爬取音频文件

courses/the truth of wealth/get_course_ids.py

@@ -0,0 +1,18 @@
+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)

courses/the truth of wealth/parse_course.py

@@ -0,0 +1,91 @@
+import json
+from pathlib import Path
+
+import requests
+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()
+        # 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'])
+        return ids
+
+
+# 通过request来爬取课程信息json数据
+def request_date(course_id, request_token):
+    url = 'https://bandu-api.songy.info/v2/courses/' + str(course_id) + '?expand=contents'
+    headers = {"Authorization": "Bearer " + request_token}
+    course_json = requests.get(url, headers=headers)
+    return course_json.content
+
+
+# 下载MP3文件并按顺序合并
+def download_mp3(url, filename):
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(filename, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+    else:
+        print(f"Failed to download {url}, status code {response.status_code}")
+
+
+# 合并下载的MP3文件
+def merge_mp3_files(mp3_files, output_filename):
+    audio_segments = []
+    for file in mp3_files:
+        audio = AudioSegment.from_file(file)
+        audio_segments.append(audio)
+
+    # 合并音频
+    merged_audio = AudioSegment.empty()
+    for audio_segment in audio_segments:
+        merged_audio += audio_segment
+
+    # 导出合并后的音频
+    merged_audio.export(output_filename, format="mp3")
+
+
+def get_audio(audio_data):
+    # 解析JSON数据
+    data = json.loads(audio_data)
+
+    # 提取MP3链接
+    mp3_urls = [item["attachment"]["raw_url"] for item in data["data"]["course_contents"] if
+                item["category"] == "audio"]
+
+    # 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")
+    temp_mp3_files = [Path(f"{idx}.mp3") for idx in range(len(mp3_urls))]
+
+    # 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)
+
+    # 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.")
+
+
+if __name__ == '__main__':
+    ids = get_course_id('course_data.json')
+    token = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhdWQiOiIxMDAwMDgzNDciLCJleHAiOjE3MTkxODk0ODQsImp0aSI6IjU3ZTJhMzdmLTMyZGEtNGQ2My1hZjQxLTY5NTRlNmU1OTg2MiIsImlhdCI6MTcxNjUxMTA4NCwiaXNzIjoiYXBwdXNlciIsInVpZCI6ImJlMmViOGIyLTFhOTItNGVmMC05ZDAwLTA1YTlkN2E2OWRiMiIsInNjaGVtZSI6Imp3dGhzIiwic2lkIjoiMWI4ZjE1ZTItYjQ5ZC00MmRmLWEwNDUtZmQxYTUwNzI5ZjkxIn0.IO7C2gtsi8lMdrOgWGNuxK-t2zzmDPvmI4BqISHeZEI"
+    json_data = request_date(ids[0], token)
+    get_audio(json_data)

requirements.txt

@@ -1,2 +1,3 @@
 requests~=2.31.0
-ipython~=8.24.0
+ipython~=8.24.0
+Scrapy~=2.11.2