@acedatacloud/skills 2026.714.4 → 2026.715.0

package/skills/xiaohongshu/scripts/vendor/xhs/publish_long_article.py

@@ -1,293 +0,0 @@
-"""长文发布模式，参考 cdp_publish.py 的长文工作流。"""
-
-from __future__ import annotations
-
-import json
-import logging
-import time
-from pathlib import Path
-
-from .cdp import Page
-from .errors import PublishError
-from .publish import _find_content_element
-from .selectors import (
-    AUTO_FORMAT_BUTTON_TEXT,
-    CONTENT_EDITOR,
-    LONG_ARTICLE_TITLE,
-    NEW_CREATION_BUTTON_TEXT,
-    NEXT_STEP_BUTTON_TEXT,
-    TEMPLATE_CARD,
-    TEMPLATE_TITLE,
-)
-
-logger = logging.getLogger(__name__)
-
-# 等待常量
-_AUTO_FORMAT_WAIT = 3.0
-_TEMPLATE_WAIT_ROUNDS = 15
-_PAGE_LOAD_WAIT = 3.0
-_LONG_ARTICLE_URL = (
-    "https://creator.xiaohongshu.com/publish/publish?source=official&target=article"
-)
-
-
-def publish_long_article(
-    page: Page,
-    title: str,
-    content: str,
-    image_paths: list[str] | None = None,
-) -> list[str]:
-    """长文发布：导航 → 点击写长文 → 新的创作 → 填写标题正文 → 一键排版。
-
-    返回可用模板名称列表。
-
-    Args:
-        page: CDP 页面对象。
-        title: 长文标题。
-        content: 长文正文（段落用换行分隔）。
-        image_paths: 可选的图片路径列表（插入编辑器）。
-
-    Returns:
-        可用模板名称列表。
-
-    Raises:
-        PublishError: 操作失败。
-    """
-    # 1. 直达长文入口，避免 tab_switch 的 SPA 重载竞态。
-    page.navigate(_LONG_ARTICLE_URL)
-    page.wait_for_load(timeout=120)
-    page.wait_dom_stable()
-    time.sleep(1)
-
-    # 2. 点击"新的创作"
-    _click_new_creation(page)
-
-    # 3. 填写标题（textarea）
-    _fill_long_title(page, title)
-
-    # 4. 填写正文（TipTap 编辑器）
-    _fill_long_content(page, content)
-
-    # 5. 可选：插入图片到编辑器
-    if image_paths:
-        _insert_images_to_editor(page, image_paths)
-
-    # 6. 点击"一键排版"
-    _click_auto_format(page)
-
-    # 7. 等待模板加载并返回名称列表
-    _wait_for_templates(page)
-    template_names = get_template_names(page)
-    logger.info("模板加载完成: %s", template_names)
-    return template_names
-
-
-def get_template_names(page: Page) -> list[str]:
-    """获取当前可用的排版模板名称列表。
-
-    Args:
-        page: CDP 页面对象。
-
-    Returns:
-        模板名称列表。
-    """
-    names = page.evaluate(
-        f"""
-        (() => {{
-            const cards = document.querySelectorAll({json.dumps(TEMPLATE_CARD)});
-            const names = [];
-            for (const card of cards) {{
-                const title = card.querySelector({json.dumps(TEMPLATE_TITLE)});
-                names.push(title ? title.textContent.trim() : 'Template ' + names.length);
-            }}
-            return names;
-        }})()
-        """
-    )
-    return names or []
-
-
-def select_template(page: Page, template_name: str) -> bool:
-    """选择指定名称的排版模板。
-
-    Args:
-        page: CDP 页面对象。
-        template_name: 模板名称。
-
-    Returns:
-        是否成功选择。
-    """
-    clicked = page.evaluate(
-        f"""
-        (() => {{
-            const cards = document.querySelectorAll({json.dumps(TEMPLATE_CARD)});
-            for (const card of cards) {{
-                const title = card.querySelector({json.dumps(TEMPLATE_TITLE)});
-                if (title && title.textContent.trim() === {json.dumps(template_name)}) {{
-                    card.click();
-                    return true;
-                }}
-            }}
-            return false;
-        }})()
-        """
-    )
-
-    if clicked:
-        logger.info("已选择模板: %s", template_name)
-        time.sleep(1)
-    else:
-        logger.warning("未找到模板: %s", template_name)
-
-    return bool(clicked)
