Byted Vod Process Tools

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
add_subtitle.py — 添加内嵌字幕

用法:
  python <SKILL_DIR>/scripts/add_subtitle.py '<json_args>'
  python <SKILL_DIR>/scripts/add_subtitle.py @params.json

json_args 字段见 references/18-add-subtitle.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, fmt_src, out, bail


def main():
    client, sp, args = init_and_parse()

    # ── 视频参数 ──
    video = args.get("video")
    if not video:
        bail("add_subtitle: video 不能为空")
    vt = video.get("type", "vid")
    vs = video.get("source", "")
    formatted_video = fmt_src(vt, vs) if vt in ("vid", "directurl") else vs

    # ── 字幕来源（二选一，subtitle_url 优先） ──
    subtitle_url = args.get("subtitle_url")
    text_list = args.get("text_list")
    if not subtitle_url and not text_list:
        bail("add_subtitle: 必须指定 subtitle_url 或 text_list 中的一个")

    param_obj = {
        "space_name": sp,
        "video": formatted_video,
    }
    if subtitle_url:
        param_obj["subtitle_url"] = subtitle_url
    elif text_list:
        param_obj["text_list"] = text_list

    # ── 字幕样式配置（可选） ──
    subtitle_config = args.get("subtitle_config")
    if subtitle_config:
        param_obj["subtitle_config"] = subtitle_config

    out(client.submit_vcreative("loki://168214785", param_obj, sp))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
asr_speech_to_text.py — 语音转字幕 (ASR)

用法:
  python <SKILL_DIR>/scripts/asr_speech_to_text.py '<json_args>'
  python <SKILL_DIR>/scripts/asr_speech_to_text.py @params.json

json_args 字段见 references/15-asr-speech-to-text.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, build_media_input, out, bail


def main():
    client, sp, args = init_and_parse()

    t = args.get("type", "Vid")
    video = args.get("video")
    if not video:
        bail("asr_speech_to_text: video 不能为空")

    asr_config = {"WithSpeakerInfo": True}
    language = args.get("language")
    if language:
        asr_config["Language"] = language

    params = {
        "Input": build_media_input(t, video, sp),
        "Operation": {
            "Type": "Task",
            "Task": {
                "Type": "Asr",
                "Asr": asr_config,
            },
        },
    }
    out(client.submit_media(params, "asr", sp))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
clipping.py — 视频/音频裁剪

用法:
  python <SKILL_DIR>/scripts/clipping.py '<json_args>'
  python <SKILL_DIR>/scripts/clipping.py @params.json

json_args 字段见 references/02-clipping.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, fmt_src, out, bail


def main():
    client, sp, args = init_and_parse()

    t = args.get("type", "video")
    source = args.get("source")
    if not source:
        bail("clipping: source 不能为空")
    start = float(args.get("start_time", 0))
    end = float(args.get("end_time", start + 1))
    if end <= start:
        bail("clipping: end_time 必须大于 start_time")

    param_obj = {
        "space_name": sp,
        "source": fmt_src(t, source),
        "start_time": start,
        "end_time": end,
    }
    wf = "loki://158666752" if t == "audio" else "loki://154419276"
    out(client.submit_vcreative(wf, param_obj, sp))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
comic_style.py — AI 漫剧转绘（Comic Style Transfer）

使用 AsyncVCreativeTask（Scene=videostyletrans）提交转绘任务，
通过 GetVCreativeTaskResult 轮询到终态。

用法:
  # 直接执行（提交 + 自动轮询）
  python <SKILL_DIR>/scripts/comic_style.py @params.json

  # 恢复轮询已提交的任务
  python <SKILL_DIR>/scripts/comic_style.py --poll <VCreativeId> [space_name]

params.json 示例:
{
  "Vid": "v0d012xxxx",
  "Style": "漫画风",
  "Resolution": "720p"
}

参数说明:
  Vid        (必填) 视频 ID，也可传入 vid://xxx 格式
  Style      (选填) 转绘风格，默认 "漫画风"。可选："漫画风" | "3D卡通风格"
  Resolution (必填) 输出分辨率："480p" | "720p" | "1080p"
"""

import sys
import os
import json

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import (
    init_and_parse,
    get_space_name,
    out,
    bail,
    log,
)
from api_manage import ApiManage
from vod_api_constants import (
    VOD_ACTION_SUBMIT_ASYNC_AI_CLIP,
    VOD_FIELD_AI_CLIP_TASK_ID,
)


