bilinote-cli 0.1.0__py3-none-any.whl

src/app/downloaders/base.py

@@ -0,0 +1,52 @@
+import enum
+
+from abc import ABC, abstractmethod
+from typing import Optional, Union
+
+from app.enmus.note_enums import DownloadQuality
+from app.models.notes_model import AudioDownloadResult
+from app.models.transcriber_model import TranscriptResult
+from os import getenv
+QUALITY_MAP = {
+    "fast": "32",
+    "medium": "64",
+    "slow": "128"
+}
+
+
+class Downloader(ABC):
+    def __init__(self):
+        #TODO 需要修改为可配置
+        self.quality = QUALITY_MAP.get('fast')
+        self.cache_data=getenv('DATA_DIR')
+
+    @abstractmethod
+    def download(self, video_url: str, output_dir: str = None,
+                 quality: DownloadQuality = "fast", need_video: Optional[bool] = False,
+                 skip_download: bool = False) -> AudioDownloadResult:
+        '''
+
+        :param need_video:
+        :param video_url: 资源链接
+        :param output_dir: 输出路径 默认根目录data
+        :param quality: 音频质量 fast | medium | slow
+        :return:返回一个 AudioDownloadResult 类
+        '''
+        pass
+
+    @staticmethod
+    def download_video(self, video_url: str,
+                       output_dir: Union[str, None] = None) -> str:
+        pass
+
+    def download_subtitles(self, video_url: str, output_dir: str = None,
+                           langs: list = None) -> Optional[TranscriptResult]:
+        '''
+        尝试获取平台字幕（人工字幕或自动生成字幕）
+
+        :param video_url: 视频链接
+        :param output_dir: 输出路径
+        :param langs: 优先语言列表，如 ['zh-Hans', 'zh', 'en']
+        :return: TranscriptResult 或 None（无字幕时）
+        '''
+        return None

