update

getAudio.py

@@ -0,0 +1,94 @@
+import json
+import time
+
+import requests
+from IPython.display import Audio,display
+from pydub import AudioSegment
+import os
+import random
+
+with open('audio.json', encoding="UTF-8") as f:
+    audios = json.load(f)
+# print(type(audios[1]))  # Output: dict
+# TODO: 优化代码
+
+course_id =  str(audios[1]['course_id'])
+os.makedirs(course_id, exist_ok=True)
+
+# 遍历
+audio_list = []
+for audio in audios:
+    # t = random.randint(1, 10)
+    # time.sleep(1)
+    category = audio['category']
+    # requests.adapters.DEFAULT_RETRIES = 100
+    # 获取音频内容
+    i = 1
+    while(i >= 1):
+        try:
+            if category == "PLAIN_AUDIO":
+                url = audio['attachment']['url']
+                # print(url)
+                audio = requests.get(url)
+                # print(audio.status_code)
+                # display(Audio(audio.content))
+                audio_list.append(audio.content)
+                # print(audio['attachment']['url'])
+                # filename = os.path.basename(url)
+                # with open(os.path.join(course_id, filename), 'wb') as file:
+                #     file.write(audio.content)
+            # 获取文本笔记
+            elif category == "PLAIN_TEXT":
+                text = audio['text']
+                print(text)
+                with open(os.path.join(course_id, course_id + 'note.txt'), 'a') as file:
+                        file.write(text)
+                        file.write("\n")
+            # 获取其他可下载附件
+            elif category != "MESSAGE_RECALL":
+                # print(audio['category'])
+                if 'attachment' in audio:
+                    url = audio['attachment']['url']
+                    # print(audio['attachment']['url'])
+                    attachment = requests.get(url)
+                    filename = os.path.basename(url)
+                    with open(os.path.join(course_id, filename), 'wb') as file:
+                        file.write(attachment.content)
+            # 获取其他内容
+            else:
+                print(audio['category'])
+                if 'attachment' in audio:
+                    print(audio['attachment']['url'])
+            i = 0
+        except:
+            i += 1
+            print("get file failed")
+            if 'attachment' in audio:
+                    print(audio['attachment']['url'])
+
+# 处理获取所有音频文件
+audio_seg_list = []
+for i in audio_list:
+    with open('temp.mp3', 'wb') as file:
+        file.write(i)
+    audio_part = AudioSegment.from_mp3('temp.mp3')
+    # audio_part = AudioSegment.from_mp3(i)
+    audio_seg_list.append(audio_part)
+
+# print(len(audio_seg_list))
+x = sum(audio_seg_list)
+
+# 递归求和
+# def sumOfList(list, size):
+#    if (size == 0):
+#      return 0
+#    else:
+#      return list[size - 1] + sumOfList(list, size - 1)
+#
+# total = sumOfList(list1, len(list1))
+
+audio_name = course_id + '/' + course_id + '.mp3'
+
+x.export(audio_name, format="mp3")
+
+display(Audio(audio_name))