⚠️

重要前提

安装AI Skills的关键前提是：必须科学上网，且开启TUN模式，这一点至关重要，直接决定安装能否顺利完成，在此郑重提醒三遍：科学上网，科学上网，科学上网。查看完整安装教程 →

Apify技能：无需MCP直接访问9大社交媒体与网络爬虫，节省99% token

Apify by danielmiessler/personal_ai_infrastructure

60 周安装量

10,400 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill Apify

自动化网页数据采集数据处理

🇨🇳中文介绍

自定义配置

执行前，请检查用户自定义配置位于： ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Apify/

如果此目录存在，则加载并应用在那里找到的任何 PREFERENCES.md、配置或资源。这些将覆盖默认行为。如果目录不存在，则使用技能默认设置。

🚨 强制要求：语音通知（在任何操作之前必须执行）

当此技能被调用时，你必须先发送此通知，然后再执行任何其他操作。

发送语音通知：

curl -s -X POST http://localhost:8888/notify
-H "Content-Type: application/json"
-d '{"message": "Running the WORKFLOWNAME workflow in the Apify skill to ACTION"}'
> /dev/null 2>&1 &
输出文本通知：

Running the WorkflowName workflow in the Apify skill to ACTION...

这不是可选的。请在技能调用时立即执行此 curl 命令。

Apify - 社交媒体与网络爬虫

直接通过 TypeScript 访问 9 个流行的 Apify actors，节省 99% 的 token。

🔌 基于文件的 MCP

此技能是一个基于文件的 MCP —— 一种代码优先的 API 包装器，替代了消耗大量 token 的 MCP 协议调用。

在代码中过滤数据，然后再返回给模型上下文 = 节省 97.5% 的 token。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

📊 可用的 Actors

社交媒体（5 个平台）

Instagram (145k 用户, 4.60★) - 个人资料、帖子、话题标签、评论
LinkedIn (26k 用户, 4.10★) - 个人资料、职位、帖子
TikTok (90k 用户, 4.61★) - 个人资料、视频、话题标签、评论
YouTube (40k 用户, 4.40★) - 频道、视频、评论、搜索
Facebook (35k 用户, 4.56★) - 帖子、群组、评论

商业与潜在客户生成

Google Maps (198k 用户, 4.76★) - 最高价值！
- 搜索企业，提取联系方式、评论、图片
- 非常适合潜在客户生成

Amazon (8k 用户, 4.97★) - 产品、评论、价格

Web Scraper (94k 用户, 4.39★) - 通用型，适用于任何网站

import { scrapeInstagramProfile, searchGoogleMaps } from '~/.claude/skills/Apify/actors'

// 1. 调用 actor 包装器
const profile = await scrapeInstagramProfile({
  username: 'target_username',
  maxPosts: 50
})

// 2. 在代码中过滤 - 在数据到达模型之前！
const viral = profile.latestPosts?.filter(p => p.likesCount > 10000)

// 3. 只有过滤后的结果会到达模型上下文
console.log(viral) // 约 10 个帖子，而不是 50 个

📚 按用例分类的示例

Instagram - 追踪互动情况：

import { scrapeInstagramProfile, scrapeInstagramPosts } from '~/.claude/skills/Apify/actors'

// 获取个人资料及近期帖子
const profile = await scrapeInstagramProfile({
  username: 'competitor',
  maxPosts: 100
})

// 在代码中过滤 - 仅过去 30 天的高表现帖子
const thirtyDaysAgo = Date.now() - (30 * 24 * 60 * 60 * 1000)
const topRecent = profile.latestPosts
  ?.filter(p =>
    new Date(p.timestamp).getTime() > thirtyDaysAgo &&
    p.likesCount > 5000
  )
  .sort((a, b) => b.likesCount - a.likesCount)
  .slice(0, 10)

// 只有 10 个帖子到达模型，而不是 100 个！

LinkedIn - 职位搜索：

import { searchLinkedInJobs } from '~/.claude/skills/Apify/actors'

const jobs = await searchLinkedInJobs({
  keywords: 'AI engineer',
  location: 'San Francisco',
  remote: true,
  maxResults: 200
})

// 在代码中过滤 - 仅资金充足的初创公司的高级职位
const topJobs = jobs.filter(j =>
  j.seniority?.includes('Senior') &&
  parseInt(j.applicants || '0') > 50
)