# ── 限制 ────────────────────────────────────────────
MAX_DURATION_SEC = 300  # 视频时长 ≤ 5 分钟

VALID_STYLES = {"漫画风", "3D卡通风格"}
VALID_RESOLUTIONS = {"480p", "720p", "1080p"}


def get_duration(api: ApiManage, vid: str, space_name: str) -> float:
    """通过 GetMediaInfos 获取视频时长（秒）。"""
    raw = api.get_media_infos(vid, space_name)
    result = raw.get("Result", raw)
    info_list = result.get("MediaInfoList", [])
    if not info_list:
        bail(f"未找到 Vid={vid} 的媒资信息，请确认 Vid 及空间名称")
    basic = info_list[0].get("BasicInfo", {})
    duration = basic.get("Duration", 0)
    return float(duration)


def submit_comic_style(
    api: ApiManage, vid: str, style: str, resolution: str, space_name: str
) -> dict:
    """提交 AsyncVCreativeTask (Scene=videostyletrans) 并自动轮询。"""

    # 构建 vid:// 格式输入
    vid_input = vid if vid.startswith("vid://") else f"vid://{vid}"

    param_obj = {
        "input": vid_input,
        "style": style,
        "resolution": resolution,
    }

    payload = {
        "Uploader": space_name,
        "Scene": "videostyletrans",
        # ParamObj 需要是对象而不是字符串
        "ParamObj": param_obj,
    }

    log(f"提交漫剧转绘任务：Vid={vid}, Style={style}, Resolution={resolution}")

    # 直接调用底层 _post 接口，因为 comic_style 使用 Scene 而非 WorkflowId
    try:
        resp = api._post(VOD_ACTION_SUBMIT_ASYNC_AI_CLIP, payload)
    except Exception as e:
        bail(f"提交任务失败：{e}")

    if isinstance(resp, str):
        resp = json.loads(resp)

    result = resp.get("Result", {})
    base_resp = result.get("BaseResp", {}) or {}
    sc = base_resp.get("StatusCode", 0)
    if sc != 0:
        bail(f"提交任务失败：StatusCode={sc} msg={base_resp.get('StatusMessage', '')}")

    vcreative_id = result.get(VOD_FIELD_AI_CLIP_TASK_ID, "") or result.get(
        "VCreativeId", ""
    )
    if not vcreative_id:
        bail(f"提交任务未返回 VCreativeId，原始响应：{json.dumps(resp)}")

    log(f"任务已提交，VCreativeId={vcreative_id}，开始轮询...")
    return api.poll_vcreative(vcreative_id, space_name)


def main():
    # ── 恢复轮询模式 ───────────────────────────────
    if len(sys.argv) >= 3 and sys.argv[1] == "--poll":
        vcreative_id = sys.argv[2]
        api = ApiManage()
        space_name = get_space_name(argv_pos=3)
        result = api.poll_vcreative(vcreative_id, space_name)
        out(result)
        return

    # ── 正常提交模式 ───────────────────────────────
    api, space_name, params = init_and_parse(argv_pos=1)

    vid = params.get("Vid", "").strip()
    if not vid:
        bail("缺少必填参数 Vid（视频 ID）")

    # 去掉 vid:// 前缀用于校验
    raw_vid = vid.replace("vid://", "") if vid.startswith("vid://") else vid

    resolution = params.get("Resolution", "").strip()
    if not resolution:
        bail(f"缺少必填参数 Resolution，可选值：{', '.join(sorted(VALID_RESOLUTIONS))}")
    if resolution not in VALID_RESOLUTIONS:
        bail(
            f"Resolution 不合法：{resolution}，可选值：{', '.join(sorted(VALID_RESOLUTIONS))}"
        )

    style = params.get("Style", "漫画风").strip()
    if style not in VALID_STYLES:
        bail(f"Style 不合法：{style}，可选值：{', '.join(sorted(VALID_STYLES))}")

