compare

LinkDigest vs MediaCrawler

MediaCrawler is free, open source, searches by keyword and collects comments — with your own logged-in browser session and no transcription or OCR. LinkDigest is hosted, needs nothing from you, and returns transcript, OCR and image descriptions per link. Dated comparison.

Competitor rows from their public docs on 2026-09-12; tell us if something changed. MediaCrawler rows from its GitHub README (about 65k stars). LinkDigest rows are computed from the same constants as the pricing page and the coverage table. “” means not stated in what we checked.

FeatureLinkDigestMediaCrawler
Xiaohongshu / DouyinYes — Xiaohongshu image and video notes; Douyin video and 图文 image notes.Yes.
Other platformsYouTube, TikTok, X, web pages. Instagram wired but not verified; Bilibili blocked (HTTP 412).Several Chinese platforms — see its README.
OCR of images and framesYes — every image described and read for on-screen text; frames sampled from video.No.
Transcript (ASR)Yes — native captions where a platform publishes them, otherwise SenseVoice ASR with timecodes.No.
Cookies or login from youXiaohongshu: no login, no cookies. Douyin runs on our session; you supply nothing.Yes — it drives your own logged-in browser session. The account at risk is yours.
Search and commentsNo — one post per link.Yes — crawls by keyword and collects comments.
BatchNot yet — one call per link today. A batch endpoint is being built.Yes — a keyword run collects many posts.
WebhooksNo. Long videos return a job id you poll.Not applicable — runs on your machine.
degraded fieldYes — a `degraded` array names what did not read fully.No.
Failed reads freeYes — a digest that read nothing is not charged.Free regardless; your time and your account.
Cached links freeYes — anything anyone already digested is free.Not applicable.
Price: a typical image note1 credit ≈ $0.018 ($9 for 500 credits a month)Free (open source).
Price: a 10-minute video21 credits ≈ $0.378 (2 per started minute, plus the base credit)Free, but no transcript comes back.

Where MediaCrawler is better

  • Free and open source. If you have the session, the machine and the time, nothing is cheaper.
  • Search: it crawls by keyword, which LinkDigest does not do at all. Discovering posts is its job; reading a known post is ours.
  • Comments, which LinkDigest does not collect.
  • You own the code and the data path end to end.

Where LinkDigest is better

  • Nothing of yours on the line. MediaCrawler needs your logged-in browser session; Xiaohongshu here is read with no account, and Douyin runs on our session.
  • The content, not just the metadata: a transcript with timecodes and OCR of every image and sampled frame. MediaCrawler returns the post's fields and media URLs; the reading is left to you.
  • Hosted: no browser, no Playwright, no cookie refresh. An MCP server for Claude Code and Cursor, and a REST call.
  • A `degraded` field, a free failed read, and a shared cache.

try the difference

One call, on a real link

curl -X POST https://linkdigest.dev/api/v1/digest \
  -H "Authorization: Bearer ld_live_..." \
  -H "Content-Type: application/json" \
  -d '{"url": "https://xhslink.cn/o/...", "format": "markdown"}'