bilibili-to-doc

Name: bilibili-to-doc
Author: programmerloverun

98stars4forks

How to install bilibili-to-doc?

programmerloverun/bilibili-to-doc/bilibili-to-doc

$npx -y skills add programmerloverun/bilibili-to-doc --skill bilibili-to-doc

Installs into the current project.

Summary

This skill should be used when the user asks to "提取B站视频", "B站视频转文档", "bilibili视频提取", "将B站视频转文字", or provides a bilibili.com video URL and wants to extract its content into a structured Markdown document. Automatically downloads AI subtitles (Chinese) via yt-dlp, parses SRT, and g

Files · 1

View on GitHub

SKILL.md

1	# Bilibili Video to Document (B站视频提取文档)
2
3	## Overview
4
5	Extract Bilibili video content into a structured Markdown document by: (1) downloading AI-generated subtitles via yt-dlp with browser cookies, (2) parsing the SRT subtitle file, (3) reorganizing the transcript into a logical, well-structured document with sections, tables, and code blocks.
6
7	## When to Use
8
9	Trigger this skill when the user:
10	- Provides a bilibili.com video URL and asks to extract/converter it to a document
11	- "提取B站视频内容" / "B站视频转文档" / "将视频转成文章"
12	- "把这个B站视频整理成笔记"
13	- "generate document from Bilibili video"
14
15	## Prerequisites
16
17	- `yt-dlp` must be installed: `pip3 install yt-dlp`
18	- Browser cookies are needed for Bilibili access (Chrome or other browser)
19	- Python 3.10+ for subtitle processing
20
21	## Workflow
22
23	### Step 1: Download Subtitles
24
25	Use yt-dlp with browser cookies to download the AI Chinese subtitles:
26
27	```bash
28	yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
29	--write-subs --sub-lang ai-zh \
30	--skip-download \
31	-o "/tmp/bilibili_output"
32	```
33
34	Also get the video title:
35
36	```bash
37	yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
38	--print "%(title)s" --skip-download 2>&1 \| tail -1
39	```
40
41	If `chrome` browser cookies are not available, try `safari`, `firefox`, or `edge`.
42
43	### Step 2: Parse SRT and Generate Document
44
45	Read the downloaded `.ai-zh.srt` file, then:
46
47	1. Strip SRT formatting: Remove sequence numbers, timestamps, empty lines
48	2. Merge consecutive lines: Combine fragmented subtitle lines into complete sentences
49	3. Identify logical sections: The AI should read through the full transcript and identify:
50	- Topic/theme divisions
51	- Step-by-step procedures
52	- Key concepts and definitions
53	- Configuration examples / code blocks
54	4. Structure the document with proper heading hierarchy
55
56	### Step 3: Document Structure
57
58	Generate a Markdown document following this structure (from reference template):
59
60	```markdown
61	# {Video Title}
62
63	> 来源：B站视频 {BV号} \| 主讲：{author}
64
65	---
66
67	## 一、{Topic Overview}
68
69	{Summary of what the video covers}
70
71	## 二、{Main Content Sections}
72
73	{Organized by logical topic divisions}
74
75	## N、总结
76
77	{Key takeaways}
78	```
79
80	### Step 4: Save Output
81
82	Save to the user's Desktop by default: `~/Desktop/{Video_Title}.md`
83
84	## Document Writing Guidelines
85
86	- Preserve technical details: Configuration code, SQL, JSON, YAML, shell commands should be formatted in code blocks
87	- Use tables for comparisons: Feature comparisons, parameter lists, pros/cons
88	- Bullet lists for key points: Use hierarchical bullet points for nested concepts
89	- Add section numbers: Use Chinese numbered sections (一、二、三...) for main divisions
90	- Keep code accurate: If the speaker mentions specific config/code, represent it faithfully
91	- Add explanatory notes: Fill in gaps where the spoken word might be ambiguous without visuals
92	- Trim filler content: Remove repeated phrases, verbal fillers (嗯, 啊, 这个), and self-promotion segments
93	- Mark at the end: Add a disclaimer that the document is AI-generated from subtitles
94
95	## Reference
96
97	See `references/doc-template.md` for the full document template.

