SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsdouyin-comment

douyin-comment

General & other

View repository

Updated 10-16 06:49

About this skill

Douyin Comment Analysis

📝 Introduction

Enter a Douyin work link to retrieve first-level comment data, 20 per page, with pagination support. Display all comments on the current page and AI summary analysis in the conversation, while generating an interactive HTML report containing the current page data and summary.

✨ Features

Feature Module Capability Description Core Value
Comment Retrieval Paste a work link to retrieve comments Pull the latest data from the work's comment section
Paginated Browsing 20 per page, with pagination support Browse large numbers of comments page by page
AI Summary Four-dimensional sentiment analysis (positive/negative/demand/competitor) Quickly understand the full picture of comment public opinion
Pinned Marking Special marking for pinned comments Identify important comments at a glance
HTML Report Dark-themed interactive report Save/share analysis results offline

🔑 Authentication

  • Get API Key: Go to Red Fox hub
  • Configuration method 1: Write to ~/.openclaw/openclaw.json → { "env": { "REDFOX_API_KEY": "ak_xxxx..." } }
  • Configuration method 2: Execute in terminal export REDFOX_API_KEY="ak_xxxx..."

🔄 Workflow

Step 1: Understand user intent, extract videoId

⚠️ Core rule: videoId must be extracted from user input.

  • The user may provide the videoId directly (pure digits)
  • The user may provide a work link (such as https://www.douyin.com/video/7131700643076623629), extract the videoId from the link
  • If the user does not provide a work link, proactively ask: "Please provide the Douyin work link"
  • If the user queried data for a certain work in the previous round of conversation, and the current input is ambiguous (such as "next page", "comment analysis"), use the videoId from the previous round

Step 2: Call the comment retrieval script (automatically generates HTML)

⚠️ Each call requests only one page of data (one API request); do not initiate multiple calls to pull multiple pages without authorization.

The script automatically generates an HTML report on each call(including {{PLACEHOLDER}} placeholders, with analysis data not yet filled in). The terminal display and HTML are based onthe same API call, ensuring data consistency.

python3 ~/.agents/skills/douyin-comment-search/scripts/douyin_comment_search.py "<videoId>" [--offset <offset>]

Parameter description:

Parameter Description Default Value
videoId Douyin work ID (required) —
--offset Offset, 20 per page 0
--output-dir HTML output directory ~/Downloads/QoderReports

Correspondence between offset and page number:

Page Number offset
Page 1 0
Page 2 20
Page 3 40
... offset = (page - 1) × 20

Script returns JSON:

Field Description
video_id Work ID
current_page Current page number
total_fetched Number of comments retrieved this time
has_next Whether there is a next page (true/false)
comments Comment list
html_path Path of the generated HTML report (contains placeholders, to be filled in later)

Fields for each comment:

Field Description
comment_id Comment ID
content Comment content
like_count Like count
reply_count Reply count
create_time Comment time
ip_location IP location
user_name User nickname
user_avatar User avatar URL
user_id User ID (used to generate profile link)
user_url User profile link
is_top Whether pinned (true/false)

Note: The HTML report currently contains only the raw comment data; the analysis placeholders ({{PLACEHOLDER}}) will be filled in after user confirmation.

Step 3: Display comment data + AI summary in the conversation

⚠️ Each operation calls the API only once to retrieve one page of data. The conversation display and the HTML report are based on the same page of data.

A1. State the query scope

📊 Work「{videoId}」retrieved Ncomments (page {page}), the detailed data is as follows:

A2. Render the comment table (display all comments on the current page)

| # | 评论人 | 评论内容 | 👍 | 💬 | 时间 | IP |
|---|--------|---------|----|----|------|-----|
| 1 | ![avatar](头像URL)[昵称](主页链接) | 评论内容... | 1223 | 213 | 02-12 15:30 | 广东 |
| 2 | ![avatar](头像URL)[昵称](主页链接) | 评论内容... | 856 | 45 | 02-12 14:20 | 北京 |
| ... | ... | ... | ... | ... | ... | ... |

Formatting rules:

  • The commenter column uses ![avatar](头像URL)[昵称](user_url) Markdown format, no need to set image dimensions
  • Comment content exceeding 40 characters is truncated with ...
  • Time is formatted as MM-DD HH:MM
  • Pinned comments add 📌 after the nickname (the entire comment row uses bold style)
  • like_count / reply_count Numbers ≥ 10000 use x.xw format
  • ⚠️ Maximum 20 per page, all displayed in the conversation, must not be truncated

A3. AI comment summary (⚠️ must be output for every query (including pagination))

Based on all comments retrieved on the current page, perform four-dimensional sentiment analysis.Before analysis, it is necessary to understand Douyin meme culture(popular slang, abbreviations, emoji semantics, trending topic background).

📈 Comment summary analysis (based on {total} comments)

✅ Positive reviews ({positive_ratio}%)

  • {point 1}
  • {point 2}
  • ...

