SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsdouyin-realtime-search

douyin-realtime-search

Marketing & growth

View repository

Updated 10-15 23:43

About this skill

Douyin work real-time search

📝 Overview

Douyin work real-time search tool, based on keywords calls the Redfox interface in real time to search for the latest Douyin works, returning real-time data (not cached/historical data). Supports filtering by sorting method and publish time.

✨ Features

Function module Capability description Core value
Real-time search Real-time keyword search for the latest Douyin works Obtain non-cached real-time data
Multi-dimensional sorting Supports three sorting types: comprehensive/latest/likes Discover high-quality content by different dimensions
Time filtering Supports 7 days/30 days/90 days/unlimited time range Flexibly control the search time window
Smart expansion Automatically generates 10 expanded terms when there are no results Break through search bottlenecks and discover related content
Paginated browsing Supports multiple-page result browsing Explore large numbers of search results page by page
Subscription push Supports daily keyword push Scheduled access to the latest search results

🔑 Authentication

Get API Key

Please go to Honghu hub to get the API KEY

Configure API Key

Option 1: Taking OpenClaw as an example, add REDFOX_API_KEY to ~/.openclaw/openclaw.json :

{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }

Option 2: Terminal configuration

export REDFOX_API_KEY="ak_xxxx..."

🔄 Workflow

Step 1: Understand user intent, extract keywords and filter parameters

⚠️ Core rule: semantic understanding takes priority, prioritize extracting niche direction terms rather than generalized broad category terms

1. Extract keywords

  • Extract 2-6 character niche keywords from the user's description
  • If the user's intent is vague (such as "help me search Douyin"), proactively ask: "Which direction or field of content would you like to search for?"
  • Do not guess on your own and call the script when the user has not provided keywords

2. Identify filter parameters(use default values when the user does not specify)

  • Sorting method（--sort): default 1(comprehensive sorting)
    • User mentions "latest", "recently published" → 2
    • User mentions "likes", "popular", "hit" → 3
    • No sorting mentioned → 1(default)
  • Publish time（--time): default 7(last 7 days)
    • User mentions "last month", "30 days" → 30
    • User mentions "last three months", "90 days" → 90
    • User mentions "unlimited time", "all" → 0
    • No time mentioned → 7(default)
  • Page number（--page): Default 1
    • User mentions "next page", "page 2" → corresponding page number
    • User mentions "previous page" → current page - 1
    • No page number mentioned → 1(default)

Step 2: Call the real-time search script

python3 ~/.agents/skills/douyin-realtime-search/scripts/search_douyin_realtime.py "<关键词>" [--sort 排序] [--time 时间] [--page 页码]

Parameter description:

Parameter Optional values Meaning
keyword Any string Search keywords, connect multiple words with English commas
--sort 1 / 2 / 3 Comprehensive sorting / Latest published / Most likes (default 1)
--time 7 / 30 / 90 / 0 Last 7 days / 30 days / 90 days / Unlimited (default 7)
--page Positive integer Page number, starting from 1 (default 1)

The script outputs in JSON format:

Field Description
articles List of works matching keywords (sorted by likes in descending order)
latestHotArticles Recently popular recommended works (fallback display)
hotTopics Related popular topic tags
sort_type_label Text description of this sorting method
publish_time_label Text description of this time range
page Current page number
has_next Whether there is a next page (true/false)

Fields for each work:

Field Description
title Work title
author Author name
like_count Like count
comment_count Comment count
share_count Share count
collect_count Favorite count
work_url Work link
publish_time Publish time
follower_count Follower count

Step 3: Judge the results and display

Case A: articles count > 0 (has matching results)

A1. Inform the user of the query scope

📊 Keyword "XXX" real-time query found N itemsworks (sorting: {sort_type_label} | time range: {publish_time_label} | page {page}), the detailed data is as follows:

A2. Render Markdown table (display all)

| #   | 作品标题             | 作者   | 点赞数 | 评论数 | 分享数 | 收藏数 |
| --- | -------------------- | ------ | ------ | ------ | ------ | ------ |
| 1   | [标题文字](作品链接) | 作者名 | 305.2w | 7.1w   | 51.0w  | 14.7w  |

Number formatting rules:

  • < 10000: original number (e.g. 320）
  • ≥ 10000：x.xw format (e.g. 1.2w）

Title rules: [标题](work_url); truncate if over 30 characters and add ...

A3. Filtering capability prompt (immediately after the table, must be output every time)

🔧 Filtering is supported. Reply with the following commands to switch conditions and search again:

  • Sorting method: Comprehensive sorting / Latest published / Most likes (current: {sort_type_label})
  • Publish time: Last 7 days / Last 30 days / Last 90 days / Unlimited (current: {publish_time_label})

Example: "Search again by latest published, last 30 days"

A4. Pagination prompt (⚠️ immediately after A3, cannot be omitted, must be output every time)

  • If has_next is true:

    📄 Currently page {page} . Reply "next page" to continue viewing.

  • If has_next is false (the current page has fewer than 9 items or is empty, and it is already the last page):

    📄 Currently page {page} , there is no more data.

⚠️ A1~A4 are all indispensable and must be completed consecutively in the same round of output. After outputting A4, immediately follow with the Step 4 subscription prompt. If A4 is missing, it is considered an execution error and the output must be re-supplemented.

Case B: articles count = 0 (no matching results)

B1. Apology prompt + keyword expansion recommendations

😔 Sorry, no content directly related to「XXX」was found. You can try again with shorter or broader keywords (expansion word 1, expansion word 2, ... expansion word 10)

AI must generatefixed 10expansion words, 2~6 characters, separated by English commas, no fewer than 10.

B2. Filtering capability prompt (immediately after B1, must be output every time, format same as A3)

⚠️ B1~B2 must be completed consecutively in the same round of output. After outputting B2, immediately follow with the Step 4 subscription prompt, with no interruption.

Step 4: Subscription prompt

After all content is displayed,without waiting, end the output immediately, and only append the subscription prompt at the end:

📩 Would you like to subscribe to the daily push of「XXX」? After subscribing, the latest trending works will be automatically pushed every day at 10:00. Reply "Confirm Subscription" to create a scheduled task.

Step 5: Create a scheduled task (executed when the user replies "Confirm Subscription")

Prioritize using the platform's built-in scheduled task capability; if unavailable, provide a general solution:

Platform built-in scheduled task (preferred):

  • Task name:抖音实时搜索订阅 - <关键词>
  • Execution frequency: every day at 10:00 (cron:0 10 * * *）
  • Execution content: run the script and display/push the results to the current conversation in the Step 3~4 format

General configuration solution:

# Linux/macOS crontab
0 10 * * * python3 ~/.agents/skills/douyin-realtime-search/scripts/search_douyin_realtime.py "<关键词>"

After successful creation, inform the user: "You have successfully subscribed to real-time work push for the keyword「<keyword>」. Every day at 10:00, the latest data will be automatically queried and notified to you."