TikTok - 趋势分析：

import { scrapeTikTokHashtag } from '~/.claude/skills/Apify/actors'

const videos = await scrapeTikTokHashtag({
  hashtag: 'ai',
  maxResults: 500
})

// 在代码中过滤 - 仅病毒式传播内容
const viral = videos
  .filter(v => v.playCount > 1000000)
  .sort((a, b) => b.playCount - a.playCount)
  .slice(0, 20)

潜在客户生成（商业智能）

Google Maps - 本地商业潜在客户：

import { searchGoogleMaps } from '~/.claude/skills/Apify/actors'

// 搜索并提取联系信息
const places = await searchGoogleMaps({
  query: 'restaurants in Austin',
  maxResults: 500,
  includeReviews: true,
  maxReviewsPerPlace: 20,
  scrapeContactInfo: true // 从网站提取电子邮件！
})

// 在代码中过滤 - 仅高评分且有电子邮件/电话的
const qualifiedLeads = places
  .filter(p =>
    p.rating >= 4.5 &&
    p.reviewsCount >= 100 &&
    (p.email || p.phone)
  )
  .map(p => ({
    name: p.name,
    rating: p.rating,
    reviews: p.reviewsCount,
    email: p.email,
    phone: p.phone,
    website: p.website,
    address: p.address
  }))

// 导出潜在客户 - 仅合格的结果！
console.log(`找到 ${qualifiedLeads.length} 个合格的潜在客户`)

Google Maps - 评论情感分析：

import { scrapeGoogleMapsReviews } from '~/.claude/skills/Apify/actors'

const reviews = await scrapeGoogleMapsReviews({
  placeUrl: 'https://maps.google.com/maps?cid=12345',
  maxResults: 1000
})

// 在代码中过滤 - 按评分分析情感
const recentNegative = reviews
  .filter(r => {
    const thirtyDaysAgo = Date.now() - (30 * 24 * 60 * 60 * 1000)
    return (
      r.rating <= 2 &&
      new Date(r.publishedAtDate).getTime() > thirtyDaysAgo &&
      r.text.length > 50
    )
  })

// 识别常见投诉
const complaints = recentNegative.map(r => r.text)

电子商务与竞争情报

Amazon - 价格监控：

import { scrapeAmazonProduct } from '~/.claude/skills/Apify/actors'

const product = await scrapeAmazonProduct({
  productUrl: 'https://www.amazon.com/dp/B08L5VT894',
  includeReviews: true,
  maxReviews: 200
})

// 在代码中过滤 - 仅近期负面评论
const recentNegative = product.reviews
  ?.filter(r => {
    const weekAgo = Date.now() - (7 * 24 * 60 * 60 * 1000)
    return (
      r.rating <= 2 &&
      new Date(r.date).getTime() > weekAgo
    )
  })

console.log(`价格：$${product.price}`)
console.log(`评分：${product.rating}/5`)
console.log(`近期问题：${recentNegative?.length} 条投诉`)

自定义网络爬虫

任何网站 - 自定义提取：

import { scrapeWebsite } from '~/.claude/skills/Apify/actors'

const products = await scrapeWebsite({
  startUrls: ['https://example.com/products'],
  linkSelector: 'a.product-link',
  maxPagesPerCrawl: 100,
  pageFunction: `
    async function pageFunction(context) {
      const { request, $, log } = context

      return {
        url: request.url,
        title: $('h1.product-title').text(),
        price: $('span.price').text(),
        inStock: $('.in-stock').length > 0,
        description: $('.description').text()
      }
    }
  `
})

// 在代码中过滤 - 仅 100 美元以下的有货产品
const affordable = products.filter(p =>
  p.inStock &&
  parseFloat(p.price.replace('$', '')) < 100
)

模式 1：多平台社交监听

import {
  scrapeInstagramHashtag,
  scrapeTikTokHashtag,
  searchYouTube
} from '~/.claude/skills/Apify/actors'

// 并行运行所有平台
const [instagramPosts, tiktokVideos, youtubeVideos] = await Promise.all([
  scrapeInstagramHashtag({ hashtag: 'ai', maxResults: 100 }),
  scrapeTikTokHashtag({ hashtag: 'ai', maxResults: 100 }),
  searchYouTube({ query: '#ai', maxResults: 100 })
])

