butterbot-python 3.1.0.dev1__py3-none-any.whl

butterbot/sources/bilibili/data/dto/dynamic_dto.py

@@ -0,0 +1,276 @@
+import json
+from logging import getLogger
+from typing import Any, ClassVar, Optional
+
+from butterbot.core.data import BaseDataModel
+
+_log = getLogger("DynamicDTO")
+
+
+class AuthorDto(BaseDataModel):
+    """
+    作者信息DTO
+    """
+
+    uid: int  # UP主UID
+    name: str  # UP主昵称
+    face: str  # UP主头像URL
+
+
+class StatDto(BaseDataModel):
+    """
+    动态统计信息DTO
+    """
+
+    comment_count: int = 0  # 评论数
+    like_count: int = 0  # 点赞数
+    forward_count: int = 0  # 转发数
+
+
+class VideoDto(BaseDataModel):
+    """
+    视频信息DTO
+    """
+
+    av_id: str  # 视频AV号
+    bv_id: str  # 视频BV号
+    title: str  # 视频标题
+    cover: str  # 视频封面
+    desc: str  # 视频简介
+    duration_text: str  # 视频时长
+    play_count: str  # 播放数
+    danmaku_count: str  # 弹幕数
+    dynamic_text: str = ""  # 动态文本
+
+
+class MusicDto(BaseDataModel):
+    """
+    音乐信息DTO
+    """
+
+    music_id: str  # 音乐ID
+    title: str  # 音乐标题
+    cover: str  # 音乐封面
+    label: str  # 音乐标签（作者/歌手）
+    dynamic_text: str = ""  # 动态文本
+
+
+class ArticleDto(BaseDataModel):
+    """
+    专栏信息DTO
+    """
+
+    title: str  # 专栏标题
+    summary: str  # 专栏摘要
+    has_more: bool  # 是否有更多内容
+    id: int
+
+
+class LiveRcmdDto(BaseDataModel):
+    """
+    直播推荐信息DTO
+    """
+
+    room_id: int  # 直播间ID
+    live_status: int  # 直播状态 1:直播中
+    title: str  # 直播间标题
+    cover: str  # 直播间封面
+    online: int  # 在线人数
+    area_id: int  # 直播分区ID
+    area_name: str  # 直播分区
+    parent_area_id: int  # 直播父分区ID
+    parent_area_name: str  # 直播父分区
+    live_start_time: int  # 开播时间戳
+    watched_num: int | None = None  # 观看人数
+    switch: bool | None = None  # 观看榜开关
+    text_small: str | None = None  # 小文本
+    text_large: str | None = None  # 大文本
+
+
+class DynamicDTO(BaseDataModel):
+    """
+    动态消息DTO
+    """
+
+    discriminator_value: ClassVar[str] = "dynamic"  # 数据类型标识
+
+    dynamic_id: str  # 动态ID
+    dynamic_type: str  # 动态类型
+    visible: bool  # 动态显示状态(false时被折叠)
+    pub_time: str  # 发布时间
+    pub_ts: int  # 发布时间戳
+    author: AuthorDto  # 作者信息
+    tag: str | None = None  # 标签（如置顶）
+    text: str | None = None  # 文字内容
+    pics_url: tuple[str, ...] | None = None  # 图片列表
+    stat: StatDto | None = None  # 统计信息
+    video: VideoDto | None = None  # 视频信息
+    music: MusicDto | None = None  # 音乐信息
+    article: ArticleDto | None = None  # 专栏信息
+    live_rcmd: LiveRcmdDto | None = None  # 直播推荐信息
+    forward_orig: Optional["DynamicDTO"] = None  # 转发的原动态
+
+    @classmethod
+    def from_raw(cls, data: dict[Any, Any] | None) -> "DynamicDTO | None":
+        """
+        从原始API数据构造DTO对象
+        """
+        if data is None:
+            return None
+        try:
+            # 基础信息
+            dynamic_id = data.get("id_str", "")
+            dynamic_type = data.get("type", "")
+            visible = data.get("visible", True)
+            modules = data.get("modules", {})
+            author_info = modules.get("module_author", {})
+            pub_time = author_info.get("pub_time", "")
+            pub_ts = author_info.get("pub_ts", 0)
+
+            # 动态内容
+            text = None
+            pics_url = None
+            video = None
+            music = None
+            article = None
+            live_rcmd = None
+
+            module_dynamic = modules.get("module_dynamic", {})
+            major = module_dynamic.get("major", {})
+
+            # 作者信息
+            author = {
+                "uid": author_info.get("mid", 0),
+                "name": author_info.get("name", ""),
+                "face": author_info.get("face", ""),
+            }
+
+            # 统计信息
+            stat = None
+            stat_info = modules.get("module_stat")
+            if stat_info:
+                stat = {
+                    "comment_count": stat_info.get("comment", {}).get("count", 0),
