PDF to Markdown & Document Parser

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

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

已验证Streamable HTTP可网页运行Files & StorageKnowledge & Memory

概览

AI 生成的概览

让助手把 PDF、Office 文档和扫描件转换为 Markdown、表格和 RAG 分块，并支持 OCR。

功能
这是一个远程 MCP 服务器，提供 Apify 的文档处理工具。它可以把 PDF、Word、Excel、PowerPoint 文件以及扫描件转换为 Markdown，把表格提取为 Excel 工作簿，并生成适合 RAG 的 JSONL 分块。对扫描输入会应用 OCR。它属于同一端点下更大的一组 Apify 数据工具。
适用场景
当助手需要读取或重构文档时使用：把报告转成 Markdown、从 PDF 中提取表格，或为检索流程准备素材。它适合文档摄取类工作流，而不是通用的网页或代码任务。
运行要求
远程 MCP 端点位于 mcp.apify.com；未声明本地运行时或软件包。需要 Apify 账号和 API 令牌，在文档示例中通过 APIFY_TOKEN 环境变量提供。需要网络访问，并按结果计费。
安装前请注意
处理通过 Apify 按结果计费，每处理一个文档、表格或分块都会产生费用；免费方案包含每月额度。需要 Apify API 令牌，应妥善保密。文档会上传到第三方云服务处理，未经确认服务条款前不要发送机密或受监管文件。

安装

在 SourceWeft 中

  1. 打开 控制台中的 PDF to Markdown & Document Parser，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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.

来源：README.md，提交 2c4f1e0

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v1.0.0最新Oct 6, 2026