// 合并并过滤 - 仅所有平台上的病毒式传播内容
const allViral = [
  ...instagramPosts.filter(p => p.likesCount > 10000),
  ...tiktokVideos.filter(v => v.playCount > 100000),
  ...youtubeVideos.filter(v => v.viewsCount > 50000)
]

console.log(`在 3 个平台上找到 ${allViral.length} 个病毒式传播帖子`)

模式 2：潜在客户丰富管道

import { searchGoogleMaps, scrapeLinkedInProfile } from '~/.claude/skills/Apify/actors'

// 1. 在 Google Maps 上查找企业
const restaurants = await searchGoogleMaps({
  query: 'restaurants in SF',
  maxResults: 100,
  scrapeContactInfo: true
})

// 2. 过滤出合格的潜在客户
const qualified = restaurants.filter(r =>
  r.rating >= 4.5 &&
  r.email &&
  r.reviewsCount >= 50
)

// 3. 使用 LinkedIn 数据丰富信息（如果可用）
const enriched = await Promise.all(
  qualified.map(async (restaurant) => {
    // 尝试查找 LinkedIn 公司页面
    // ... 额外的丰富逻辑
    return restaurant
  })
)

模式 3：竞争分析仪表板

import {
  scrapeInstagramProfile,
  scrapeYouTubeChannel,
  scrapeTikTokProfile
} from '~/.claude/skills/Apify/actors'

async function analyzeCompetitor(username: string) {
  // 从所有平台收集数据
  const [instagram, youtube, tiktok] = await Promise.all([
    scrapeInstagramProfile({ username, maxPosts: 30 }),
    scrapeYouTubeChannel({ channelUrl: `https://youtube.com/@${username}`, maxVideos: 30 }),
    scrapeTikTokProfile({ username, maxVideos: 30 })
  ])

  // 在代码中计算互动指标
  return {
    username,
    instagram: {
      followers: instagram.followersCount,
      avgLikes: average(instagram.latestPosts?.map(p => p.likesCount) || []),
      engagementRate: calculateEngagement(instagram)
    },
    youtube: {
      subscribers: youtube.subscribersCount,
      avgViews: average(youtube.videos?.map(v => v.viewsCount) || [])
    },
    tiktok: {
      followers: tiktok.followersCount,
      avgPlays: average(tiktok.videos?.map(v => v.playCount) || [])
    }
  }
}

💰 Token 节省计算器

示例：包含 100 个帖子的 Instagram 个人资料

1. search-actors → 1,000 tokens
2. call-actor → 1,000 tokens
3. get-actor-output → 50,000 tokens (100 个未过滤的帖子)
总计：约 52,000 tokens

基于文件的方法：

const profile = await scrapeInstagramProfile({
  username: 'user',
  maxPosts: 100
})

// 在代码中过滤 - 仅前 10 个帖子
const top = profile.latestPosts
  ?.sort((a, b) => b.likesCount - a.likesCount)
  .slice(0, 10)

// 总计：约 500 tokens (只有 10 个过滤后的帖子到达模型)

节省：减少 99% (52,000 → 500 tokens)

scrapeInstagramProfile(input) - 个人资料 + 帖子
scrapeInstagramPosts(input) - 用户的帖子
scrapeInstagramHashtag(input) - 按话题标签的帖子
scrapeInstagramComments(input) - 帖子评论

scrapeLinkedInProfile(input) - 个人资料 + 经历 + 电子邮件
searchLinkedInJobs(input) - 职位列表
scrapeLinkedInPosts(input) - 个人资料/公司的帖子

scrapeTikTokProfile(input) - 个人资料 + 视频
scrapeTikTokHashtag(input) - 按话题标签的视频
scrapeTikTokComments(input) - 视频评论

scrapeYouTubeChannel(input) - 频道 + 视频
searchYouTube(input) - 搜索视频
scrapeYouTubeComments(input) - 视频评论

scrapeFacebookPosts(input) - 页面的帖子
scrapeFacebookGroups(input) - 群组帖子
scrapeFacebookComments(input) - 帖子评论

