extract
Extract Structured Website Data with Playwright
Dynamic websites make reliable data extraction difficult. This skill discovers selectors, handles common loading patterns, and produces reusable Playwright scripts with structured output.
安裝前請停止並請求確認。
請審查安裝計畫，並在變更檔案前取得使用者明確同意。
使用我的智慧代理安裝
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "extract" from https://skillstore.io/skills/actionbook-extract.md and its manifest at https://skillstore.io/api/skills/actionbook-extract/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
測試它
正在使用「extract」。 Extract product name, current price, and product link from the first five catalog pages.
預期結果:
Created a reusable Playwright script and a JSON dataset containing 240 products. Validation found complete names and links, with three missing prices.
正在使用「extract」。 Collect article titles and authors from an infinite-scroll publication feed.
預期結果:
- Generated a bounded scroll workflow that stops after three rounds without new records.
- Extracted 618 unique articles and checked the first and last visible records.
- Saved the dataset and reported the script path, data path, and record count.
正在使用「extract」。 Export a public results table to CSV with date, category, and score columns.
預期結果:
Produced a CSV with the requested columns and a rerunnable extraction script. All declared fields exceeded the configured completeness threshold.
安全審計
高風險The Playwright eval APIs, Markdown backticks, and reconnaissance matches are false positives rather than dynamic or shell code execution. The fixed output path can overwrite an existing file. Untrusted webpage content and shell placeholder interpolation create additional injection risks that require safeguards.
已確認的安全問題 (2)
能力複核項目 (2)
這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。
風險因素
⚡ 包含腳本 (5)
⚙️ 外部命令 (50)
📁 檔案系統存取 (2)
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/actionbook-extract/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/actionbook-extract?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/actionbook-extract?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/actionbook-extract/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/actionbook-extract.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>學術引用 (APA · BibTeX · CFF)
APA 引用
actionbook. (2026). extract security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/actionbook-extract/audits/1BibTeX 引用
@techreport{actionbook-actionbook-extract-2026,
author = {actionbook},
title = {extract security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/actionbook-extract/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "extract security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "actionbook"
date-released: "2026-08-15"
url: "https://skillstore.io/skills/actionbook-extract/audits/1"
identifiers:
- type: other
value: "skillstore:actionbook-extract:audit:1"
description: "Skillstore immutable audit report identifier"
比較變體
3 個可安裝變體每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。
為何此變體排名第一
Skillstore 評分
評分依據 證據置信度: 中你可以打造什麼
Collect Product Catalogs
Extract product names, prices, availability, and links from paginated or dynamically loaded catalog pages.
Build Research Datasets
Collect titles, authors, dates, and metadata from public search results or publication listings.
Monitor Operational Listings
Create a repeatable script for collecting authorized job, property, event, or dashboard records.
試試這些提示
Extract [fields] from [URL]. Save the records as [JSON or CSV] and provide a reusable Playwright script.
Extract [fields] from every results page at [URL]. Stop after [maximum pages] and validate the first and last records.
Extract [fields] from [URL]. Detect hydration, infinite scrolling, or virtualization, then use bounded waits and scrolling to collect unique records.
Build and run an authorized extractor for [URL]. Use stable selectors, protect existing files, enforce limits, and report completeness checks and caveats.
最佳實務
- Use stable semantic selectors and verify them against a small page sample before full extraction.
- Set maximum pages, scrolls, and timeouts for every dynamic collection loop.
- Use authorized targets and review extracted fields for personal or sensitive information.
避免
- Do not bypass authentication, CAPTCHAs, access controls, or website restrictions.
- Do not interpolate untrusted URLs or selectors into shell commands without robust argument handling.
- Do not overwrite existing output files without explicit user confirmation.
常見問題
What does this skill produce?
Does the generated script require Actionbook?
Can it handle infinite scrolling?
Can it extract authenticated pages?
How does it validate results?
What happens when selectors stop working?
開發者詳細資訊
作者
actionbook授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
7fc57fb4532f9ea45a9e19def4e06cab71f7343a
維護新鮮度
2026/8/16
使用量
0 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md