt

@@ -1,3 +1,4 @@
-requests~=2.31.0
+requests>=2.31.0
 ipython~=8.24.0
-Scrapy~=2.11.2
+Scrapy~=2.11.2
+pydub~=0.25.1