+                    "like_count": stat_info.get("like", {}).get("count", 0),
+                    "forward_count": stat_info.get("forward", {}).get("count", 0),
+                }
+
+            # 标签（如置顶）
+            tag = None
+            if modules.get("module_tag"):
+                tag = modules["module_tag"].get("text")
+
+            # 解析文字和图片（DYNAMIC_TYPE_WORD, DYNAMIC_TYPE_DRAW）
+            if dynamic_type in ["DYNAMIC_TYPE_WORD", "DYNAMIC_TYPE_DRAW"]:
+                opus = major.get("opus", {})
+                summary = opus.get("summary", {})
+                text = summary.get("text", "")
+                pics = opus.get("pics", [])
+                if pics:
+                    pics_url = tuple(pic.get("url", "") for pic in pics)
+
+            # 解析视频信息
+            elif dynamic_type == "DYNAMIC_TYPE_AV":
+                archive = major.get("archive", {})
+                desc_info = module_dynamic.get("desc", {})
+                stat_info_video = archive.get("stat", {})
+                video = {
+                    "av_id": archive.get("aid", ""),
+                    "bv_id": archive.get("bvid", ""),
+                    "title": archive.get("title", ""),
+                    "cover": archive.get("cover", ""),
+                    "desc": archive.get("desc", ""),
+                    "duration_text": archive.get("duration_text", ""),
+                    "dynamic_text": desc_info.get("text", "") if desc_info else "",
+                    "play_count": stat_info_video.get("play"),
+                    "danmaku_count": stat_info_video.get("danmaku"),
+                }
+
+            # 解析音乐信息
+            elif dynamic_type == "DYNAMIC_TYPE_MUSIC":
+                music_info = major.get("music", {})
+                desc_info = module_dynamic.get("desc", {})
+                music = {
+                    "music_id": str(music_info.get("id", "")),
+                    "title": music_info.get("title", ""),
+                    "cover": music_info.get("cover", ""),
+                    "label": music_info.get("label", ""),
+                    "dynamic_text": desc_info.get("text", "") if desc_info else "",
+                }
+
+            # 解析专栏信息
+            elif dynamic_type == "DYNAMIC_TYPE_ARTICLE":
+                opus = major.get("opus", {})
+                summary_info = opus.get("summary", {})
+                article = {
+                    "title": opus.get("title", ""),
+                    "summary": summary_info.get("text", ""),
+                    "has_more": summary_info.get("has_more", False),
+                    "id": int(dynamic_id) if dynamic_id else 0,
+                }
+
+            # 解析直播推荐信息
+            elif dynamic_type == "DYNAMIC_TYPE_LIVE_RCMD":
+                live_rcmd_content = major.get("live_rcmd", {}).get("content", "{}")
+                live_data = json.loads(live_rcmd_content)
+                live_play_info = live_data.get("live_play_info", {})
+                watched_show = live_play_info.get("watched_show", {})
+                live_rcmd = {
+                    "room_id": live_play_info.get("room_id", 0),
+                    "live_status": live_play_info.get("live_status", 0),
+                    "title": live_play_info.get("title", ""),
+                    "cover": live_play_info.get("cover", ""),
+                    "online": live_play_info.get("online", 0),
+                    "area_id": live_play_info.get("area_id", 0),
+                    "area_name": live_play_info.get("area_name", ""),
+                    "parent_area_id": live_play_info.get("parent_area_id", 0),
+                    "parent_area_name": live_play_info.get("parent_area_name", ""),
+                    "live_start_time": live_play_info.get("live_start_time", 0),
+                    "watched_num": watched_show.get("num"),
+                    "switch": watched_show.get("switch"),
+                    "text_small": watched_show.get("text_small"),
