PDF to Markdown & Document Parser

io.github.fernandoguiraud16-coderv1.0.0更新於 Oct 6, 2026

Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR.

已驗證Streamable HTTP可網頁執行Files & StorageKnowledge & Memory

概覽

AI 產生的概覽

讓助理把 PDF、Office 文件和掃描檔轉成 Markdown、表格與 RAG 分塊，並支援 OCR。

功能
這是一個遠端 MCP 伺服器，提供 Apify 的文件處理工具。它能把 PDF、Word、Excel、PowerPoint 檔案以及掃描檔轉換為 Markdown，將表格擷取成 Excel 活頁簿，並產生適合 RAG 的 JSONL 分塊。掃描輸入會套用 OCR。它屬於同一個端點下更大一組 Apify 資料工具。
適用情境
當助理需要讀取或重新整理文件時使用：把報告轉成 Markdown、從 PDF 擷取表格，或為檢索流程準備素材。它適合文件匯入類工作流程，而不是通用的網頁或程式碼任務。
執行需求
遠端 MCP 端點位於 mcp.apify.com；未宣告本機執行環境或套件。需要 Apify 帳號與 API 權杖，在文件範例中透過 APIFY_TOKEN 環境變數提供。需要網路存取，並依結果計費。
安裝前請注意
處理透過 Apify 依結果計費，每處理一份文件、表格或分塊都會產生費用；免費方案包含每月額度。需要 Apify API 權杖，應妥善保密。文件會上傳到第三方雲端服務處理，未確認服務條款前不要傳送機密或受監管文件。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 PDF to Markdown & Document Parser，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "document-to-markdown-tables": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fguiraud/document-to-markdown-tables"
    }
  }
}

README

Data Tools: clean web data for developers and AI agents

Ready-to-run Python examples for pay-per-use Apify Actors that turn search trends, news, competitor ads, documents, websites, YouTube, TikTok and Instagram videos and audio into clean JSON, Markdown, CSV and Excel.

🌐 Website: https://fernandoguiraud16-coder.github.io/data-tools/

Each example is a single short script plus a sample-output.json from a real cloud run, so you can see exactly what you get before running anything.

[Sample output of the TikTok Transcript Scraper: real results from a cloud run]

Examples

ExampleWhat it doesActor
google-trendsCompare terms over time, export to CSV, see rising searches and what's trending nowGoogle Trends Scraper
google-newsSave news articles as Markdown files, or get alerts for new stories onlyGoogle News Scraper
google-ads-transparencyEvery Google Search, Display and YouTube ad of a competitor, longest-running first, and alerts for new adsGoogle Ads Transparency Scraper
trends-to-newsFind the fastest rising searches on a topic and the news that explains themTrends + News
pdf-to-markdownPDF, Word, Excel, PowerPoint and scans to Markdown, or to RAG chunks in JSONLPDF to Markdown Extractor
pdf-table-extractorEvery table in a PDF to an Excel workbook, one sheet per tablePDF Table Extractor
tech-stack-whoisEnrich a list of company domains: CMS, email provider, hosting, age, security gradeTech Stack Detector & WHOIS
bulk-whoisFind available and soon-to-expire domains in a listBulk WHOIS Lookup
audio-transcriptionAudio or video to text and SRT subtitles, 99 languagesAudio & Video Transcription
podcast-transcriptsTranscribe only the new episodes of your favourite podcastsPodcast Transcript Scraper
youtube-transcriptsYouTube videos, Shorts, whole channels and playlists to Markdown with timestamps, SRT or textYouTube Transcript Scraper
mcp-agentsUse all of these as tools in Claude, Cursor or any MCP clientApify MCP server

Also in the family (same engine as Audio & Video Transcription, so the audio-transcription example works with them too):

ActorWhat it does
Instagram Reels Transcript ScraperInstagram Reels to text with author, date, likes and comments ($0.009 per Reel)
TikTok Transcript ScraperTikTok videos or whole accounts to text with views and likes ($0.009 per video)
Video to Text TranscriberTikTok, Instagram, X, Facebook and MP4 links to transcripts and readable subtitles, per minute
SRT Subtitle GeneratorBroadcast-formatted SRT/VTT subtitles (42 characters, 2 lines)

For AI agents

  • MCP: every tool is listed in the official MCP registry as io.github.fernandoguiraud16-coder/<tool> and served at https://mcp.apify.com/?tools=fguiraud/<tool>. See examples/mcp-agents.
  • Agent skills: npx skills add fernandoguiraud16-coder/data-tools installs 4 skills for Claude Code, Codex, Cursor and other coding agents.
  • llms.txt: a short index of all tools for LLMs.

Quick start

  1. Create a free Apify account and copy your API token from Console → Settings → API & Integrations.

  2. Install the client and set the token:

    bash
    pip install -r requirements.txtexport APIFY_TOKEN=your_token          # Windows PowerShell: $env:APIFY_TOKEN="your_token"

  3. Run any example:

    bash
    python examples/google-trends/compare_terms.py "chatgpt, gemini, claude" --geo US

Pricing

All Actors are pay per result: you pay a fraction of a cent per item (term, article, ad, document, domain, video or audio minute), and failed or empty items are not charged. Apify's free plan includes monthly credits, enough to try every example. Exact prices are on each Actor's page.

Support

Found a bug or need a feature? Open an issue on the Actor's page in the Apify Store (replies within 48 hours), or an issue in this repository for problems with the examples.

License

The example code is MIT licensed: copy it into your own projects.

來源：README.md，提交 2c4f1e0

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Oct 6, 2026