    # ── 时长校验 ─────────────────────────────────
    log("检查视频时长...")
    duration = get_duration(api, raw_vid, space_name)
    log(f"视频时长：{duration:.1f}s")
    if duration > MAX_DURATION_SEC:
        bail(f"视频时长 {duration:.0f}s 超过限制（最大 {MAX_DURATION_SEC}s / 5 分钟）")

    # ── 提交 ─────────────────────────────────────
    result = submit_comic_style(api, raw_vid, style, resolution, space_name)
    out(result)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
compile.py — 音视频合成（替换/叠加背景音）

用法:
  python <SKILL_DIR>/scripts/compile.py '<json_args>'
  python <SKILL_DIR>/scripts/compile.py @params.json

json_args 字段见 references/06-compile.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, fmt_src, out, bail


def main():
    client, sp, args = init_and_parse()

    video = args.get("video")
    if not video:
        bail("compile: video 不能为空")
    audio = args.get("audio")
    if not audio:
        bail("compile: audio 不能为空")
    vt, vs = video.get("type", "vid"), video.get("source", "")
    at, as_ = audio.get("type", "vid"), audio.get("source", "")

    param_obj = {
        "space_name": sp,
        "video": fmt_src(vt, vs) if vt in ("vid", "directurl") else vs,
        "audio": fmt_src(at, as_) if at in ("vid", "directurl") else as_,
        "is_audio_reserve": bool(args.get("is_audio_reserve", True)),
        "is_video_audio_sync": bool(args.get("is_video_audio_sync", False)),
    }
    if param_obj["is_video_audio_sync"]:
        param_obj["sync_mode"] = args.get("sync_mode", "video")
        param_obj["sync_method"] = args.get("sync_method", "trim")

    out(client.submit_vcreative("loki://167984726", param_obj, sp))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
drama_recap.py — 提交解说视频生成任务（CreateDramaRecapTask / QueryDramaRecapTask）

基于大模型视频理解，根据原视频生成不同风格的 AI 解说视频，支持自定义解说词或 AI 自动生成，
支持多种音色、字幕样式和短剧三要素模板。

用法:
  python <SKILL_DIR>/scripts/drama_recap.py '<json_args>' [space_name]
  python <SKILL_DIR>/scripts/drama_recap.py @params.json [space_name]
  python <SKILL_DIR>/scripts/drama_recap.py --poll <TaskId> [space_name]

JSON 参数说明:
  视频输入（二选一）:
    Vids                  — 视频 ID 列表（至少 1 个）
    DramaScriptTaskId     — 已完成的剧本还原任务 ID（与 Vids 互斥）

  解说词（根据模式必选或可选）:
    RecapText             — 自定义解说词文本（AutoGenerateRecapText=false 时必选）

  可选:
    AutoGenerateRecapText — 是否 AI 自动生成解说词，默认 false
    RecapStyle            — AI 解说风格关键词（如"搞笑"、"悬疑"），≤500 字符
    RecapTextSpeed        — 解说语速 [0.5, 2.0]，默认 1.0，推荐 1.2
    RecapTextLength       — AI 生成解说词长度（字符数），≤5000
    PauseTime             — 句间停顿（毫秒）[1, 1000]，默认 120
    AllowRepeatMatch      — 是否允许匹配重复画面，默认 false
    IsEraseSubtitle       — 是否擦除原字幕，默认 false
    BatchGenerateCount    — 批量生成数量，默认 1，最大 100
    VoiceType             — 音色名称（默认 Yunxi），预置: Yunxi/Yunjian/Yunfeng/Yunyi/Yunjie/Yunze/Yunye/Xiaoxiao/Xiaochen/Xiaohan/Xiaomo
    AppId                 — 豆包语音 App ID（使用高级音色时需要）
    FontConfig            — 字幕样式配置（详见 reference 文档）
    MiniseriesEdit        — 短剧三要素配置（Template/Title/Hint）

输出:
  成功: {"Status":"success","TaskId":"...","Vid":"...","MultipleResult":{...}}
  失败: {"error":"..."}
  超时: {"error":"轮询超时...","resume_hint":{"command":"python .../drama_recap.py --poll <TaskId> <space>"}}
"""

import sys
import os
import json
import time

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from vod_common import (
    init_and_parse,
    get_space_name,
    log,
    bail,
    out,
)
from api_manage import ApiManage