-
-
-def click_next_and_fill_description(page: Page, description: str) -> None:
-    """点击下一步，进入发布页并填写正文描述。
-
-    注意：发布页有独立的正文编辑器，需单独填入。
-    如果 description 超过 1000 字，应压缩到 800 字左右。
-
-    Args:
-        page: CDP 页面对象。
-        description: 发布页正文描述。
-
-    Raises:
-        PublishError: 操作失败。
-    """
-    # 点击"下一步"
-    _click_button_by_text(page, NEXT_STEP_BUTTON_TEXT)
-    time.sleep(_PAGE_LOAD_WAIT)
-
-    # 填写发布页描述
-    if description:
-        # 截断描述到 1000 字以内
-        if len(description) > 1000:
-            description = description[:800]
-            logger.warning("描述超过1000字，已截断到800字")
-
-        content_selector = _find_content_element(page)
-        page.input_content_editable(content_selector, description)
-        logger.info("已填写发布页描述")
-
-
-# ========== 内部辅助函数 ==========
-
-
-def _click_new_creation(page: Page) -> None:
-    """点击"新的创作"按钮。"""
-    deadline = time.monotonic() + 15
-    clicked = False
-    while time.monotonic() < deadline:
-        if page.has_element("button.new-btn"):
-            page.click_element("button.new-btn")
-            clicked = True
-            break
-        time.sleep(0.25)
-    if not clicked:
-        _click_button_by_text(page, NEW_CREATION_BUTTON_TEXT)
-    time.sleep(2)
-    page.wait_for_load(timeout=60)
-    page.wait_dom_stable()
-    logger.info("已点击'新的创作'")
-
-
-def _fill_long_title(page: Page, title: str) -> None:
-    """填写长文标题（textarea，需使用 native setter）。"""
-    page.wait_for_element(LONG_ARTICLE_TITLE, timeout=10)
-
-    page.evaluate(
-        f"""
-        (() => {{
-            const el = document.querySelector({json.dumps(LONG_ARTICLE_TITLE)});
-            if (!el) return false;
-            const nativeSetter = Object.getOwnPropertyDescriptor(
-                window.HTMLTextAreaElement.prototype, 'value'
-            ).set;
-            el.focus();
-            nativeSetter.call(el, {json.dumps(title)});
-            el.dispatchEvent(new Event('input', {{ bubbles: true }}));
-            el.dispatchEvent(new Event('change', {{ bubbles: true }}));
-            return true;
-        }})()
-        """
-    )
-    logger.info("已填写长文标题: %s", title[:20])
-    time.sleep(0.5)
-
-
-def _fill_long_content(page: Page, content: str) -> None:
-    """填写长文正文（TipTap/ProseMirror 编辑器）。"""
-    content_selector = CONTENT_EDITOR
-    if not page.has_element(CONTENT_EDITOR):
-        content_selector = _find_content_element(page)
-
-    page.input_content_editable(content_selector, content)
-    logger.info("已填写长文正文 (%d 字)", len(content))
-    time.sleep(1)
-
-
-def _insert_images_to_editor(page: Page, image_paths: list[str]) -> None:
-    """将图片插入到编辑器中。"""
-    for img_path in image_paths:
-        file_uri = Path(img_path).resolve().as_uri()
-        page.evaluate(
-            f"""
-            (() => {{
-                const editor = document.querySelector({json.dumps(CONTENT_EDITOR)});
-                if (!editor) return false;
-                const img = document.createElement('img');
-                img.src = {json.dumps(file_uri)};
-                editor.appendChild(img);
-                editor.dispatchEvent(new Event('input', {{ bubbles: true }}));
-                return true;
-            }})()
-            """
-        )
-    logger.info("已插入 %d 张图片到编辑器", len(image_paths))
-    time.sleep(1)
-
-
-def _click_auto_format(page: Page) -> None:
-    """点击"一键排版"按钮。"""
-    _click_button_by_text(page, AUTO_FORMAT_BUTTON_TEXT)
-    logger.info("已点击'一键排版'，等待模板加载...")
