← 返回 Skills 市场

Social Media Data Collector

Name: Social Media Data Collector
Author: dr-xiaoming

作者 Dr-xiaoming · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install social-media-data-collector

功能描述

Multi-platform social media data collection and aggregation for content performance tracking. Use when: (1) collecting engagement metrics (views/likes/commen...

使用说明 (SKILL.md)

Social Media Data Collector

Overview

Collect engagement metrics from 13+ platforms, aggregate into structured format (飞书多维表格/CSV). Three-tier approach: API first → browser scrape fallback → manual flag.

Execution Flow

Classify platforms by data access method (see references/platform-guide.md)
API tier — call APIs for platforms with programmatic access
Browser tier — Playwright render + text extraction for remaining
Aggregate — normalize data, write to target (bitable/CSV)
Cleanup — remove screenshots, temp files, browser cache

Platform Tiers

Tier	Platforms	Method
API-first	抖音, 微博, 快手, B站, 今日头条, 小红书	TikHub API / BlueAI Crawler
Browser-scrape	百家号, 汽车之家, 易车, 视频号, 斗鱼, 皮皮虾	Playwright headless
API+scrape	懂车帝	TikHub (limited) + scrape

Model Strategy (Token Optimization)

Problem

Using opus/sonnet for the entire pipeline wastes tokens on mechanical tasks.

Recommended Model Split

Phase	Model	Why
Planning & classification	opus/sonnet	Needs reasoning
API calls & JSON parsing	haiku/flash	Mechanical, no reasoning needed
Browser text extraction	Code (no LLM)	Pure Python, no model call
Data normalization	haiku/flash	Simple mapping
Report/summary	sonnet	Needs synthesis

Implementation

Use scripts/collect_api.py for API tier — zero LLM tokens (pure code)
Use scripts/collect_browser.py for browser tier — zero LLM tokens (pure code)
Only invoke LLM for: planning which platforms to hit, handling errors, writing summaries

Token Budget Estimate (per 13-platform run)

With current approach (all-opus): ~80k tokens
With optimized approach (code scripts + haiku routing): ~5k tokens
Savings: 94%

Key Commands

# Full collection run
python3 scripts/collect_api.py --config /tmp/sm-collect/config.json

# Browser scrape specific platforms  
python3 scripts/collect_browser.py --platforms "百家号,汽车之家,视频号"

# Write to bitable
python3 scripts/write_bitable.py --app-token XXX --table-id YYY --data /tmp/sm-collect/results.json

# Cleanup
rm -rf /tmp/sm-collect/ /tmp/screenshots/

Bitable Field Mapping

多维表格字段	类型	说明
播放量	text	带"万"后缀的文本
点赞	number	纯数字
评论	number	纯数字
分享	number	纯数字
收藏	number	纯数字
互动量合计	text	带"万"后缀的文本
数据统计日期	text	格式 "2026.5.15"

⚠️ 注意 播放量 和 互动量合计 是 text 类型，不是 number！传数字会报 TextFieldConvFail。

Cleanup Protocol

After each collection run, delete:

/tmp/sm-collect/ (intermediate JSON)
/tmp/screenshots/ (browser screenshots)
/tmp/subagent-out/ (if spawned sub-agents)
Any .json temp files in workspace

Error Handling

API 403/401 → token expired, refresh and retry once
Browser timeout → increase to 25s, retry with wait_until="domcontentloaded"
Platform redirects → check URL is correct (易车 hao vs sv domain!)
Empty data → flag for manual check, don't guess

Platform-Specific Notes

See references/platform-guide.md for detailed per-platform experience including:

Authentication requirements
URL patterns and gotchas
Data extraction selectors
Known limitations

安全使用建议

This skill appears safe for its stated purpose if you intend to collect social media metrics and update a Feishu Bitable. Before using it, confirm the exact URLs, table ID, and record IDs, use least-privilege TikHub and Feishu credentials, and restrict cleanup to files created by this run.

功能分析

Type: OpenClaw Skill Name: social-media-data-collector Version: 1.0.0 The skill bundle is a social media data aggregator designed to collect engagement metrics from over 13 platforms and sync them to Feishu Bitable. It utilizes the TikHub API (scripts/collect_api.py) and Playwright-based scraping (scripts/collect_browser.py) as a fallback. The implementation is transparent, includes a cleanup protocol for temporary files, and lacks any indicators of malicious intent, such as unauthorized data exfiltration or hidden backdoors. The use of third-party APIs (api.tikhub.io) and browser automation is consistent with the stated goal of cross-platform data tracking.

能力标签

requires-oauth-tokenrequires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The scripts match the stated purpose: collect engagement metrics through APIs or browser scraping and write normalized results to Feishu Bitable. The Bitable write capability is expected but can modify user business data.

ℹ Instruction Scope

The execution flow is disclosed and task-focused. The cleanup instructions include broader temporary-file deletion language that should be interpreted narrowly.

ℹ Install Mechanism

There is no automatic install mechanism, but the browser tier requires Playwright/Chromium and suggests an unpinned pip install command if missing.

ℹ Credentials

Network access to TikHub, Feishu, and the target social platforms is proportional to the skill purpose. Users should still treat submitted URLs, metrics, and credentials as external data flows.

ℹ Persistence & Privilege

No background persistence or token storage is shown. The skill does use Feishu app credentials and Bitable table identifiers to update records, so least-privilege credentials are important.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install social-media-data-collector
安装完成后，直接呼叫该 Skill 的名称或使用 /social-media-data-collector 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: 13-platform data collection with API + browser scraping, Feishu bitable integration

元数据

Slug social-media-data-collector

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题