+                    "text_large": watched_show.get("text_large"),
+                }
+
+            # 解析转发信息
+            forward_orig = None
+            if dynamic_type == "DYNAMIC_TYPE_FORWARD":
+                orig_data = data.get("orig")
+                if orig_data:
+                    forward_orig = cls.from_raw(orig_data)
+
+            # 构造标准化字典后使用model_validate
+            normalized_data = {
+                "dynamic_id": dynamic_id,
+                "dynamic_type": dynamic_type,
+                "visible": visible,
+                "pub_ts": pub_ts,
+                "pub_time": pub_time,
+                "author": author,
+                "stat": stat,
+                "tag": tag,
+                "text": text,
+                "pics_url": pics_url,
+                "video": video,
+                "music": music,
+                "article": article,
+                "live_rcmd": live_rcmd,
+                "forward_orig": forward_orig,
+            }
+
+            return cls.model_validate(normalized_data)
+
+        except Exception as e:
+            _log.error("解析动态数据失败: %s", e, exc_info=True)
+            return None
+
+    @classmethod
+    def from_list(cls, data_dict: list[dict[Any, Any]]) -> "list[DynamicDTO | None]":
+        """
+        从动态列表数据构造DTO对象列表
+        """
+        try:
+            return [cls.from_raw(data) for data in data_dict]
+        except Exception as e:
+            _log.error("解析动态数据列表失败: %s", e, exc_info=True)
+            return [None]

butterbot/sources/bilibili/data/dto/live_room_dto.py

@@ -0,0 +1,169 @@
+import re
+from html import unescape
+from logging import getLogger
+from typing import Any, ClassVar
+
+from butterbot.core.data import BaseDataModel
+
+_log = getLogger("LiveRoomDTO")
+
+
+def _html2_text(text: str) -> str:
+    """处理html以及换行符.
+
+    Args:
+        text (str): HTML内容
+
+    Returns:
+        text (str): 纯文本内容
+    """
+    # 将<br>标签替换为换行符
+    text = re.sub(r"<br\s*/?>", "\n", text)
+    # 去除其他HTML标签
+    text = re.sub(r"<[^>]*>", "", text)
+    # 处理HTML实体
+    text = unescape(text)
+    # 处理多余的空白字符，但保留单个换行符
+    text = re.sub(r"[ \t]+", " ", text)  # 将多个空格或制表符合并为单个空格
+    text = re.sub(r" *\n *", "\n", text)  # 去除换行符前后的空格
+    text = re.sub(r"\n+", "\n", text).strip()  # 合并多个换行符并去除首尾空白
+    return text
+
+
+class RoomInfoDto(BaseDataModel):
+    """直播间信息DTO"""
+
+    uid: int  # 用户uid
+    room_id: int  # 房间号
+    title: str  # 直播间标题
+    cover_url: str  # 直播间封面url
+    background_url: str  # 直播间背景图url
+    description: str  # 主播简介
+    tags: tuple[str, ...]  # 直播间标签列表
+    live_status: int  # 直播状态 0：未开播 1：直播中 2：轮播中
+    live_start_time: int  # 直播开始时间戳
+    parent_area_name: str  # 直播间父分区
+    parent_area_id: int  # 直播间父分区ID
+    area_name: str  # 直播间子分区
+    area_id: int  # 直播间子分区ID
+    keyframe_url: str  # 直播间关键帧url
+    online: int  # 直播间当前在线人数
+
+
+class AnchorInfoDto(BaseDataModel):
+    """主播信息DTO"""
+
+    name: str  # 主播昵称
+    face_url: str  # 主播头像url
+    gender: str  # 主播性别
+    official_info: str  # 主播官方信息(认证信息)
+    fanclub_name: str  # 粉丝牌名称
+    fanclub_num: int  # 粉丝团人数
+    live_level: int  # 主播等级
+    live_score: int  # 直播分数
+    live_upgrade_score: int  # 升级所需分数
+
+
+class WatchedShowDto(BaseDataModel):
+    """观看榜信息DTO"""
+
+    switch: bool  # 观看榜开关
+    num: int  # 观看人数/人气值
+    text_small: str  # 小文本
+    text_large: str  # 大文本
+
+
+class NoticeBoardDto(BaseDataModel):
+    """公告栏信息DTO"""
+
+    content: str  # 公告内容
+    ctime: str  # 公告发布时间
+
+
+class LiveRoomDTO(BaseDataModel):
+    """直播间数据DTO"""
+
+    discriminator_value: ClassVar[str] = "live_room"  # 数据类型标识
+
+    room_info: RoomInfoDto  # 直播间信息
+    anchor_info: AnchorInfoDto  # 主播信息
+    watched_show: WatchedShowDto  # 观看榜信息
+    notice_board: NoticeBoardDto | None = None  # 公告栏信息
+
+    @classmethod
+    def from_raw(cls, data: dict[Any, Any]) -> "LiveRoomDTO | None":