-    time.sleep(_AUTO_FORMAT_WAIT)
-
-
-def _wait_for_templates(page: Page) -> bool:
-    """等待模板卡片出现。"""
-    for _ in range(_TEMPLATE_WAIT_ROUNDS):
-        count = page.get_elements_count(TEMPLATE_CARD)
-        if count and count > 0:
-            logger.info("发现 %d 个模板卡片", count)
-            return True
-        time.sleep(1)
-
-    logger.warning("等待模板卡片超时")
-    return False
-
-
-def _click_button_by_text(page: Page, text: str) -> None:
-    """通过文本内容查找并点击按钮（通用方法）。"""
-    clicked = page.evaluate(
-        f"""
-        (() => {{
-            const elems = document.querySelectorAll(
-                'button, [role="button"], span, div, a, [class*="btn"]'
-            );
-            for (const el of elems) {{
-                if (el.textContent.trim() === {json.dumps(text)}) {{
-                    const rect = el.getBoundingClientRect();
-                    if (rect.width === 0 || rect.height === 0) continue;
-                    el.click();
-                    return true;
-                }}
-            }}
-            return false;
-        }})()
-        """
-    )
-
-    if not clicked:
-        raise PublishError(f"未找到'{text}'按钮，页面结构可能已变化")

package/skills/xiaohongshu/scripts/vendor/xhs/publish_video.py

@@ -1,183 +0,0 @@
-"""视频发布，对应 Go xiaohongshu/publish_video.go。"""
-
-from __future__ import annotations
-
-import logging
-import os
-import time
-
-from .cdp import Page
-from .errors import PublishError, UploadTimeoutError
-from .publish import (
-    _click_publish_tab,
-    _find_content_element,
-    _input_tags,
-    _navigate_to_publish_page,
-    _set_schedule_publish,
-    _set_visibility,
-    click_publish_button,
-)
-from .selectors import (
-    FILE_INPUT,
-    PUBLISH_BUTTON,
-    TITLE_INPUT,
-    UPLOAD_INPUT,
-)
-from .types import PublishVideoContent
-
-logger = logging.getLogger(__name__)
-VIDEO_OPERATION_TIMEOUT_SECONDS = 100.0
-
-
-def publish_video_content(page: Page, content: PublishVideoContent) -> None:
-    """发布视频内容（填写表单 + 点击发布）。
-
-    Args:
-        page: CDP 页面对象。
-        content: 视频发布内容。
-
-    Raises:
-        PublishError: 发布失败。
-        UploadTimeoutError: 上传/处理超时。
-    """
-    deadline = time.monotonic() + VIDEO_OPERATION_TIMEOUT_SECONDS
-    fill_publish_video_form(page, content, deadline=deadline)
-    click_publish_video_button(page, deadline=deadline)
-
-
-def fill_publish_video_form(
-    page: Page, content: PublishVideoContent, *, deadline: float | None = None
-) -> None:
-    """填写视频发布表单，不点击发布按钮。
-
-    Args:
-        page: CDP 页面对象。
-        content: 视频发布内容。
-
-    Raises:
-        PublishError: 填写失败。
-        UploadTimeoutError: 上传/处理超时。
-    """
-    if not content.video_path:
-        raise PublishError("视频不能为空")
-
-    # 导航到发布页
-    _navigate_to_publish_page(page)
-
-    # 点击"上传视频" TAB
-    _click_publish_tab(page, "上传视频")
-    time.sleep(1)
-
-    # 上传视频
-    operation_deadline = deadline or time.monotonic() + VIDEO_OPERATION_TIMEOUT_SECONDS
-    _upload_video(page, content.video_path, deadline=operation_deadline)
-
-    # 填写表单（不点击发布）
-    _fill_publish_video_form(
-        page,
-        content.title,
-        content.content,
-        content.tags,
-        content.schedule_time,
-        content.visibility,
-    )
-
-