People who liked this also viewed

6 picks

Type

bilibili-to-doc

98stars4forks

View on GitHub

How to install bilibili-to-doc?

programmerloverun/bilibili-to-doc/bilibili-to-doc

$npx -y skills add programmerloverun/bilibili-to-doc --skill bilibili-to-doc

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Bilibili Video to Document (B站视频提取文档)
2
3	## Overview
4
5	Extract Bilibili video content into a structured Markdown document by: (1) downloading AI-generated subtitles via yt-dlp with browser cookies, (2) parsing the SRT subtitle file, (3) reorganizing the transcript into a logical, well-structured document with sections, tables, and code blocks.
6
7	## When to Use
8
9	Trigger this skill when the user:
10	- Provides a bilibili.com video URL and asks to extract/converter it to a document
11	- "提取B站视频内容" / "B站视频转文档" / "将视频转成文章"
12	- "把这个B站视频整理成笔记"
13	- "generate document from Bilibili video"
14
15	## Prerequisites
16
17	- `yt-dlp` must be installed: `pip3 install yt-dlp`
18	- Browser cookies are needed for Bilibili access (Chrome or other browser)
19	- Python 3.10+ for subtitle processing
20
21	## Workflow
22
23	### Step 1: Download Subtitles
24
25	Use yt-dlp with browser cookies to download the AI Chinese subtitles:
26
27	```bash
28	yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
29	--write-subs --sub-lang ai-zh \
30	--skip-download \
31	-o "/tmp/bilibili_output"
32	```
33
34	Also get the video title:
35
36	```bash
37	yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
38	--print "%(title)s" --skip-download 2>&1 \| tail -1
39	```
40
41	If `chrome` browser cookies are not available, try `safari`, `firefox`, or `edge`.
42
43	### Step 2: Parse SRT and Generate Document
44
45	Read the downloaded `.ai-zh.srt` file, then:
46
47	1. Strip SRT formatting: Remove sequence numbers, timestamps, empty lines
48	2. Merge consecutive lines: Combine fragmented subtitle lines into complete sentences
49	3. Identify logical sections: The AI should read through the full transcript and identify:
50	- Topic/theme divisions
51	- Step-by-step procedures
52	- Key concepts and definitions
53	- Configuration examples / code blocks
54	4. Structure the document with proper heading hierarchy
55
56	### Step 3: Document Structure
57
58	Generate a Markdown document following this structure (from reference template):
59
60	```markdown
61	# {Video Title}
62
63	> 来源：B站视频 {BV号} \| 主讲：{author}
64
65	---
66
67	## 一、{Topic Overview}
68
69	{Summary of what the video covers}
70
71	## 二、{Main Content Sections}
72
73	{Organized by logical topic divisions}
74
75	## N、总结
76
77	{Key takeaways}
78	```
79
80	### Step 4: Save Output
81
82	Save to the user's Desktop by default: `~/Desktop/{Video_Title}.md`
83
84	## Document Writing Guidelines
85
86	- Preserve technical details: Configuration code, SQL, JSON, YAML, shell commands should be formatted in code blocks
87	- Use tables for comparisons: Feature comparisons, parameter lists, pros/cons
88	- Bullet lists for key points: Use hierarchical bullet points for nested concepts
89	- Add section numbers: Use Chinese numbered sections (一、二、三...) for main divisions
90	- Keep code accurate: If the speaker mentions specific config/code, represent it faithfully
91	- Add explanatory notes: Fill in gaps where the spoken word might be ambiguous without visuals
92	- Trim filler content: Remove repeated phrases, verbal fillers (嗯, 啊, 这个), and self-promotion segments
93	- Mark at the end: Add a disclaimer that the document is AI-generated from subtitles
94
95	## Reference
96
97	See `references/doc-template.md` for the full document template.

People who liked this also viewed

6 picks

Type