Douyin 抖音, TikTok & X (Twitter) Article to Markdown (MCP)
Pricing
from $5.00 / 1,000 extracted content items
Douyin 抖音, TikTok & X (Twitter) Article to Markdown (MCP)
Extract full X (Twitter) long-form Articles, watermark-free Douyin (抖音) & TikTok videos/images, and YouTube transcripts into clean Markdown for AI Agents, Obsidian & MCP. Zero cookies required.
Pricing
from $5.00 / 1,000 extracted content items
Rating
0.0
(0)
Developer
PowerAGY Labs
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
6 days ago
Last modified
Categories
Features
Share
Douyin (抖音) & X (Twitter) Article to Markdown Scraper (MCP & x402 Ready)
Extract full long-form X (Twitter) Articles & Threads, watermark-free Douyin (抖音) & TikTok videos/photo galleries, Xiaohongshu (RedNote) notes, YouTube/Bilibili transcripts with timestamps, and anti-bot web articles into clean, LLM-ready Markdown + Structured JSON in one call.
- Zero Cookies or Login Required: Pure-algorithm
x-secsdk-web-signaturesigning for Douyin (v.douyin.com) and GraphQL extraction for X Articles — no account ban risk, no proxy setup required. - 50%+ Cheaper Than Single-Platform Scrapers: Just $0.005 per extracted item ($5.00 / 1,000 results) with automatic 24h deduplication cache.
- Built for AI Agents, MCP, n8n, Make & Obsidian: Returns both clean
markdown(ready for LLM context windows or Obsidian vaults) and structured metadata (media_urls,transcript,segments, engagement counts).
Supported Platforms & Capabilities
| Platform | URL Examples | What You Get |
|---|---|---|
| Douyin (抖音) | https://v.douyin.com/...https://www.douyin.com/video/...https://www.douyin.com/note/... | Watermark-free MP4 stream URLs, high-res gallery images (JPEG/PNG/WebP), full caption, author info, likes/saves/comments/shares. |
| X (Twitter) Articles & Posts | https://x.com/user/status/...https://twitter.com/user/status/... | Full 10,000+ word X Articles rendered with # / ## headings, lists, code blocks & blockquotes, NoteTweets, quoted tweets, media URLs, and engagement stats. |
| YouTube & Bilibili (哔哩哔哩) | https://www.youtube.com/watch?v=...https://www.bilibili.com/video/BV... | Video metadata, cover image, full deduplicated plain-text transcript, and timestamped subtitle segments ([{"start": 1.0, "end": 3.5, "text": "..."}]). |
| TikTok & Xiaohongshu (小红书 / RedNote) | https://vt.tiktok.com/...https://www.xiaohongshu.com/explore/... | Post title, full note text/caption, author details, and media/image URLs. |
| GitHub & Anti-Bot Web | https://github.com/owner/repoAny blog, news, or documentation URL | Clean semantic Markdown stripped of ads, navbars, scripts, and Cloudflare bot-wall noise. |
Input Parameters
{"urls": ["https://x.com/ai_chuhai/status/2037437653071835440","https://v.douyin.com/0kH2cQVrf0o/","https://github.com/modelcontextprotocol/servers"],"include_transcript": true,"use_cache": true}
urls(array of strings, required): List of URLs or raw mobile share texts (e.g."4.66 复制打开抖音... https://v.douyin.com/...").include_transcript(boolean, default:true): Extract full video subtitles and timestamped segments for YouTube/Bilibili/TikTok videos.use_cache(boolean, default:true): Instant<5msresponse if the same URL was extracted within the last 24 hours.
Output Example (Dataset Item)
{"ok": true,"url": "https://v.douyin.com/0kH2cQVrf0o/","canonical_url": "https://www.douyin.com/note/7703513872124769984","platform": "douyin","content_type": "gallery","content_id": "7703513872124769984","title": "ClaudeCode最该开的设置","author": "AI进化论","text": "Claude Code 提示缓存 TTL 配置指南...","markdown": "# ClaudeCode最该开的设置\n\n- **Platform**: Douyin (gallery)\n- **Author**: AI进化论\n...","transcript": null,"segments": [],"media_urls": ["https://p3-pc-sign.douyinpic.com/tos-cn-i-0813/..."],"cover_url": "https://p3-pc-sign.douyinpic.com/tos-cn-i-0813/...","duration_seconds": 0.0,"extraction_tier": "douyin_sec_salt_md5_signature","metadata": {"aweme_id": "7703513872124769984","digg_count": 1420,"collect_count": 890,"comment_count": 64}}
Use with AI Agents (MCP) & Automation (n8n / Make / cURL)
1. Synchronous REST API Call (Get Markdown in 1 HTTP Request)
curl -X POST "https://api.apify.com/v2/acts/poweragy~omni-extract-mcp/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \-H "Content-Type: application/json" \-d '{"urls": ["https://x.com/ai_chuhai/status/2037437653071835440"]}'
2. Use via Apify MCP Server (Claude Desktop / Cursor / Windsurf)
Connect poweragy/omni-extract-mcp directly to your AI Agent via https://mcp.apify.com/?actors=poweragy/omni-extract-mcp!