-def click_publish_video_button(page: Page, *, deadline: float | None = None) -> None:
-    """点击视频发布按钮。
-
-    Args:
-        page: CDP 页面对象。
-    """
-    operation_deadline = deadline or time.monotonic() + VIDEO_OPERATION_TIMEOUT_SECONDS
-    _wait_for_publish_button_clickable(page, deadline=operation_deadline)
-    click_publish_button(page)
-    logger.info("视频发布完成")
-
-
-def _upload_video(page: Page, video_path: str, *, deadline: float) -> None:
-    """上传视频文件。"""
-    if not os.path.exists(video_path):
-        raise PublishError(f"视频文件不存在: {video_path}")
-
-    # 查找上传输入框
-    selector = UPLOAD_INPUT if page.has_element(UPLOAD_INPUT) else FILE_INPUT
-    page.set_file_input(selector, [video_path])
-
-    # 等待发布按钮可点击（视频处理完成）
-    _wait_for_publish_button_clickable(page, deadline=deadline)
-    logger.info("视频上传/处理完成")
-
-
-def _wait_for_publish_button_clickable(page: Page, *, deadline: float) -> None:
-    """等待发布按钮可点击（视频处理可能需要较长时间）。"""
-    logger.info("开始等待发布按钮可点击(视频)")
-
-    while time.monotonic() < deadline:
-        clickable = page.evaluate(
-            f"""
-            (() => {{
-                const host = document.querySelector(
-                    'xhs-publish-btn[is-publish="true"]'
-                );
-                if (host) {{
-                    return host.getAttribute('submit-disabled') !== 'true'
-                        && host.getAttribute('submit-loading') !== 'true';
-                }}
-                const btn = document.querySelector({_js_str(PUBLISH_BUTTON)});
-                if (!btn) return false;
-                const rect = btn.getBoundingClientRect();
-                if (rect.width === 0 || rect.height === 0) return false;
-                if (btn.disabled) return false;
-                if (btn.classList.contains('disabled')) return false;
-                return true;
-            }})()
-            """
-        )
-        if clickable:
-            return
-        time.sleep(1)
-
-    raise UploadTimeoutError("等待发布按钮可点击超时(100秒)")
-
-
-def _fill_publish_video_form(
-    page: Page,
-    title: str,
-    content: str,
-    tags: list[str],
-    schedule_time: str | None,
-    visibility: str,
-) -> None:
-    """填写视频表单（不点击发布）。"""
-    # 标题
-    page.input_text(TITLE_INPUT, title)
-    time.sleep(1)
-
-    # 正文 + 标签
-    content_selector = _find_content_element(page)
-    page.input_content_editable(content_selector, content)
-
-    # 回点标题
-    time.sleep(1)
-    page.click_element(TITLE_INPUT)
-
-    if tags:
-        _input_tags(page, content_selector, tags)
-    time.sleep(1)
-
-    # 定时发布
-    if schedule_time:
-        _set_schedule_publish(page, schedule_time)
-
-    # 可见范围
-    _set_visibility(page, visibility)
-
-    logger.info("视频表单填写完成，等待确认发布")
-
-
-def _js_str(s: str) -> str:
-    """将 Python 字符串转为 JS 字面量。"""
-    import json
-
-    return json.dumps(s)

package/skills/xiaohongshu/scripts/vendor/xhs/search.py

@@ -1,226 +0,0 @@
-"""搜索 Feeds，对应 Go xiaohongshu/search.go。"""
-
-from __future__ import annotations
-
-import json
-import logging
-import time
-
-from .cdp import Page
-from .errors import NoFeedsError
-from .human import sleep_random
-from .selectors import FILTER_BUTTON, FILTER_PANEL
-from .types import Feed, FilterOption