商业与潜在客户生成

searchGoogleMaps(input) - 搜索地点（带联系信息提取！）
scrapeGoogleMapsPlace(input) - 单个地点详情
scrapeGoogleMapsReviews(input) - 地点评论

scrapeAmazonProduct(input) - 产品详情 + 评论
scrapeAmazonReviews(input) - 仅产品评论

scrapeWebsite(input) - 自定义多页面爬取
scrapePage(url, pageFunction) - 单页面提取

# 必需 - 从 https://console.apify.com/account/integrations 获取
APIFY_TOKEN=apify_api_xxxxx...

Actor 运行选项：

{
  memory: 2048,    // MB: 128, 256, 512, 1024, 2048, 4096, 8192
  timeout: 300,    // 秒
  build: 'latest'  // 或特定的构建编号
}

🎯 何时使用此技能 vs MCP

使用基于文件的方法（此技能）：

✅ 需要过滤大型数据集（>100 个结果）
✅ 希望在代码中转换/聚合数据
✅ 多个顺序操作
✅ 控制流（循环、条件语句）
✅ 最大 token 效率

❌ 结果量小（<10 个项目）的简单单一操作
❌ 一次性探索性查询
❌ 不想编写代码

Apify 平台：https://apify.com
Actor 商店：https://apify.com/store
API 文档：https://docs.apify.com/api/v2

记住：在将数据返回给模型上下文之前，先在代码中过滤数据。这就是节省 99% token 的地方！

2026 年 1 月 24 日

🇺🇸English

Customization

Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Apify/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

You MUST send this notification BEFORE doing anything else when this skill is invoked.

Send voice notification :

curl -s -X POST http://localhost:8888/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Running the WORKFLOWNAME workflow in the Apify skill to ACTION"}' \
  > /dev/null 2>&1 &

Output text notification :

Running the **WorkflowName** workflow in the **Apify** skill to ACTION...

This is not optional. Execute this curl command immediately upon skill invocation.

Apify - Social Media & Web Scraping

Direct TypeScript access to 9 popular Apify actors with 99% token savings.

🔌 File-Based MCP

This skill is a file-based MCP - a code-first API wrapper that replaces token-heavy MCP protocol calls.

Why file-based? Filter data in code BEFORE returning to model context = 97.5% token savings.

Architecture: See ~/.claude/skills/CORE/SYSTEM/DOCUMENTATION/FileBasedMCPs.md

🎯 Overview

Direct TypeScript access to the 9 most popular Apify actors without MCP overhead. Filter and transform data in code BEFORE it reaches the model context.

📊 Available Actors

Social Media (5 platforms)

Instagram (145k users, 4.60★) - Profiles, posts, hashtags, comments
LinkedIn (26k users, 4.10★) - Profiles, jobs, posts
TikTok (90k users, 4.61★) - Profiles, videos, hashtags, comments
YouTube (40k users, 4.40★) - Channels, videos, comments, search
Facebook (35k users, 4.56★) - Posts, groups, comments

Business & Lead Generation

Google Maps (198k users, 4.76★) - HIGHEST VALUE!
- Search businesses, extract contacts, reviews, images
- Perfect for lead generation

E-commerce

Amazon (8k users, 4.97★) - Products, reviews, pricing

Web Scraping

Web Scraper (94k users, 4.39★) - General-purpose, works with ANY website

🚀 Quick Start

Basic Usage Pattern

import { scrapeInstagramProfile, searchGoogleMaps } from '~/.claude/skills/Apify/actors'

// 1. Call the actor wrapper
const profile = await scrapeInstagramProfile({
  username: 'target_username',
  maxPosts: 50
})

// 2. Filter in code - BEFORE data reaches model!
const viral = profile.latestPosts?.filter(p => p.likesCount > 10000)

// 3. Only filtered results reach model context
console.log(viral) // ~10 posts instead of 50

📚 Examples by Use Case

Social Media Monitoring

Instagram - Track engagement:

import { scrapeInstagramProfile, scrapeInstagramPosts } from '~/.claude/skills/Apify/actors'

// Get profile with recent posts
const profile = await scrapeInstagramProfile({
  username: 'competitor',
  maxPosts: 100
})

// Filter in code - only high-performing posts from last 30 days
const thirtyDaysAgo = Date.now() - (30 * 24 * 60 * 60 * 1000)
const topRecent = profile.latestPosts
  ?.filter(p =>
    new Date(p.timestamp).getTime() > thirtyDaysAgo &&
    p.likesCount > 5000
  )
  .sort((a, b) => b.likesCount - a.likesCount)
  .slice(0, 10)

// Only 10 posts reach model instead of 100!