src/app/downloaders/bilibili_downloader.py

@@ -0,0 +1,365 @@
+import os
+import json
+import logging
+import tempfile
+from abc import ABC
+from typing import Union, Optional, List
+from pathlib import Path
+
+import yt_dlp
+
+from app.downloaders.base import Downloader, DownloadQuality, QUALITY_MAP
+from app.models.notes_model import AudioDownloadResult
+from app.models.transcriber_model import TranscriptResult, TranscriptSegment
+from app.utils.path_helper import get_path_manager
+from app.utils.url_parser import extract_video_id
+from app.utils.cookie_helper import get_cookie
+
+logger = logging.getLogger(__name__)
+
+
+def _cookie_string_to_file(cookie_str: str, domain: str = ".bilibili.com") -> str:
+    """将 cookie 字符串转换为 Netscape 格式的临时文件，供 yt-dlp 使用"""
+    tmp_fd, tmp_path = tempfile.mkstemp(suffix=".txt", prefix="bili_cookie_")
+    # 使用一个足够远的未来时间戳作为 cookie 过期时间
+    expires = "2147483647"
+    with os.fdopen(tmp_fd, 'w', encoding='utf-8') as f:
+        f.write("# Netscape HTTP Cookie File\n")
+        for item in cookie_str.split(';'):
+            item = item.strip()
+            if '=' in item:
+                name, value = item.split('=', 1)
+                name = name.strip()
+                value = value.strip()
+                if name and value:
+                    f.write(f"{domain}\tTRUE\t/\tFALSE\t{expires}\t{name}\t{value}\n")
+    return tmp_path
+
+
+def _apply_bilibili_cookie(ydl_opts: dict):
+    """统一为 yt-dlp 选项添加 B站 cookie 支持"""
+    cookie_str = get_cookie('bilibili')
+    if cookie_str:
+        cookie_file = _cookie_string_to_file(cookie_str)
+        ydl_opts['cookiefile'] = cookie_file
+        return cookie_file
+    return None
+
+
+class BilibiliDownloader(Downloader, ABC):
+    def __init__(self):
+        super().__init__()
+
+    def download(
+        self,
+        video_url: str,
+        output_dir: Union[str, None] = None,
+        quality: DownloadQuality = "fast",
+        need_video: Optional[bool] = False,
+        skip_download: bool = False,
+    ) -> AudioDownloadResult:
+        if output_dir is None:
+            output_dir = get_path_manager().downloads_dir
+        os.makedirs(output_dir, exist_ok=True)
+
+        output_path = os.path.join(output_dir, "%(id)s.%(ext)s")
+
+        ydl_opts = {
+            'format': 'bestaudio[ext=m4a]/bestaudio/best',
+            'outtmpl': output_path,
+            'postprocessors': [
+                {
+                    'key': 'FFmpegExtractAudio',
+                    'preferredcodec': 'mp3',
+                    'preferredquality': '64',
+                }
+            ],
+            'noplaylist': True,
+            'quiet': False,
+            'http_headers': {
+                'Referer': 'https://www.bilibili.com',
+                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
+            },
+        }
+
+        cookie_file = _apply_bilibili_cookie(ydl_opts)
+
+        if skip_download:
+            ydl_opts['skip_download'] = True
+
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(video_url, download=not skip_download)
+            video_id = info.get("id")
+            title = info.get("title")
+            duration = info.get("duration", 0)
+            cover_url = info.get("thumbnail")
+            audio_path = os.path.join(output_dir, f"{video_id}.mp3")
+
+        # 清理临时 cookie 文件
+        if cookie_file and os.path.exists(cookie_file):
+            os.unlink(cookie_file)
+
+        if not skip_download and not os.path.exists(audio_path):
+            raise FileNotFoundError(f"音频下载失败，文件未生成: {audio_path}")
+
+        return AudioDownloadResult(
+            file_path=audio_path,
+            title=title,
+            duration=duration,
+            cover_url=cover_url,
+            platform="bilibili",
+            video_id=video_id,
+            raw_info=info,
+            video_path=None  # ❗音频下载不包含视频路径
+        )
+
+    def download_video(
+        self,
+        video_url: str,
+        output_dir: Union[str, None] = None,
+    ) -> str:
+        """
+        下载视频，返回视频文件路径
+        """
+
+        if output_dir is None:
+            output_dir = get_path_manager().downloads_dir
+        os.makedirs(output_dir, exist_ok=True)
+        print("video_url",video_url)
+        video_id=extract_video_id(video_url, "bilibili")
+        video_path = os.path.join(output_dir, f"{video_id}.mp4")
+        if os.path.exists(video_path):
+            return video_path
+
+        # 检查是否已经存在
+
+
+        output_path = os.path.join(output_dir, "%(id)s.%(ext)s")
+
+        ydl_opts = {
+            'format': 'bv*[ext=mp4]/bestvideo+bestaudio/best',
+            'outtmpl': output_path,
+            'noplaylist': True,
+            'quiet': False,
+            'merge_output_format': 'mp4',  # 确保合并成 mp4
+            'http_headers': {
+                'Referer': 'https://www.bilibili.com',
+                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
+            },
+        }
+
+        cookie_file = _apply_bilibili_cookie(ydl_opts)
+
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(video_url, download=True)
+            video_id = info.get("id")
+            video_path = os.path.join(output_dir, f"{video_id}.mp4")
+
+        # 清理临时 cookie 文件
+        if cookie_file and os.path.exists(cookie_file):
+            os.unlink(cookie_file)
+
+        if not os.path.exists(video_path):
+            raise FileNotFoundError(f"视频文件未找到: {video_path}")
+
+        return video_path
+
+    def delete_video(self, video_path: str) -> str:
+        """
+        删除视频文件
+        """
+        if os.path.exists(video_path):
+            os.remove(video_path)
+            return f"视频文件已删除: {video_path}"
+        else:
+            return f"视频文件未找到: {video_path}"
+
+    def download_subtitles(self, video_url: str, output_dir: str = None,
+                           langs: List[str] = None) -> Optional[TranscriptResult]:
+        """
+        尝试获取B站视频字幕
+
+        :param video_url: 视频链接
+        :param output_dir: 输出路径
+        :param langs: 优先语言列表
+        :return: TranscriptResult 或 None
+        """
+        if output_dir is None:
+            output_dir = get_path_manager().downloads_dir
+        os.makedirs(output_dir, exist_ok=True)
+
+        if langs is None:
+            langs = ['zh-Hans', 'zh', 'zh-CN', 'ai-zh', 'en', 'en-US']
+