-from .urls import make_search_url
-
-logger = logging.getLogger(__name__)
-
-# 筛选选项映射表：{筛选组索引: [文本, ...]}
-_FILTER_OPTIONS: dict[int, list[str]] = {
-    1: ["综合", "最新", "最多点赞", "最多评论", "最多收藏"],
-    2: ["不限", "视频", "图文"],
-    3: ["不限", "一天内", "一周内", "半年内"],
-    4: ["不限", "已看过", "未看过", "已关注"],
-    5: ["不限", "同城", "附近"],
-}
-
-# 从 __INITIAL_STATE__ 提取搜索结果的 JS
-_EXTRACT_SEARCH_JS = """
-(() => {
-    const s = window.__INITIAL_STATE__?.search;
-    if (!s?.feeds) return "";
-    const data = s.feeds.value !== undefined ? s.feeds.value : s.feeds._value;
-    return data ? JSON.stringify(data) : "";
-})()
-"""
-
-
-def _find_internal_option(group_index: int, text: str) -> tuple[int, str]:
-    """查找内部筛选选项。
-
-    Returns:
-        (filters_index, text)
-
-    Raises:
-        ValueError: 未找到匹配的选项。
-    """
-    options = _FILTER_OPTIONS.get(group_index)
-    if not options:
-        raise ValueError(f"筛选组 {group_index} 不存在")
-
-    if text in options:
-        return group_index, text
-
-    raise ValueError(f"在筛选组 {group_index} 中未找到 '{text}'，有效值: {options}")
-
-
-def _convert_filters(filter_opt: FilterOption) -> list[tuple[int, str]]:
-    """将 FilterOption 转换为内部 (filters_index, text) 列表。"""
-    result: list[tuple[int, str]] = []
-
-    if filter_opt.sort_by:
-        result.append(_find_internal_option(1, filter_opt.sort_by))
-    if filter_opt.note_type:
-        result.append(_find_internal_option(2, filter_opt.note_type))
-    if filter_opt.publish_time:
-        result.append(_find_internal_option(3, filter_opt.publish_time))
-    if filter_opt.search_scope:
-        result.append(_find_internal_option(4, filter_opt.search_scope))
-    if filter_opt.location:
-        result.append(_find_internal_option(5, filter_opt.location))
-
-    return result
-
-
-def search_feeds(
-    page: Page,
-    keyword: str,
-    filter_option: FilterOption | None = None,
-) -> list[Feed]:
-    """搜索 Feeds。
-
-    Args:
-        page: CDP 页面对象。
-        keyword: 搜索关键词。
-        filter_option: 可选筛选条件。
-
-    Raises:
-        NoFeedsError: 没有捕获到搜索结果。
-        ValueError: 筛选选项无效。
-    """
-    search_url = make_search_url(keyword)
-    page.navigate(search_url)
-    page.wait_for_load()
-    page.wait_dom_stable()
-
-    # 等待 __INITIAL_STATE__.search.feeds 有数据
-    _wait_for_search_feeds(page)
-
-    # 应用筛选条件（若有）
-    if filter_option:
-        internal_filters = _convert_filters(filter_option)
-        if internal_filters:
-            _apply_filters(page, internal_filters)
-
-    # 提取搜索结果
-    result = page.evaluate(_EXTRACT_SEARCH_JS)
-    if not result:
-        raise NoFeedsError()
-
-    feeds_data = json.loads(result)
-    if not feeds_data:
-        raise NoFeedsError()
-
-    return [Feed.from_dict(f) for f in feeds_data]
-
-
-def _wait_for_search_feeds(page: Page, timeout: float = 15.0) -> None:
-    """等待 __INITIAL_STATE__.search.feeds 有数据。
-
-    Raises:
-        NoFeedsError: 超时仍无数据。
-    """
-    deadline = time.monotonic() + timeout
-    while time.monotonic() < deadline:
-        result = page.evaluate(_EXTRACT_SEARCH_JS)
-        if result:
-            try:
-                if json.loads(result):
-                    return
-            except json.JSONDecodeError:
-                pass
-        time.sleep(0.3)