# ══════════════════════════════════════════════════════
# 预置音色列表
# ══════════════════════════════════════════════════════

PRESET_VOICES = {
    "Yunxi",
    "Yunjian",
    "Yunfeng",
    "Yunyi",
    "Yunjie",
    "Yunze",
    "Yunye",
    "Xiaoxiao",
    "Xiaochen",
    "Xiaohan",
    "Xiaomo",
}

# 短剧三要素模板
SUPPORTED_TEMPLATES = {
    "热门短剧1",
    "热门短剧2",
    "热门短剧3",
    "热门短剧4",
    "热门短剧5",
}


# ══════════════════════════════════════════════════════
# 轮询逻辑
# ══════════════════════════════════════════════════════


def poll_drama_recap(api, space_name, task_id, max_rounds=360, interval=5):
    """
    轮询 QueryDramaRecapTask 直到终态。
    终态: success / failed / timeout
    """
    log(f"开始轮询解说视频任务: TaskId={task_id}")

    for i in range(1, max_rounds + 1):
        try:
            raw = api.query_drama_recap_task(
                {
                    "SpaceName": space_name,
                    "TaskId": task_id,
                }
            )
            resp = json.loads(raw) if isinstance(raw, str) else raw
            result = resp.get("Result", {})
            status = result.get("Status", "")

            if i % 12 == 1:  # 每分钟打一次日志
                log(f"轮询第 {i}/{max_rounds} 次, Status={status}")

            if status == "success":
                log("解说视频生成成功")
                output = {
                    "Status": "success",
                    "TaskId": task_id,
                    "SpaceName": space_name,
                }
                # 单个视频时有 Vid
                if result.get("Vid"):
                    output["Vid"] = result["Vid"]
                # 批量时有 MultipleResult
                if result.get("MultipleResult"):
                    output["MultipleResult"] = result["MultipleResult"]
                return output

            if status in ("failed", "timeout"):
                log(f"任务终态: {status}")
                return {
                    "Status": status,
                    "TaskId": task_id,
                    "SpaceName": space_name,
                    "detail": result,
                    "note": f"任务{status}，请检查输入视频和参数后重试。",
                }

            # running — 继续等待
        except Exception as e:
            if i % 12 == 1:
                log(f"轮询异常: {e}")

        time.sleep(interval)

    # 超时
    return {
        "error": f"轮询超时（{max_rounds} 次 × {interval}s），任务仍在处理中",
        "TaskId": task_id,
        "resume_hint": {
            "description": "任务尚未完成，可用以下命令重启轮询",
            "command": f"python <SKILL_DIR>/scripts/drama_recap.py --poll '{task_id}' {space_name}",
        },
    }


# ══════════════════════════════════════════════════════
# 主流程
# ══════════════════════════════════════════════════════


def main():
    # ── 检查恢复轮询模式 ──
    if len(sys.argv) >= 3 and sys.argv[1] == "--poll":
        task_id = sys.argv[2]
        space_name = get_space_name(argv_pos=3)
        api = ApiManage()
        result = poll_drama_recap(api, space_name, task_id)
        out(result)
        return

    api, space_name, args = init_and_parse(argv_pos=1)

    # ── 解析视频输入（Vids 和 DramaScriptTaskId 二选一）──
    vids = args.get("Vids") or args.get("vids") or []
    if isinstance(vids, str):
        vids = [vids]
    drama_script_task_id = (
        args.get("DramaScriptTaskId") or args.get("dramaScriptTaskId") or ""
    )

    if vids and drama_script_task_id:
        bail("Vids 和 DramaScriptTaskId 互斥，只能提供其中一个")
    if not vids and not drama_script_task_id:
        bail("必须提供 Vids（视频 ID 列表）或 DramaScriptTaskId（剧本还原任务 ID）之一")

    # ── 解析解说词相关 ──
    auto_generate = args.get("AutoGenerateRecapText", False)
    recap_text = args.get("RecapText") or args.get("recapText") or ""

    if not auto_generate and not recap_text:
        bail(
            "当 AutoGenerateRecapText 为 false（默认）时，必须提供 RecapText（解说词文本）。\n"
            "或设置 AutoGenerateRecapText=true 让 AI 自动生成解说词。"
        )
    if auto_generate and recap_text:
        bail("AutoGenerateRecapText=true 时不可同时设置 RecapText，请二选一")