+        """从原始API数据构造DTO对象"""
+        try:
+            # 直播间信息
+            room_info_data = data.get("room_info", {})
+            _tags: str = room_info_data.get("tags", "")
+            tags_tuple = tuple(_tags.split(",")) if _tags else ()
+
+            room_info = {
+                "uid": room_info_data.get("uid", 0),
+                "room_id": room_info_data.get("room_id", 0),
+                "title": room_info_data.get("title", ""),
+                "cover_url": room_info_data.get("cover", ""),
+                "background_url": room_info_data.get("background", ""),
+                "description": _html2_text(room_info_data.get("description", "")),
+                "tags": tags_tuple,
+                "live_status": room_info_data.get("live_status", 0),
+                "live_start_time": room_info_data.get("live_start_time", 0),
+                "parent_area_name": room_info_data.get("parent_area_name", ""),
+                "parent_area_id": room_info_data.get("parent_area_id", 0),
+                "area_name": room_info_data.get("area_name", ""),
+                "area_id": room_info_data.get("area_id", 0),
+                "keyframe_url": room_info_data.get("keyframe", ""),
+                "online": room_info_data.get("online", 0),
+            }
+
+            # 主播信息
+            anchor_info_data = data.get("anchor_info", {})
+            base_info = anchor_info_data.get("base_info", {})
+            medal_info = anchor_info_data.get("medal_info", {})
+            live_info = anchor_info_data.get("live_info", {})
+            official_info = base_info.get("official_info", {})
+
+            anchor_info = {
+                "name": base_info.get("uname", ""),
+                "face_url": base_info.get("face", ""),
+                "gender": base_info.get("gender", ""),
+                "official_info": official_info.get("title", ""),
+                "fanclub_name": medal_info.get("medal_name", ""),
+                "fanclub_num": medal_info.get("fansclub", 0),
+                "live_level": live_info.get("level", 0),
+                "live_score": live_info.get("score", 0),
+                "live_upgrade_score": live_info.get("upgrade_score", 0),
+            }
+
+            # 观看榜信息
+            watched_show_data = data.get("watched_show", {})
+            watched_show = {
+                "switch": watched_show_data.get("switch", False),
+                "num": watched_show_data.get("num", 0),
+                "text_small": watched_show_data.get("text_small", ""),
+                "text_large": watched_show_data.get("text_large", ""),
+            }
+
+            # 公告栏信息
+            notice_board = None
+            notice_board_data = data.get("news_info")
+            if notice_board_data:
+                notice_board = {
+                    "content": notice_board_data.get("content", ""),
+                    "ctime": notice_board_data.get("ctime", ""),
+                }
+
+            # 构造标准化字典后使用model_validate
+            normalized_data = {
+                "room_info": room_info,
+                "anchor_info": anchor_info,
+                "watched_show": watched_show,
+                "notice_board": notice_board,
+            }
+
+            return cls.model_validate(normalized_data)
+
+        except Exception as e:
+            _log.error("解析直播间数据失败: %s", e, exc_info=True)
+            return None

butterbot/sources/bilibili/data/dto/video_part_dto.py

@@ -0,0 +1,18 @@
+from typing import ClassVar
+
+from butterbot.core.data import BaseDataModel
+
+
+class VideoPartDto(BaseDataModel):
+    """视频分段数据DTO"""
+
+    discriminator_value: ClassVar[str] = "video_part"  # 数据类型标识
+
+    start_timestamp: int  # 开始时间戳
+    end_timestamp: int  # 结束时间戳
+    content: str  # 字幕内容
+
+    @classmethod
+    def from_list(cls, data: list) -> list["VideoPartDto"]:
+        """从列表构造DTO对象列表"""
+        return [cls.model_validate(i) for i in data]