diff --git a/爬虫/003_B站视频下载/BliBli.py b/爬虫/003_B站视频下载/BliBli.py deleted file mode 100644 index 13df6a3..0000000 --- a/爬虫/003_B站视频下载/BliBli.py +++ /dev/null @@ -1,349 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- -# ------------------------------------ -# Time : 2025/8/10 -# File : BliBli.py -# 脚本作用 : 获取B站视频 -# 项目名称 : -# ------------------------------------ - -import logging -import os -import re -import shutil -import time -from concurrent.futures import ThreadPoolExecutor -import requests -from moviepy import AudioFileClip, VideoFileClip -from requests.adapters import HTTPAdapter -from urllib3.util.retry import Retry - -# -------------------------- 配置参数（可自定义） -------------------------- -# 自定义存储路径（默认在当前目录下的download文件夹，可修改为绝对路径如"D:/B站视频"） -STORAGE_PATH = "E:/download/B站视频" -# 日志输出级别（INFO=基本信息，WARNING=仅警告和错误，ERROR=仅错误） -LOG_LEVEL = logging.WARNING -# 最大线程数（避免请求过于频繁） -MAX_THREADS = 3 -# 最大重试次数 -MAX_RETRY = 5 -# ------------------------------------------------------------------------- - -# 配置日志 -logging.basicConfig( - level=logging.INFO, - format='%(asctime)s - %(levelname)s - %(message)s', - handlers=[logging.FileHandler("bilibili.log"), logging.StreamHandler()] -) -logger = logging.getLogger(__name__) - -# 全局请求头 -headers = { - 'referer': 'https://www.bilibili.com/', - 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36', -} - - -def get_response(url, retry_times=3, timeout=15): - """获取HTTP响应，包含重试机制和错误处理""" - session = requests.Session() - retries = Retry( - total=retry_times, - backoff_factor=0.5, - status_forcelist=[500, 502, 503, 504, 429] - ) - session.mount('http://', HTTPAdapter(max_retries=retries)) - session.mount('https://', HTTPAdapter(max_retries=retries)) - - try: - response = session.get(url, headers=headers, timeout=timeout) - response.raise_for_status() - return response - except requests.exceptions.RequestException as e: - logger.error(f"请求失败: {url}（错误: {str(e)}）") - return None - - -def get_video_urls_advanced(bv_id, cid, page=1): - """增强版视频链接获取函数，支持新旧格式自动切换""" - try: - # 优先尝试新版DASH格式（视频音频分离） - url = f'https://api.bilibili.com/x/player/playurl?bvid={bv_id}&cid={cid}&qn=112&type=&otype=json' - response = get_response(url) - if not response: - logger.warning(f"尝试旧版格式获取链接: {bv_id}") - return get_old_format_urls(bv_id, cid, page) - - data = response.json() - if data.get('code') != 0: - logger.warning(f"新版格式错误，尝试旧版: {data.get('message')}") - return get_old_format_urls(bv_id, cid, page) - - dash_data = data.get('data', {}).get('dash', {}) - video_urls = dash_data.get('video', []) - audio_urls = dash_data.get('audio', []) - - if video_urls and audio_urls: - video_url = video_urls[0].get('backupUrl', [video_urls[0].get('url', '')])[0] - audio_url = audio_urls[0].get('backupUrl', [audio_urls[0].get('url', '')])[0] - return video_url, audio_url - - # DASH格式获取失败，尝试旧版格式 - #logger.warning(f"新版格式解析失败，切换旧版格式") - return get_old_format_urls(bv_id, cid, page) - - except Exception as e: - logger.error(f"链接获取异常，切换旧版: {str(e)}") - return get_old_format_urls(bv_id, cid, page) - - -def get_old_format_urls(bv_id, cid, page=1): - """获取旧版FLV格式视频链接（视频音频合并）""" - try: - url = f'https://api.bilibili.com/x/player/playurl?bvid={bv_id}&cid={cid}&qn=112&type=flv&otype=json' - response = get_response(url) - if not response: - logger.error(f"旧版格式请求失败: {bv_id}") - return None, None - - data = response.json() - if data.get('code') != 0: - logger.error(f"旧版格式API错误: {data.get('message')}") - return None, None - - durl = data.get('data', {}).get('durl', [{}])[0].get('url', '') - if not durl: - logger.error(f"旧版格式链接为空: {bv_id}") - return None, None - - return durl, None # 旧版无独立音频链接 - except Exception as e: - logger.error(f"旧版格式处理异常: {str(e)}") - return None, None - - -def download_video_audio_and_combine_compatible(video_url, audio_url, video_path, audio_path, output_path): - """兼容新旧格式的下载合并函数""" - try: - # 下载视频 - print(f"正在下载视频: {os.path.basename(output_path)}") # 控制台显示进度 - video_resp = get_response(video_url) - if not video_resp: - logger.error(f"视频下载失败: {os.path.basename(output_path)}") - return False - - with open(video_path, 'wb') as f: - f.write(video_resp.content) - - # 处理旧版格式(无独立音频) - if not audio_url: - shutil.copy2(video_path, output_path) - print(f"下载完成: {os.path.basename(output_path)}") - return True - - # 下载音频(新版格式) - audio_resp = get_response(audio_url) - if not audio_resp: - logger.warning(f"音频下载失败，仅保存视频: {os.path.basename(output_path)}") - shutil.copy2(video_path, output_path) - return True - - with open(audio_path, 'wb') as f: - f.write(audio_resp.content) - - # 合并视频和音频 - try: - video = VideoFileClip(video_path) - audio = AudioFileClip(audio_path) - final_video = video.set_audio(audio) - final_video.write_videofile(output_path, codec="libx264", audio_codec="aac") - print(f"合并完成: {os.path.basename(output_path)}") - return True - except Exception as e: - logger.warning(f"合并失败，保存原始视频: {str(e)}") - shutil.copy2(video_path, output_path) - return True - finally: - # 清理临时文件 - if os.path.exists(audio_path): - os.remove(audio_path) - - except Exception as e: - logger.error(f"处理失败: {str(e)}") - return False - finally: - if os.path.exists(video_path): - os.remove(video_path) - - -def add_copyright_headers(): - """添加版权敏感内容所需的请求头（可选）""" - global headers - headers.update({ - 'Referer': 'https://www.bilibili.com/cheese/', - 'Origin': 'https://www.bilibili.com', - # 如需下载会员内容，可添加Cookie（格式: 'Cookie': 'SESSDATA=xxx; bili_jct=xxx;'） - # 'Cookie': 'your_cookie_here' - }) - - -def create_directory(path): - """创建目录（支持自定义存储路径）""" - dir_path = os.path.dirname(path) - try: - os.makedirs(dir_path, exist_ok=True) - return True - except Exception as e: - logger.error(f"目录创建失败: {dir_path}（错误: {str(e)}）") - return False - - -def download_part_video_advanced(part_info, main_title): - """增强版分P下载函数""" - bv_id = part_info['bv'] - page = part_info['page'] - part_title = part_info['title'] - cid = part_info.get('cid') - - # 生成文件路径（基于自定义存储路径） - safe_title = re.sub(r'[\\/:*?"<>|]', '_', part_title) - main_dir = os.path.join(STORAGE_PATH, re.sub(r'[\\/:*?"<>|]', '_', main_title)) - video_path = os.path.join(main_dir, f'{safe_title}_video.mp4') # 临时视频文件 - audio_path = os.path.join(main_dir, f'{safe_title}_audio.mp3') # 临时音频文件 - output_path = os.path.join(main_dir, f'{safe_title}.mp4') # 最终输出路径 - - # 创建目录（包括临时文件夹） - if not create_directory(video_path) or not create_directory(output_path): - logger.error(f"跳过下载: {part_title}（目录创建失败）") - return False - - # 重试机制 - for retry in range(MAX_RETRY): - wait_time = 2 ** retry # 指数退避（1s, 2s, 4s...） - if retry > 0: - print(f"重试 {retry}/{MAX_RETRY}（等待{wait_time}秒）: {part_title}") - time.sleep(wait_time) - - try: - # 获取视频链接 - video_url, audio_url = get_video_urls_advanced(bv_id, cid, page) - if not video_url: - continue - - # 针对版权敏感内容添加额外头 - if "会员" in part_title or "加密" in part_title: - add_copyright_headers() - - # 下载并合并 - if download_video_audio_and_combine_compatible(video_url, audio_url, video_path, audio_path, output_path): - return True - - except Exception as e: - logger.error(f"下载异常: {str(e)}") - continue - - logger.error(f"下载失败: {part_title}（已达最大重试次数）") - return False - - -def parse_video_info(bv_id): - """解析视频基本信息和分P信息""" - base_url = f'https://www.bilibili.com/video/{bv_id}' - response = get_response(base_url) - if not response: - logger.error(f"无法访问视频页面: {base_url}") - return None, None - - html = response.text - try: - # 提取视频标题 - title_match = re.search(r'

= 50 - - -if __name__ == '__main__': - # 示例：替换为需要下载的BV号 - bv_id = 'BV1xe4y1s7Uq' # 可修改为目标视频的BV号 - download_bilibili_video(bv_id) \ No newline at end of file diff --git a/爬虫/003_B站视频下载/README.md b/爬虫/003_B站视频下载/README.md deleted file mode 100644 index 2c93eec..0000000 --- a/爬虫/003_B站视频下载/README.md +++ /dev/null @@ -1,12 +0,0 @@ -# tools - -#### 介绍 -个人脚本存放 - -#### 软件架构 -软件架构说明 - -#### 使用说明 -获取bilibili上面免费视频 - - diff --git a/爬虫/003_B站视频下载/bilibili.log b/爬虫/003_B站视频下载/bilibili.log deleted file mode 100644 index 10dd350..0000000 --- a/爬虫/003_B站视频下载/bilibili.log +++ /dev/null @@ -1,5 +0,0 @@ -2025-08-10 19:20:08,907 - WARNING - °ʽʧܣлɰʽ -2025-08-10 19:20:08,928 - WARNING - °ʽʧܣлɰʽ -2025-08-10 19:20:08,930 - WARNING - °ʽʧܣлɰʽ -2025-08-10 19:20:16,658 - WARNING - °ʽʧܣлɰʽ -2025-08-10 19:20:16,677 - WARNING - °ʽʧܣлɰʽ