Telegram Groups Search Scraper
Pricing
from $4.99 / 1,000 results
Search and rank Telegram groups by keyword. Get member counts, rankings, language, avatars, and Telegram links with automatic pagination. 📊
Pricing
from $4.99 / 1,000 results
Rating
0.0
(0)
Developer
PowerAI
Maintained by CommunityActor stats
1
Bookmarked
5
Total users
3
Monthly active users
7 days ago
Last modified
Categories
Share
# Specify the base Docker image. You can read more about# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images# You can also use any other image from Docker Hub.FROM apify/actor-node:20
# Check preinstalled packagesRUN npm ls apify
# Copy just package.json and package-lock.json# to speed up the build using Docker layer cache.COPY package*.json ./
# Install NPM packages, skip optional and development dependencies to# keep the image small. Avoid logging too much and print the dependency# tree for debuggingRUN npm --quiet set progress=false \ && npm install --omit=dev --omit=optional \ && echo "Installed NPM packages:" \ && (npm list --omit=dev --all || true) \ && echo "Node.js version:" \ && node --version \ && echo "NPM version:" \ && npm --version \ && rm -r ~/.npm
# Next, copy the remaining files and directories with the source code.# Since we do this after NPM install, quick build will be really fast# for most source file changes.COPY . ./
# Run the image.CMD npm start --silent{ "actorSpecification": 1, "name": "telegram-groups-search-scraper", "title": "Empty JavaScript project", "description": "Empty project in JavaScript.", "version": "0.0", "buildTag": "latest", "meta": { "templateId": "js-empty" }, "input": "./input_schema.json", "dockerfile": "./Dockerfile"}{ "title": "Telegram Groups Search Scraper Input", "type": "object", "schemaVersion": 1, "properties": { "keywords": { "title": "Search Keywords", "type": "array", "description": "Keywords to search Telegram groups, e.g. coin or crypto", "editor": "stringList", "default": ["coin"], "prefill": ["coin"], "uniqueItems": true, "minItems": 1 }, "lng": { "title": "Language", "type": "string", "description": "Filter groups by language code, or all for every language", "editor": "textfield", "default": "all", "prefill": "all" }, "limit": { "title": "Limit", "type": "integer", "description": "Number of groups per API request (1-100)", "default": 100, "prefill": 100, "minimum": 1, "maximum": 100 }, "maxItems": { "title": "Maximum Results", "type": "integer", "description": "Maximum total number of groups to scrape per keyword", "default": 100, "prefill": 100, "minimum": 1, "maximum": 50000 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for the actor", "default": { "useApifyProxy": false }, "editor": "proxy" } }, "required": ["keywords"]}1import { Actor } from 'apify';2import axios from 'axios';3
4const API_URL = 'https://combot.org/api/chart/all';5const SITE_BASE = 'https://combot.org';6
7const DEFAULT_HEADERS = {8 accept: '*/*',9 'accept-language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',10 'cache-control': 'no-cache',11 pragma: 'no-cache',12 'sec-ch-ua': '"Chromium";v="148", "Google Chrome";v="148", "Not/A)Brand";v="99"',13 'sec-ch-ua-mobile': '?0',14 'sec-ch-ua-platform': '"macOS"',15 'sec-fetch-dest': 'empty',16 'sec-fetch-mode': 'cors',17 'sec-fetch-site': 'same-origin',18 'user-agent':19 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',20};21
22class TelegramGroupsSearchScraper {23 normalizeOptionalString(value) {24 if (value === undefined || value === null) return '';25 return String(value).trim();26 }27
28 buildReferer(lng, offset, pageLimit) {29 const page = Math.floor(offset / pageLimit) + 1;30 const params = new URLSearchParams({31 lng: lng || 'all',32 page: String(page),33 });34 return `${SITE_BASE}/top/telegram/groups?${params.toString()}`;35 }36
37 getAxiosConfig(proxyUrl) {38 if (!proxyUrl) return {};39
40 const parsed = new URL(proxyUrl);41 return {42 proxy: {43 protocol: parsed.protocol.replace(':', ''),44 host: parsed.hostname,45 port: Number(parsed.port),46 ...(parsed.username47 ? {48 auth: {49 username: decodeURIComponent(parsed.username),50 password: decodeURIComponent(parsed.password),51 },52 }53 : {}),54 },55 };56 }57
58 mapGroupItem(keyword, item) {59 const username = item.u || null;60 const avatarBase64 = item.i || null;61
62 return {63 searchKeyword: keyword || null,64 rank: item.p ?? null,65 title: item.t || null,66 username,67 members: item.s ?? null,68 positionChange: item.pc || null,69 language: item.l || null,70 chatId: item.c ?? null,71 boostCount: item.b ?? null,72 additionalInfo: item.a || null,73 avatarBase64,74 avatarUrl: avatarBase64 ? `data:image/jpeg;base64,${avatarBase64}` : null,75 telegramUrl: username ? `https://t.me/${username}` : null,76 scrapedAt: new Date().toISOString(),77 };78 }79