+        video_id = extract_video_id(video_url, "bilibili")
+
+        ydl_opts = {
+            'writesubtitles': True,
+            'writeautomaticsub': True,
+            'subtitleslangs': langs,
+            'subtitlesformat': 'srt/json3/best',  # 支持多种格式
+            'skip_download': True,
+            'outtmpl': os.path.join(output_dir, f'{video_id}.%(ext)s'),
+            'quiet': True,
+            'http_headers': {
+                'Referer': 'https://www.bilibili.com',
+                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
+            },
+        }
+
+        cookie_file = _apply_bilibili_cookie(ydl_opts)
+
+        try:
+            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                # extract_info 不需要下载文件，与 skip_download 保持一致
+                info = ydl.extract_info(video_url, download=False)
+
+                # 查找下载的字幕文件
+                subtitles = info.get('requested_subtitles') or {}
+                if not subtitles:
+                    logger.info(f"B站视频 {video_id} 没有可用字幕")
+                    return None
+
+                # 按优先级查找字幕
+                detected_lang = None
+                sub_info = None
+                for lang in langs:
+                    if lang in subtitles:
+                        detected_lang = lang
+                        sub_info = subtitles[lang]
+                        break
+
+                # 如果按优先级没找到，取第一个可用的（排除弹幕）
+                if not detected_lang:
+                    for lang, info_item in subtitles.items():
+                        if lang != 'danmaku':  # 排除弹幕
+                            detected_lang = lang
+                            sub_info = info_item
+                            break
+
+                if not sub_info:
+                    logger.info(f"B站视频 {video_id} 没有可用字幕（排除弹幕）")
+                    return None
+
+                # 检查是否有内嵌数据（yt-dlp 有时直接返回字幕内容）
+                if 'data' in sub_info and sub_info['data']:
+                    logger.info(f"直接从返回数据解析字幕: {detected_lang}")
+                    return self._parse_srt_content(sub_info['data'], detected_lang)
+
+                # 查找字幕文件
+                ext = sub_info.get('ext', 'srt')
+                subtitle_file = os.path.join(output_dir, f"{video_id}.{detected_lang}.{ext}")
+
+                if not os.path.exists(subtitle_file):
+                    logger.info(f"字幕文件不存在: {subtitle_file}")
+                    return None
+
+                # 根据格式解析字幕文件
+                if ext == 'json3':
+                    return self._parse_json3_subtitle(subtitle_file, detected_lang)
+                else:
+                    with open(subtitle_file, 'r', encoding='utf-8') as f:
+                        return self._parse_srt_content(f.read(), detected_lang)
+
+        except Exception as e:
+            logger.warning(f"获取B站字幕失败: {e}")
+            return None
+        finally:
+            if cookie_file and os.path.exists(cookie_file):
+                os.unlink(cookie_file)
+
+    def _parse_srt_content(self, srt_content: str, language: str) -> Optional[TranscriptResult]:
+        """
+        解析 SRT 格式字幕内容
+
+        :param srt_content: SRT 字幕文本内容
+        :param language: 语言代码
+        :return: TranscriptResult
+        """
+        import re
+        try:
+            segments = []
+            # SRT 格式: 序号\n时间戳\n文本\n\n
+            pattern = r'(\d+)\n(\d{2}:\d{2}:\d{2},\d{3})\s*-->\s*(\d{2}:\d{2}:\d{2},\d{3})\n(.*?)(?=\n\n|\n\d+\n|$)'
+            matches = re.findall(pattern, srt_content, re.DOTALL)
+
+            for match in matches:
+                idx, start_time, end_time, text = match
+                text = text.strip()
+                if not text:
+                    continue
+
+                # 转换时间格式 00:00:00,000 -> 秒
+                def time_to_seconds(t):
+                    parts = t.replace(',', '.').split(':')
+                    return float(parts[0]) * 3600 + float(parts[1]) * 60 + float(parts[2])
+
+                segments.append(TranscriptSegment(
+                    start=time_to_seconds(start_time),
+                    end=time_to_seconds(end_time),
+                    text=text
+                ))
+
+            if not segments:
+                return None
+
+            full_text = ' '.join(seg.text for seg in segments)
+            logger.info(f"成功解析B站SRT字幕，共 {len(segments)} 段")
+            return TranscriptResult(
+                language=language,
+                full_text=full_text,
+                segments=segments,
+                raw={'source': 'bilibili_subtitle', 'format': 'srt'}
+            )
+
+        except Exception as e:
+            logger.warning(f"解析SRT字幕失败: {e}")
+            return None
+
+    def _parse_json3_subtitle(self, subtitle_file: str, language: str) -> Optional[TranscriptResult]:
+        """
+        解析 json3 格式字幕文件
+
+        :param subtitle_file: 字幕文件路径
+        :param language: 语言代码
+        :return: TranscriptResult
+        """
+        try:
+            with open(subtitle_file, 'r', encoding='utf-8') as f:
+                data = json.load(f)
+
+            segments = []
+            events = data.get('events', [])
+
+            for event in events:
+                # json3 格式中时间单位是毫秒
+                start_ms = event.get('tStartMs', 0)
+                duration_ms = event.get('dDurationMs', 0)
+
+                # 提取文本
+                segs = event.get('segs', [])
+                text = ''.join(seg.get('utf8', '') for seg in segs).strip()
+
+                if text:  # 只添加非空文本
+                    segments.append(TranscriptSegment(
+                        start=start_ms / 1000.0,
+                        end=(start_ms + duration_ms) / 1000.0,
+                        text=text
+                    ))
+
+            if not segments:
+                return None
+
+            full_text = ' '.join(seg.text for seg in segments)
+
+            logger.info(f"成功解析B站字幕，共 {len(segments)} 段")
+            return TranscriptResult(
+                language=language,
+                full_text=full_text,
+                segments=segments,
+                raw={'source': 'bilibili_subtitle', 'file': subtitle_file}
+            )
+
+        except Exception as e:
+            logger.warning(f"解析字幕文件失败: {e}")
+            return None

src/app/downloaders/common.py

@@ -0,0 +1 @@
+# def download():