LinkedIn - Job search:

import { searchLinkedInJobs } from '~/.claude/skills/Apify/actors'

const jobs = await searchLinkedInJobs({
  keywords: 'AI engineer',
  location: 'San Francisco',
  remote: true,
  maxResults: 200
})

// Filter in code - only senior roles at well-funded startups
const topJobs = jobs.filter(j =>
  j.seniority?.includes('Senior') &&
  parseInt(j.applicants || '0') > 50
)

TikTok - Trend analysis:

import { scrapeTikTokHashtag } from '~/.claude/skills/Apify/actors'

const videos = await scrapeTikTokHashtag({
  hashtag: 'ai',
  maxResults: 500
})

// Filter in code - only viral content
const viral = videos
  .filter(v => v.playCount > 1000000)
  .sort((a, b) => b.playCount - a.playCount)
  .slice(0, 20)

Lead Generation (Business Intelligence)

Google Maps - Local business leads:

import { searchGoogleMaps } from '~/.claude/skills/Apify/actors'

// Search with contact info extraction
const places = await searchGoogleMaps({
  query: 'restaurants in Austin',
  maxResults: 500,
  includeReviews: true,
  maxReviewsPerPlace: 20,
  scrapeContactInfo: true // Extracts emails from websites!
})

// Filter in code - only highly-rated with email/phone
const qualifiedLeads = places
  .filter(p =>
    p.rating >= 4.5 &&
    p.reviewsCount >= 100 &&
    (p.email || p.phone)
  )
  .map(p => ({
    name: p.name,
    rating: p.rating,
    reviews: p.reviewsCount,
    email: p.email,
    phone: p.phone,
    website: p.website,
    address: p.address
  }))

// Export leads - only qualified results!
console.log(`Found ${qualifiedLeads.length} qualified leads`)

Google Maps - Review sentiment analysis:

import { scrapeGoogleMapsReviews } from '~/.claude/skills/Apify/actors'

const reviews = await scrapeGoogleMapsReviews({
  placeUrl: 'https://maps.google.com/maps?cid=12345',
  maxResults: 1000
})

// Filter in code - analyze sentiment by rating
const recentNegative = reviews
  .filter(r => {
    const thirtyDaysAgo = Date.now() - (30 * 24 * 60 * 60 * 1000)
    return (
      r.rating <= 2 &&
      new Date(r.publishedAtDate).getTime() > thirtyDaysAgo &&
      r.text.length > 50
    )
  })

// Identify common complaints
const complaints = recentNegative.map(r => r.text)

E-commerce & Competitive Intelligence

Amazon - Price monitoring:

import { scrapeAmazonProduct } from '~/.claude/skills/Apify/actors'

const product = await scrapeAmazonProduct({
  productUrl: 'https://www.amazon.com/dp/B08L5VT894',
  includeReviews: true,
  maxReviews: 200
})

// Filter in code - only recent negative reviews
const recentNegative = product.reviews
  ?.filter(r => {
    const weekAgo = Date.now() - (7 * 24 * 60 * 60 * 1000)
    return (
      r.rating <= 2 &&
      new Date(r.date).getTime() > weekAgo
    )
  })

console.log(`Price: $${product.price}`)
console.log(`Rating: ${product.rating}/5`)
console.log(`Recent issues: ${recentNegative?.length} complaints`)

Custom Web Scraping

Any Website - Custom extraction:

import { scrapeWebsite } from '~/.claude/skills/Apify/actors'

const products = await scrapeWebsite({
  startUrls: ['https://example.com/products'],
  linkSelector: 'a.product-link',
  maxPagesPerCrawl: 100,
  pageFunction: `
    async function pageFunction(context) {
      const { request, $, log } = context

      return {
        url: request.url,
        title: $('h1.product-title').text(),
        price: $('span.price').text(),
        inStock: $('.in-stock').length > 0,
        description: $('.description').text()
      }
    }
  `
})

// Filter in code - only available products under $100
const affordable = products.filter(p =>
  p.inStock &&
  parseFloat(p.price.replace('$', '')) < 100
)

🎨 Advanced Patterns

Pattern 1: Multi-Platform Social Listening

import {
  scrapeInstagramHashtag,
  scrapeTikTokHashtag,
  searchYouTube
} from '~/.claude/skills/Apify/actors'

// Run all platforms in parallel
const [instagramPosts, tiktokVideos, youtubeVideos] = await Promise.all([
  scrapeInstagramHashtag({ hashtag: 'ai', maxResults: 100 }),
  scrapeTikTokHashtag({ hashtag: 'ai', maxResults: 100 }),
  searchYouTube({ query: '#ai', maxResults: 100 })
])

// Combine and filter - only viral content across all platforms
const allViral = [
  ...instagramPosts.filter(p => p.likesCount > 10000),
  ...tiktokVideos.filter(v => v.playCount > 100000),
  ...youtubeVideos.filter(v => v.viewsCount > 50000)
]

console.log(`Found ${allViral.length} viral posts across 3 platforms`)

Pattern 2: Lead Enrichment Pipeline

import { searchGoogleMaps, scrapeLinkedInProfile } from '~/.claude/skills/Apify/actors'

// 1. Find businesses on Google Maps
const restaurants = await searchGoogleMaps({
  query: 'restaurants in SF',
  maxResults: 100,
  scrapeContactInfo: true
})

// 2. Filter for qualified leads
const qualified = restaurants.filter(r =>
  r.rating >= 4.5 &&
  r.email &&
  r.reviewsCount >= 50
)

// 3. Enrich with LinkedIn data (if available)
const enriched = await Promise.all(
  qualified.map(async (restaurant) => {
    // Try to find LinkedIn company page
    // ... additional enrichment logic
    return restaurant
  })
)

Pattern 3: Competitive Analysis Dashboard

import {
  scrapeInstagramProfile,
  scrapeYouTubeChannel,
  scrapeTikTokProfile
} from '~/.claude/skills/Apify/actors'

async function analyzeCompetitor(username: string) {
  // Gather data from all platforms
  const [instagram, youtube, tiktok] = await Promise.all([
    scrapeInstagramProfile({ username, maxPosts: 30 }),
    scrapeYouTubeChannel({ channelUrl: `https://youtube.com/@${username}`, maxVideos: 30 }),
    scrapeTikTokProfile({ username, maxVideos: 30 })
  ])

  // Calculate engagement metrics in code
  return {
    username,
    instagram: {
      followers: instagram.followersCount,
      avgLikes: average(instagram.latestPosts?.map(p => p.likesCount) || []),
      engagementRate: calculateEngagement(instagram)
    },
    youtube: {
      subscribers: youtube.subscribersCount,
      avgViews: average(youtube.videos?.map(v => v.viewsCount) || [])
    },
    tiktok: {
      followers: tiktok.followersCount,
      avgPlays: average(tiktok.videos?.map(v => v.playCount) || [])
    }
  }
}

💰 Token Savings Calculator

Example: Instagram profile with 100 posts

MCP Approach:

1. search-actors → 1,000 tokens
2. call-actor → 1,000 tokens
3. get-actor-output → 50,000 tokens (100 unfiltered posts)
TOTAL: ~52,000 tokens

File-Based Approach:

const profile = await scrapeInstagramProfile({
  username: 'user',
  maxPosts: 100
})

// Filter in code - only top 10 posts
const top = profile.latestPosts
  ?.sort((a, b) => b.likesCount - a.likesCount)
  .slice(0, 10)

// TOTAL: ~500 tokens (only 10 filtered posts reach model)

Savings: 99% reduction (52,000 → 500 tokens)

🔧 Actor Reference

Social Media

Instagram

scrapeInstagramProfile(input) - Profile + posts
scrapeInstagramPosts(input) - Posts from user
scrapeInstagramHashtag(input) - Posts by hashtag
scrapeInstagramComments(input) - Comments on post

scrapeLinkedInProfile(input) - Profile + experience + email
searchLinkedInJobs(input) - Job listings
scrapeLinkedInPosts(input) - Posts from profile/company

