bilibili-subtitle-fetcher-skill_suyuan2022_skill

This skill searches Bilibili, downloads subtitles, and converts them to Markdown for easy analysis and sharing.
  • Python

8

GitHub Stars

8

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill jackspace/claudeskillz --skill bilibili-subtitle-fetcher-skill_suyuan2022

  • bili_simple.py12.8 KB
  • config.json.example591 B
  • install.sh1.3 KB
  • LICENSE1.1 KB
  • README.md150 B
  • SKILL.json3.3 KB
  • SKILL.md3.0 KB
  • SKILL.md.backup3.0 KB

Overview

This skill searches Bilibili (bilibili.com) for videos, downloads Chinese subtitles, and converts them into Markdown with timestamps. It supports keyword search, single-video processing, and concurrent batch downloads with intelligent file naming. The tool is designed to streamline subtitle extraction for analysis, summarization, or documentation workflows.

How this skill works

The skill queries Bilibili search and video APIs to retrieve video metadata, then fetches subtitle tracks via the player subtitle endpoint. Subtitles are parsed, cleaned, and emitted as UTF-8 Markdown files that include timestamps and text. For batch jobs it runs up to three concurrent downloads with randomized delays and timeout handling to reduce request throttling.

When to use it

  • You need to extract readable transcripts from Bilibili videos for research or notes.
  • You want to bulk-download subtitles from multiple BV IDs for corpus creation.
  • You want Markdown-formatted subtitles ready for summarization or editing.
  • You need to pull subtitles before running topic extraction, QA, or timeline analysis.
  • You need to automate subtitle retrieval as part of a content pipeline.

Best practices

  • Provide valid SESSDATA, bili_jct, and DedeUserID cookies in the config file to authenticate subtitle requests.
  • Limit batch runs to under 10 videos at once and respect the built-in 1–3s randomized delay.
  • Store outputs in the default subtitles directory or set OUTPUT_DIR to a controlled location.
  • Re-check cookie values every ~30 days as SESSDATA can expire and cause failures.
  • Validate subtitle quality after download because auto-generated captions may contain errors.

Example use cases

  • Search for Python tutorial videos, download subtitles, then summarize content with a summarizer skill.
  • Download subtitles for a set of BV IDs into Markdown for annotations and lecture notes.
  • Run a batch job to collect transcripts for NLP keyword extraction and topic modeling.
  • Fetch a single video’s subtitles to create a time-stamped study guide or script.
  • Pipeline subtitles to document conversion tools to produce PDFs or DOCX meeting notes.

FAQ

Place SESSDATA, bili_jct, and DedeUserID in the config file at ~/.claude/skills/bilibili-subtitle-fetcher/config.txt; obtain values from your browser cookies after logging into bilibili.com.

Can I change where subtitle files are saved?

Yes. Use the OUTPUT_DIR environment variable when running commands, e.g. OUTPUT_DIR=/path/to/dir python3 bili_simple.py download BVxxxxx.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational