AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Bilibili Source Fetcher

Pulls real, citable Bilibili video data — stats, metadata, tags and full danmaku — through login-free API calls so numbers are never guessed.

Data & AnalyticsIntermediate★ 1,519⑂ 235AI score 8/10Last updated: Nov 8, 2026

What it does

  • Accepts whatever a user pastes — BVID, av number, b23.tv short link or full URL — normalizes it and returns one JSON object from a single view/detail call.
  • Collects views, likes, coins, favorites, shares, replies, danmaku count, UP name/mid/fans, partition, tags, duration and per-part cid list for multi-part videos.
  • Downloads full danmaku (time-synced overlay comments) so you can analyze where viewers reacted, not just how many commented.
  • Enforces data-honesty rules: always cite fetched_at, never estimate (write "未获取/未核实"), plus built-in handling of the local-proxy problem, browser UA/Referer to dodge HTTP 412, retries, and CJK sorting pitfalls.
  • Documents verified limits: subtitles and favorites enumeration are login-gated with no bypass, and the subtitle script asks before touching your browser session.

Who it's for

  • Marketers and researchers benchmarking Chinese-language video content.
  • Knowledge-base builders who need sourced, timestamped metrics instead of recalled numbers.
  • Creators and agencies who must explain video performance with real data.

Example uses

  1. "Analyze why this BV video performed well" — the skill fetches live stats and danmaku, then grounds the write-up in like/view ratios and audience reactions.
  2. Archive a set of competitor videos as JSON records with fetched_at stamps for a research doc.
  3. For a multi-part tutorial, resolve each part's cid and pull only that part's danmaku to find hype or drop-off moments.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/bilibili-source/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the bilibili-source folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/bilibili-source/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git /tmp/ccs && mkdir -p ~/.claude/skills && cp -r /tmp/ccs/bilibili-source ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, WSL or Git Bash on Windows).
  2. Clone the repo: git clone https://github.com/daymade/claude-code-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r claude-code-skills/bilibili-source ~/.claude/skills/
  5. Make the scripts executable: chmod +x ~/.claude/skills/bilibili-source/scripts/*.sh
  6. Make sure curl and python3 are available (optionally uv, and yt-dlp for the subtitle path).
  7. Verify it works: run ~/.claude/skills/bilibili-source/scripts/bili-selftest.sh and check for PASS rows.
  8. Restart Claude Code, then ask something like "fetch the data for this Bilibili video: <link>".
  9. Only use the subtitle/favorites features if you are comfortable with the script reading your logged-in Bilibili cookies.
View source on GitHub ↗License: MIT