80 async run(input) {81 const {82 keywords,83 lng = 'all',84 limit = 100,85 maxItems = Infinity,86 proxyConfiguration,87 } = input;88
89 if (!Array.isArray(keywords) || keywords.length === 0) {90 throw new Error('Input must include a non-empty keywords array');91 }92
93 this.lng = this.normalizeOptionalString(lng) || 'all';94 this.pageLimit = Math.min(Math.max(Number(limit) || 100, 1), 100);95 this.maxItems = maxItems;96
97 const proxyConfig = proxyConfiguration98 ? await Actor.createProxyConfiguration(proxyConfiguration)99 : undefined;100
101 for (const rawKeyword of keywords) {102 const keyword = String(rawKeyword ?? '').trim();103 const proxyUrl = proxyConfig ? await proxyConfig.newUrl() : undefined;104 const axiosConfig = this.getAxiosConfig(proxyUrl);105
106 await this.scrapeKeyword(keyword, axiosConfig);107 await this.randomDelay(500, 1500);108 }109 }110
111 async scrapeKeyword(keyword, axiosConfig) {112 const label = keyword ? `"${keyword}"` : 'top groups';113 console.log(`Searching Telegram groups for ${label}...`);114
115 const seenChatIds = new Set();116 let offset = 0;117 let totalSaved = 0;118
119 while (totalSaved < this.maxItems) {120 const page = Math.floor(offset / this.pageLimit) + 1;121 console.log(`Fetching page ${page} (offset ${offset}) for ${label}...`);122
123 let items;124 try {125 const params = {126 limit: this.pageLimit,127 offset,128 lng: this.lng,129 };130
131 if (keyword) {132 params.q = keyword;133 }134
135 const response = await axios.get(API_URL, {136 ...axiosConfig,137 params,138 headers: {139 ...DEFAULT_HEADERS,140 Referer: this.buildReferer(this.lng, offset, this.pageLimit),141 },142 timeout: 60000,143 });144
145 items = Array.isArray(response.data) ? response.data : [];146 } catch (error) {147 const message = error.response?.data?.message || error.message;148 console.error(`API request failed for ${label}:`, message);149 if (totalSaved === 0) {150 await Actor.pushData([151 {152 searchKeyword: keyword || null,153 error: message,154 scrapedAt: new Date().toISOString(),155 },156 ]);157 }158 break;159 }160
161 if (items.length === 0) {162 console.log(`No more results for ${label}`);163 break;164 }165
166 const currentData = [];167 for (const item of items) {168 if (totalSaved >= this.maxItems) break;169
170 const dedupeKey = item.c ?? item.u;171 if (dedupeKey !== undefined && dedupeKey !== null && seenChatIds.has(dedupeKey)) {172 continue;173 }174 if (dedupeKey !== undefined && dedupeKey !== null) {175 seenChatIds.add(dedupeKey);176 }177
178 currentData.push(this.mapGroupItem(keyword, item));179 totalSaved++;180 }181
182 if (currentData.length > 0) {183 console.log(`Saved ${currentData.length} groups from page ${page}`);184 await Actor.pushData(currentData);185 }186
187 if (totalSaved >= this.maxItems) break;188 if (items.length < this.pageLimit) {189 console.log(`Last page received for ${label}`);190 break;191 }192
193 offset += this.pageLimit;194 await this.randomDelay(800, 1500);195 }196
197 console.log(`Finished ${label} with ${totalSaved} groups`);198 }199
200 async randomDelay(min = 500, max = 1500) {201 const delay = Math.floor(Math.random() * (max - min + 1) + min);202 await new Promise((resolve) => setTimeout(resolve, delay));203 }204}205
206await Actor.init();207
208Actor.main(async () => {209 const input = await Actor.getInput();210
211 // const input = {212 // "keywords": ["ai"],213 // "lng": "all",214 // "limit": 100,215 // "maxItems": 30216 // };217
218 const scraper = new TelegramGroupsSearchScraper();219 await scraper.run(input);220});# configurations.idea
# crawlee and apify storage foldersapify_storagecrawlee_storagestorage
# installed filesnode_modules
# git folder.gitroot = true
[*]indent_style = spaceindent_size = 4charset = utf-8trim_trailing_whitespace = trueinsert_final_newline = trueend_of_line = lf{ "extends": "@apify", "root": true}# This file tells Git which files shouldn't be added to source control
.DS_Store.idea.zednode_modulesstorage{ "name": "js-scrape-single-page", "version": "0.0.1", "type": "module", "description": "This is an example of an Apify actor.", "engines": { "node": ">=18.0.0" }, "dependencies": { "apify": "^3.4.4", "crypto-js": "^4.1.1", "node-fetch": "3", "uuid": "^11.1.0", "ioredis": "^5.4.1", "axios": "^1.7.7" }, "scripts": { "start": "node ./src/main.js", "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1" }, "author": "It's not you it's me", "license": "ISC"}