    # ── 构造请求体 ──
    body = {"SpaceName": space_name}

    if vids:
        body["Vids"] = [v for v in vids if v]
        if not body["Vids"]:
            bail("Vids 列表中没有有效的视频 ID")
    else:
        body["DramaScriptTaskId"] = drama_script_task_id

    if recap_text:
        body["RecapText"] = recap_text

    # IsEraseSubtitle
    if "IsEraseSubtitle" in args:
        body["IsEraseSubtitle"] = args["IsEraseSubtitle"]

    # BatchGenerateCount
    batch_count = args.get("BatchGenerateCount", 1)
    if batch_count != 1:
        body["BatchGenerateCount"] = batch_count

    # ── SpeakerConfig ──
    voice_type = args.get("VoiceType") or args.get("voiceType") or ""
    app_id = args.get("AppId") or args.get("appId") or ""
    if voice_type or app_id:
        speaker = {}
        if voice_type:
            speaker["VoiceType"] = voice_type
        if app_id:
            speaker["AppId"] = app_id
            speaker["Cluster"] = "volcano_tts"
        body["SpeakerConfig"] = speaker

    # ── FontConfig (pass-through) ──
    font_config = args.get("FontConfig") or args.get("fontConfig")
    if font_config and isinstance(font_config, dict):
        body["FontConfig"] = font_config

    # ── DramaRecapConfig ──
    recap_config = {}
    if auto_generate:
        recap_config["AutoGenerateRecapText"] = True
    recap_style = args.get("RecapStyle") or args.get("recapStyle") or ""
    if recap_style:
        recap_config["RecapStyle"] = recap_style
    recap_speed = args.get("RecapTextSpeed") or args.get("recapTextSpeed")
    if recap_speed is not None:
        recap_config["RecapTextSpeed"] = float(recap_speed)
    recap_length = args.get("RecapTextLength") or args.get("recapTextLength")
    if recap_length is not None:
        recap_config["RecapTextLength"] = int(recap_length)
    pause_time = args.get("PauseTime") or args.get("pauseTime")
    if pause_time is not None:
        recap_config["PauseTime"] = int(pause_time)
    allow_repeat = args.get("AllowRepeatMatch")
    if allow_repeat is not None:
        recap_config["AllowRepeatMatch"] = allow_repeat

    if recap_config:
        body["DramaRecapConfig"] = recap_config

    # ── MiniseriesEdit (短剧三要素) ──
    mini_edit = args.get("MiniseriesEdit") or args.get("miniseriesEdit")
    if mini_edit and isinstance(mini_edit, dict):
        tmpl = mini_edit.get("Template", "")
        if tmpl and tmpl not in SUPPORTED_TEMPLATES:
            bail(
                f"不支持的短剧三要素模板: {tmpl}。支持: {', '.join(sorted(SUPPORTED_TEMPLATES))}"
            )
        body["MiniseriesEdit"] = mini_edit

    input_desc = (
        f"{len(vids)} 个视频" if vids else f"DramaScriptTaskId={drama_script_task_id}"
    )
    log(
        f"提交解说视频生成任务: {input_desc}, AutoGenerate={auto_generate}, BatchCount={batch_count}"
    )

    # ── 提交任务 ──
    try:
        raw = api.create_drama_recap_task(body)
        resp = json.loads(raw) if isinstance(raw, str) else raw
    except Exception as e:
        bail(f"CreateDramaRecapTask 调用失败: {e}")

    resp_meta = resp.get("ResponseMetadata", {})
    if resp_meta.get("Error"):
        bail(
            f"CreateDramaRecapTask 返回错误: {json.dumps(resp_meta['Error'], ensure_ascii=False)}"
        )

    result = resp.get("Result", {})
    task_id = result.get("TaskId", "")
    if not task_id:
        bail(
            f"CreateDramaRecapTask 未返回 TaskId: {json.dumps(resp, ensure_ascii=False)}"
        )

    drama_script_tid = result.get("DramaScriptTaskId", "")
    log(
        f"任务已提交: TaskId={task_id}"
        + (f", DramaScriptTaskId={drama_script_tid}" if drama_script_tid else "")
    )