-    raise NoFeedsError()
-
-
-def _apply_filters(page: Page, filters: list[tuple[int, str]]) -> None:
-    """应用筛选条件。
-
-    在单次 evaluate 调用内完成：点击筛选按钮 → 等待面板 → 按文本点击各选项
-    → 等待搜索结果刷新。
-    避免多次 WebSocket 连接导致面板关闭的时序问题。
-    """
-    filter_js_list = ", ".join(
-        f'[{idx}, {json.dumps(text)}]' for idx, text in filters
-    )
-
-    # 记录当前 feeds 快照，用于检测结果是否已刷新
-    snapshot_js = "JSON.stringify(window.__INITIAL_STATE__?.search?.feeds?.value ?? window.__INITIAL_STATE__?.search?.feeds?._value ?? null)"
-
-    script = f"""
-(() => {{
-  return new Promise((resolve, reject) => {{
-    const btn = document.querySelector('div.filter');
-    if (!btn) {{ reject('筛选按钮不存在'); return; }}
-
-    // 记录点击前的 feeds 快照（用于判断结果已刷新）
-    const snapshot = {snapshot_js};
-    btn.click();
-
-    const items = [{filter_js_list}];
-    let attempts = 0;
-
-    // 等待筛选面板出现
-    const panelTimer = setInterval(() => {{
-      const wrapper = document.querySelector('div.filters-wrapper');
-      if (!wrapper) {{
-        if (++attempts > 50) {{ clearInterval(panelTimer); reject('筛选面板等待超时'); }}
-        return;
-      }}
-      clearInterval(panelTimer);
-
-      // 依次点击各筛选项
-      for (const [groupIdx, text] of items) {{
-        const group = wrapper.querySelectorAll('div.filters')[groupIdx - 1];
-        if (!group) {{ reject('筛选组 ' + groupIdx + ' 不存在'); return; }}
-        const tag = Array.from(group.querySelectorAll('div.tags'))
-          .find(el => el.textContent.trim() === text);
-        if (!tag) {{ reject('选项不存在: ' + text); return; }}
-        tag.click();
-      }}
-
-            const selected = items.every(([groupIdx, text]) => {{
-                const group = wrapper.querySelectorAll('div.filters')[groupIdx - 1];
-                const tag = Array.from(group.querySelectorAll('div.tags'))
-                    .find(el => el.textContent.trim() === text);
-                return tag && (
-                    tag.classList.contains('active')
-                    || tag.classList.contains('selected')
-                    || tag.getAttribute('aria-selected') === 'true'
-                    || tag.querySelector('input:checked')
-                );
-            }});
-            if (!selected) {{ reject('筛选选项未全部生效'); return; }}
-
-            // 等待最终搜索结果刷新并稳定，忽略多筛选的中间响应。
-      let refreshAttempts = 0;
-            let last = snapshot;
-            let stableTicks = 0;
-            let changed = false;
-      const refreshTimer = setInterval(() => {{
-        const current = {snapshot_js};
-                if (current !== snapshot) changed = true;
-                if (changed && current === last) stableTicks++;
-                else stableTicks = 0;
-                last = current;
-                if (changed && stableTicks >= 8) {{
-          clearInterval(refreshTimer);
-          resolve(null);
-          return;
-        }}
-        if (++refreshAttempts > 60) {{
-          clearInterval(refreshTimer);
-                    reject('筛选结果刷新超时');
-        }}
-      }}, 100);
-    }}, 100);
-  }});
-}})()
-"""
-    try:
-        page.evaluate(script)
-    except Exception as e:
-        raise ValueError(f"应用筛选失败: {e}") from e
-
-    # 等待 __INITIAL_STATE__ 中有新数据
-    _wait_for_search_feeds(page)