⚠️ Negative reviews ({negative_ratio}%)

  • {point 1}
  • {point 2}
  • ...

💡 User needs ({demand_ratio}%)

  • {point 1}
  • {point 2}
  • ...

🔍 Competitor comparison public opinion ({competitor_ratio}%)

  • {Output only when competitors are mentioned in the comments, otherwise output "No competitors mentioned"}
  • {competitor name}: {public opinion point}

Analysis requirements:

  • Each point must cite a representative comment (extract keywords/phrases)
  • The percentage is the proportion of comments mentioning that type to the total number of comments
  • The sum of the proportions of the four categories (positive/negative/demand/competitor) may exceed 100% (a single comment may contain multiple types of information)
  • Must understand Douyin meme culture: recognize popular slang (such as "绝绝子", "yyds", "破防", "入典", etc.), emoji semantics, abbreviations (such as "xswl", "awsl"), and the contextual meaning of memes

A4. Pagination prompt (⚠️ immediately after A3, must be output every time)

  • If has_next is true:

📄 Current page {page} ({total_fetched} items total). Reply "Next Page" to continue viewing.

  • If has_next is false:

📄 Current page {page} , no more data available.

⚠️ A1~A4 must be completed consecutively in the same round of output, no step may be omitted.

After A4 output is complete,ask the user whether they need an HTML visualization report generated：

📊 Do you need an HTML visualization report generated?

If the user replies with confirmation words such as "Yes", "Need", "Generate", "html", etc., then execute the following steps (no need to call the script again, the HTML file has already been generated in Step 2):

① Backfill AI analysis results into the HTML

Call backfill_html.py to backfill the AI analysis results into the {{PLACEHOLDER}} placeholder in the HTML:

python3 ~/.agents/skills/douyin-comment-search/scripts/backfill_html.py "<html_path>" --analysis-json '{
  "positive_ratio": <正整数>,
  "negative_ratio": <正整数>,
  "demand_ratio": <正整数>,
  "competitor_ratio": <正整数>,
  "positive_summary": "<ul><li>要点1</li><li>要点2</li>...</ul>",
  "negative_summary": "<ul><li>要点1</li><li>要点2</li>...</ul>",
  "demand_summary": "<ul><li>要点1</li><li>要点2</li>...</ul>",
  "competitor_summary": "<ul><li>要点1</li><li>要点2</li>...</ul>"
}'

JSON field description:

Field Type Description Example
positive_ratio int Positive review percentage (plain number, excluding %) 45
negative_ratio int Negative review percentage 30
demand_ratio int User demand percentage 15
competitor_ratio int Competitor comparison percentage 15
positive_summary string Positive review summary (HTML format <ul><li>...</li></ul>） see example
negative_summary string Negative review summary Same as above
demand_summary string User demand summary Same as above
competitor_summary string Competitor comparison summary Same as above

Note: The JSON string parameter contains double quotes, wrap it in single quotes in Bash, internal double quotes need to be escaped \". If the content contains single quotes, pass it via stdin:echo '...' | python3 backfill_html.py "<html_path>"

② Open the HTML report:

open "<html_path>"

Step 4: Pagination handling (when the user replies "Next Page", etc.)

When the user replies "Next Page", "Previous Page", "Page N", etc.:

  1. Reuse the videoId extracted in Step 1
  2. Calculate the new offset:(page - 1) × 20
  3. Call the script again (consistent with Step 2, HTML is generated automatically）：python3 .../douyin_comment_search.py "<videoId>" --offset <offset>
  4. Fully execute A1~A4 of Step 3(independent display per page + AI analysis)
  5. After A4, ask the user whether they need an HTML report for the current page generated (same as the end-of-Step-3 process,no need to call the script again）

Pagination rules:

  • has_next is true → the current page has exactly 20 items, a next page exists
  • has_next is false → the current page has fewer than 20 items, it is the last page

Step 5: Error handling

Error type Handling method
No API Key Prompt to configure REDFOX_API_KEY, provide configuration guidance
Invalid work link Prompt "No comments found for this work, please check whether the work link is correct"
API returned an error Display error code and error message
Retrieved 0 comments Prompt "This work has no comments yet" and suggest checking whether the work exists or has been deleted
Network request timeout Prompt "Network request timed out, please try again later"

📋 Dependencies

# 脚本使用 urllib（Python 标准库），无需额外安装依赖

🎯 Usage Examples

Example 1: View comments on a specified work

用户：查看抖音作品 7131700643076623629 的评论
助手：调用脚本（自动生成HTML） → 展示全部20条 + AI总结 → 询问是否需要HTML → 用户确认 → backfill → open

Example 2: Query via link

用户：https://www.douyin.com/video/7131700643076623629 这篇的评论怎么样
助手：提取 videoId → 调用脚本 → 展示分析 → 询问是否需要HTML

Example 3: Turn the page

用户：下一页
助手：调用脚本 offset=20 → 展示第2页 + AI分析 → 询问是否需要当前页HTML