    # ── 轮询 ──
    poll_result = poll_drama_recap(api, space_name, task_id)
    out(poll_result)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
drama_script.py — 提交 AI 剧本还原任务（CreateDramaScriptTask / QueryDramaScriptTask）

基于大模型视频理解，将剧情类视频转化为结构化剧本文本。精准识别并提取视频中的
场景、人物（角色）、对话、情节等核心元素，为内容创作者和数据分析师提供高价值文本素材。

用法:
  python <SKILL_DIR>/scripts/drama_script.py '<json_args>' [space_name]
  python <SKILL_DIR>/scripts/drama_script.py @params.json [space_name]

JSON 参数说明:
  必选:
    Vids           — 视频 ID 列表（至少 1 个），如 ["v023xxx", "v024xxx"]
  可选:
    ClientToken    — 幂等 token（不传则自动生成 UUID）

输出:
  成功: {"Status":"success","TaskId":"...","ResultUrl":"..."}
  失败: {"error":"..."}
  超时: {"error":"轮询超时...","resume_hint":{"command":"python .../drama_script.py --poll <TaskId> <space>"}}

恢复轮询模式:
  python <SKILL_DIR>/scripts/drama_script.py --poll <TaskId> [space_name]
"""

import sys
import os
import json
import time
import uuid

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

from vod_common import (
    init_and_parse,
    get_space_name,
    log,
    bail,
    out,
    POLL_INTERVAL,
    POLL_MAX,
)
from api_manage import ApiManage


# ══════════════════════════════════════════════════════
# 剧本还原任务轮询
# ══════════════════════════════════════════════════════


def poll_drama_script(api, task_id: str, space_name: str) -> dict:
    """
    轮询 QueryDramaScriptTask，终态：success / failed / timeout。

    状态机：
      running  → 继续等待
      success  → 终态成功，返回 ResultUrl
      failed   → 终态失败
      timeout  → 终态超时（服务端超时，非客户端轮询超时）
    """
    TERMINAL_SUCCESS = {"success"}
    TERMINAL_FAIL = {"failed", "timeout"}

    for i in range(1, POLL_MAX + 1):
        log(f"轮询剧本还原任务 [{i}/{POLL_MAX}] TaskId={task_id}")
        try:
            raw = api.query_drama_script_task(
                {
                    "SpaceName": space_name,
                    "TaskId": task_id,
                }
            )
            if isinstance(raw, str):
                raw = json.loads(raw)
        except Exception as e:
            log(f"  查询失败: {e}，等待 {POLL_INTERVAL}s 后重试...")
            time.sleep(POLL_INTERVAL)
            continue

        result = raw.get("Result", raw)
        status = result.get("Status", "")

        if status in TERMINAL_SUCCESS:
            result_url = result.get("ResultUrl", "")
            return {
                "Status": "success",
                "TaskId": task_id,
                "SpaceName": space_name,
                "ResultUrl": result_url,
                "note": (
                    "ResultUrl 是一个 .json.gz 压缩文件的下载链接（有效期 24 小时）。"
                    "直接将此链接提供给用户，不需要下载或解压。"
                ),
            }

        if status in TERMINAL_FAIL:
            return {
                "Status": status,
                "TaskId": task_id,
                "SpaceName": space_name,
                "detail": result,
                "note": "任务失败，请检查输入视频是否满足限制条件后重新提交。"
                if status == "failed"
                else "任务服务端超时，请稍后重新提交。",
            }

        # running 或其他中间状态
        log(f"  状态={status!r}，等待 {POLL_INTERVAL}s ...")
        time.sleep(POLL_INTERVAL)

    # 客户端轮询超时
    return {
        "error": f"轮询超时（{POLL_MAX} 次 × {POLL_INTERVAL}s），任务仍在处理中",
        "TaskId": task_id,
        "resume_hint": {
            "description": "任务尚未完成，可用以下命令重启轮询",
            "command": f"python <SKILL_DIR>/scripts/drama_script.py --poll '{task_id}' {space_name}",
        },
    }