TikTok

scrapeTikTokProfile(input) - Profile + videos
scrapeTikTokHashtag(input) - Videos by hashtag
scrapeTikTokComments(input) - Comments on video

YouTube

scrapeYouTubeChannel(input) - Channel + videos
searchYouTube(input) - Search videos
scrapeYouTubeComments(input) - Comments on video

Facebook

scrapeFacebookPosts(input) - Posts from pages
scrapeFacebookGroups(input) - Group posts
scrapeFacebookComments(input) - Post comments

Business & Lead Generation

Google Maps

searchGoogleMaps(input) - Search places (with contact extraction!)
scrapeGoogleMapsPlace(input) - Single place details
scrapeGoogleMapsReviews(input) - Place reviews

E-commerce

Amazon

scrapeAmazonProduct(input) - Product details + reviews
scrapeAmazonReviews(input) - Product reviews only

Web Scraping

General Web

scrapeWebsite(input) - Custom multi-page crawling
scrapePage(url, pageFunction) - Single page extraction

⚙️ Configuration

Environment Variables:

# Required - Get from https://console.apify.com/account/integrations
APIFY_TOKEN=apify_api_xxxxx...

Actor Run Options:

{
  memory: 2048,    // MB: 128, 256, 512, 1024, 2048, 4096, 8192
  timeout: 300,    // seconds
  build: 'latest'  // or specific build number
}

🎯 When to Use This vs MCP

Use File-Based (this skill):

✅ Need to filter large datasets (>100 results)
✅ Want to transform/aggregate data in code
✅ Multiple sequential operations
✅ Control flow (loops, conditionals)
✅ Maximum token efficiency

Use MCP:

❌ Simple single operations with small results (<10 items)
❌ One-off exploratory queries
❌ Don't want to write code

🔗 Links

Remember: Filter data in code BEFORE returning to model context. This is where the 99% token savings happen!

Weekly Installs

Repository

danielmiessler/…tructure

GitHub Stars

9.7K

First Seen

Jan 24, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykFail

Installed on

gemini-cli43

codex41

opencode40

claude-code39

github-copilot39

cursor37

GitHub Actions 官方文档查询助手 - 精准解答 CI/CD 工作流问题

49,000 周安装

Apify技能：无需MCP直接访问9大社交媒体与网络爬虫，节省99% token

🇨🇳中文介绍

自定义配置

🚨 强制要求：语音通知（在任何操作之前必须执行）

Apify - 社交媒体与网络爬虫

🔌 基于文件的 MCP

相关 Skills

🎯 概述

📊 可用的 Actors

社交媒体（5 个平台）

商业与潜在客户生成

电子商务

网络爬虫

🚀 快速开始

基本使用模式

📚 按用例分类的示例

社交媒体监控

潜在客户生成（商业智能）

电子商务与竞争情报

自定义网络爬虫

🎨 高级模式

模式 1：多平台社交监听

模式 2：潜在客户丰富管道

模式 3：竞争分析仪表板

💰 Token 节省计算器

🔧 Actor 参考

社交媒体

Instagram

LinkedIn

TikTok

YouTube

Facebook

商业与潜在客户生成

Google Maps

电子商务

Amazon

网络爬虫

通用网络

⚙️ 配置

🎯 何时使用此技能 vs MCP

🔗 链接

🇺🇸English

Customization

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

Apify - Social Media & Web Scraping

🔌 File-Based MCP

🎯 Overview

📊 Available Actors

Social Media (5 platforms)

Business & Lead Generation

E-commerce

Web Scraping

🚀 Quick Start

Basic Usage Pattern

📚 Examples by Use Case

Social Media Monitoring

Lead Generation (Business Intelligence)

E-commerce & Competitive Intelligence

Custom Web Scraping

🎨 Advanced Patterns

Pattern 1: Multi-Platform Social Listening

Pattern 2: Lead Enrichment Pipeline

Pattern 3: Competitive Analysis Dashboard

💰 Token Savings Calculator

🔧 Actor Reference

Social Media

Instagram

LinkedIn

TikTok

YouTube

Facebook

Business & Lead Generation

Google Maps

E-commerce

Amazon

Web Scraping

General Web

⚙️ Configuration

🎯 When to Use This vs MCP

🔗 Links