SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillscn-last30days

cn-last30days

General & other

View repository

Updated 10-15 23:40

About this skill

Last 30 Days—CN Edition

📝 Overview

Last 30 Days—CN Edition is a Chinese social media topic research tool that searches real discussion data from the past 30 days across three major platforms—Xiaohongshu, Douyin, and WeChat Official Accounts—and analyzes public opinion trends through cross-platform comparison. It supports two modes: general topic research and entity comparison, and outputs structured research reports and visualized HTML.

✨ Features

Feature Module Capability Description Core Value
Three-platform data sources Unified interface for Xiaohongshu/WeChat Official Accounts + Douyin broad-domain database interface data Multi-dimensional public opinion perspectives
Keyword research Supports multi-word combined queries (separated by English commas) Flexible topic coverage
Cross-platform comparison Automatically synthesizes data from the three platforms to generate insights Discovers differentiated trends
Comparison A vs B structured comparative analysis Assists decision-making
HTML report Interactive visualized report generation Easy to share and disseminate
Historical backtracking Supports data for any date within the past 30 days Tracks trend evolution

🔑 Authentication

The script requires an API Key to be configured. Obtain a personal Key from RedFox Data and configure the environment variable:

export REDFOX_API_KEY=ak_你的密钥

Priority: command line --api-key > REDFOX_API_KEY / X_API_KEY environment variable > configuration file.

Core Parameters

Parameter Description Default Value
keyword Search keywords (required, separate multiple words with English commas) -
--platforms Platform list (reducing is not recommended) xhs,dy,gzh
--count Number of items per platform 50
--days Time range; set to 7 to view recent trends 30
--output-format json / html / both json
--output-dir Output directory ~/Documents/CnLast30Days

Platform signal interpretation:

Platform Content Characteristics Key Metrics
Xiaohongshu (xhs) Product recommendation experiences, tutorials and guides, user feedback High saves/likes ratio = recommendation signal
Douyin (dy) Hot topic follow-up comments, knowledge fragments, emotional spread Shares = dissemination power
WeChat Official Accounts (gzh) In-depth industry analysis, opinion output, data reports Reads = attention, shares = recognition

Workflow

1. Environment check

Before running, ensure that an API Key is configured (environment variable REDFOX_API_KEY or --api-key parameter). If not configured, prompt the user:

Please configure the API Key:export REDFOX_API_KEY=ak_你的密钥, registration address https://www.redfox.hk/login

2. Keyword quality check

Before running the engine, check whether the topic is too vague (such as "tools" or "methods"); if so, ask the user to make it more specific.

3. Pre-research

Before calling the engine, run 2-3 WebSearch queries in parallel to extract hot keywords and background:

  • 小红书 {TOPIC} 热门讨论 → Extract Xiaohongshu hot keywords
  • 抖音 {TOPIC} 热门话题 → Extract Douyin tags
  • {TOPIC} 最新动态 → Supplement timely background

4. Query plan

Determine the query strategy based on preliminary research:

  • Prioritize merging related keywords into a single call (e.g., "产品经理,AI产品经理"）
  • At most 5 keywords per platform; only split calls when the topic dimensions differ greatly
  • By default, call the engine only once

5. Run the engine

python3 scripts/cn_last30days.py "{TOPIC},{SUBTOPIC}" \
  --platforms xhs,dy,gzh \
  --count 50 \
  --days 30 \
  --output-format json \
  --output-dir="${CN_LAST30DAYS_MEMORY_DIR:-$HOME/Documents/CnLast30Days}"

Run in the foreground, with a 5-minute timeout; do not run in the background. Read the complete output, including titles, authors, engagement data, and links from the three platforms.

6. WebSearch supplement

After the engine finishes, supplement with 1-2 WebSearch queries to cover sources not covered by the engine, such as Zhihu, Bilibili, and 36Kr. Exclude xiaohongshu.com / douyin.com / mp.weixin.qq.com (already covered by the engine).

7. Comprehensive output

Follow the output rules to generate the research report. Core principles:

  • After the badge and before "My Findings", you must output the "Data Overview" module: in the order of WeChat Official Account → Xiaohongshu → Douyin, display a TOP5 works table for each platform (titles as clickable hyperlinks, authors, and platform-specific engagement metrics displayed in separate columns (WeChat Official Account reads/likes/shares, Xiaohongshu likes/saves/comments, Douyin likes/comments/shares)), and at the end of the module display the total data volume and an HTML report prompt
  • Synthesize by topic/story, not by listing platform by platform
  • Conclusions cross-validated across multiple platforms have the highest confidence
  • High-engagement content has the highest weight (including genuine user signals)
  • Each narrative paragraph starts with a bold title, followed by - and the body text
  • Citations must be clickable Markdown links

After the comprehensive report is completed,automatically executethe following steps to generate the HTML report (no need to ask the user):

# 直接从 JSON 生成 HTML（不调 API，不写入 Markdown）
python3 scripts/cn_last30days.py --from-json "JSON文件路径" \
  --output-dir="${CN_LAST30DAYS_MEMORY_DIR:-$HOME/Documents/CnLast30Days}"

# 自动打开 HTML 报告
open "HTML文件路径"

The script will output the HTML file path; after opening it automatically, simply inform the user of the path.

Other resources