# ══════════════════════════════════════════════════════
# 主流程
# ══════════════════════════════════════════════════════


def main():
    # 检查是否为恢复轮询模式
    if len(sys.argv) > 1 and sys.argv[1] == "--poll":
        if len(sys.argv) < 3:
            bail("恢复轮询用法: python drama_script.py --poll <TaskId> [space_name]")
        task_id = sys.argv[2]
        api = ApiManage()
        sp = get_space_name(argv_pos=3)
        log(f"恢复轮询剧本还原任务：TaskId={task_id}, SpaceName={sp}")
        result = poll_drama_script(api, task_id, sp)
        out(result)
        return

    api, space_name, args = init_and_parse(argv_pos=1)

    # ── 解析 Vids ──
    vids = args.get("Vids") or args.get("vids") or []
    # 兼容单个 vid 字符串
    if isinstance(vids, str):
        vids = [vids]
    if not vids:
        bail("必须提供 Vids 参数（视频 ID 列表），至少包含 1 个视频 ID")

    # 过滤空值
    vids = [v for v in vids if v]
    if not vids:
        bail("Vids 列表中没有有效的视频 ID")

    # ── 幂等 token ──
    client_token = args.get("ClientToken") or str(uuid.uuid4())

    # ── 构造请求体 ──
    body = {
        "SpaceName": space_name,
        "Vids": vids,
        "ClientToken": client_token,
    }

    log(f"提交剧本还原任务: {len(vids)} 个视频, SpaceName={space_name}")

    # ── 提交任务 ──
    try:
        raw = api.create_drama_script_task(body)
        if isinstance(raw, str):
            raw = json.loads(raw)
    except Exception as e:
        bail(f"提交剧本还原任务失败: {e}")

    result = raw.get("Result", raw)
    task_id = result.get("TaskId", "")
    if not task_id:
        bail(f"提交任务未返回 TaskId，原始响应：{json.dumps(raw, ensure_ascii=False)}")

    log(f"任务已提交，TaskId={task_id}，开始轮询...")

    # ── 轮询直到终态 ──
    poll_result = poll_drama_script(api, task_id, space_name)
    out(poll_result)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
extract_audio.py — 从视频中提取音轨

用法:
  python <SKILL_DIR>/scripts/extract_audio.py '<json_args>'
  python <SKILL_DIR>/scripts/extract_audio.py @params.json

json_args 字段见 references/07-extract-audio.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, fmt_src, out, bail


def main():
    client, sp, args = init_and_parse()

    t = args.get("type", "vid")
    source = args.get("source")
    if not source:
        bail("extract_audio: source 不能为空")
    fmt = args.get("format", "m4a")
    if fmt not in ("mp3", "m4a"):
        bail("extract_audio: format 必须为 mp3 或 m4a")

    param_obj = {
        "space_name": sp,
        "source": fmt_src(t, source),
        "format": fmt,
    }
    out(client.submit_vcreative("loki://167986559", param_obj, sp))


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
flip.py — 视频翻转（上下/左右）

用法:
  python <SKILL_DIR>/scripts/flip.py '<json_args>'
  python <SKILL_DIR>/scripts/flip.py @params.json

json_args 字段见 references/03-flip.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, fmt_src, out, bail


def main():
    client, sp, args = init_and_parse()

    t = args.get("type", "vid")
    source = args.get("source")
    if not source:
        bail("flip: source 不能为空")
    param_obj = {
        "space_name": sp,
        "source": fmt_src(t, source),
        "flip_x": bool(args.get("flip_x", False)),
        "flip_y": bool(args.get("flip_y", False)),
    }
    out(client.submit_vcreative("loki://165221855", param_obj, sp))


if __name__ == "__main__":
    main()

# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
get_media_info.py — 获取媒资信息（含播放地址）

用法：
  python get_media_info.py '{"vids":"v001,v002"}'
  python get_media_info.py @params.json

参数：
  vids (str, 必需): 逗号分隔的 Vid 列表

返回：
  每个 Vid 的基础信息、片源信息及播放链接
"""

import sys
import os
import json

sys.path.insert(0, os.path.dirname(__file__))
from vod_common import init_and_parse, log, out
from api_manage import ApiManage

# GetMediaInfos 接口单次最多 20 个 Vid
BATCH_LIMIT = 20


def _fetch_batch(api: ApiManage, vids_str: str, space_name: str) -> dict:
    """单次请求最多 20 个 vid。"""
    raw = api.get_media_infos(vids_str, space_name)
    if isinstance(raw, str):
        raw = json.loads(raw)
    return raw.get("Result", raw)


def run(api: ApiManage, args: dict, space_name: str):
    vids_raw = args.get("vids") or args.get("Vids") or ""
    if not vids_raw:
        return {"error": "缺少必需参数 vids（逗号分隔的 Vid 列表）"}

    # 统一为列表
    if isinstance(vids_raw, list):
        vid_list = [v.strip() for v in vids_raw if v.strip()]
    else:
        vid_list = [v.strip() for v in str(vids_raw).split(",") if v.strip()]

    if not vid_list:
        return {"error": "vids 为空"}

    all_media = []
    not_exist = []

    # 分批请求，每批最多 BATCH_LIMIT 个
    for i in range(0, len(vid_list), BATCH_LIMIT):
        batch = vid_list[i : i + BATCH_LIMIT]
        batch_str = ",".join(batch)
        log(f"查询媒资信息 [{i + 1}~{i + len(batch)}/{len(vid_list)}]: {batch_str}")

        result = _fetch_batch(api, batch_str, space_name)
        media_list = result.get("MediaInfoList") or []
        batch_not_exist = result.get("NotExistVids") or []
        not_exist.extend(batch_not_exist)

        for item in media_list:
            basic = item.get("BasicInfo", {})
            source = item.get("SourceInfo", {})
            vid = basic.get("Vid", "")

            # 获取播放地址
            play_url = ""
            if vid:
                try:
                    info = api.get_play_video_info(vid, space_name)
                    play_url = info.get("PlayURL", "")
                except Exception as e:
                    log(f"获取播放地址失败 ({vid}): {e}")
                    # 降级：通过 FileName 获取
                    fname = source.get("FileName", "")
                    if fname:
                        try:
                            play_url = api.get_play_url("directurl", fname, space_name)
                        except Exception:
                            pass

            all_media.append(
                {
                    "Vid": vid,
                    "Title": basic.get("Title", ""),
                    "SpaceName": basic.get("SpaceName", ""),
                    "PublishStatus": basic.get("PublishStatus", ""),
                    "CreateTime": basic.get("CreateTime", ""),
                    "Source": {
                        "Format": source.get("Format", ""),
                        "Duration": source.get("Duration"),
                        "Width": source.get("Width"),
                        "Height": source.get("Height"),
                        "Size": source.get("Size"),
                        "Codec": source.get("Codec", ""),
                        "Fps": source.get("Fps"),
                        "FileName": source.get("FileName", ""),
                    },
                    "PlayUrl": play_url,
                }
            )

    output = {"MediaInfoList": all_media}
    if not_exist:
        output["NotExistVids"] = not_exist

    return output


def main():
    api, space_name, args = init_and_parse()
    result = run(api, args, space_name)
    out(result)


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
# Copyright (c) 2025 Beijing Volcano Engine Technology Co., Ltd. and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""
green_screen.py — 绿幕抠图

用法:
  python <SKILL_DIR>/scripts/green_screen.py '<json_args>'
  python <SKILL_DIR>/scripts/green_screen.py @params.json

json_args 字段见 references/21-green-screen.md
"""

import sys
import os

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from vod_common import init_and_parse, build_media_input, out, bail


def main():
    client, sp, args = init_and_parse()

    t = args.get("type", "Vid")
    video = args.get("video")
    if not video:
        bail("green_screen: video 不能为空")

    fmt = args.get("output_format", "WEBM").upper()
    if fmt not in ("MOV", "WEBM"):
        bail(f"green_screen: output_format 必须为 MOV 或 WEBM，得到：{fmt}")

    params = {
        "Input": build_media_input(t, video, sp),
        "Operation": {
            "Type": "Task",
            "Task": {
                "Type": "VideoMatting",
                "VideoMatting": {
                    "Model": "GreenScreen",
                    "VideoOption": {"Format": fmt},
                    "NewVid": True,
                },
            },
        },
    }
    out(client.submit_media(params, "greenScreen", sp))


if __name__ == "__main__":
    main()