Discord Bot Search Scraper
Pricing
from $3.99 / 1,000 results
Search Discord bots by name. Extract bot ID, avatar, server count, invite count, and creation date. Perfect for bot discovery, competitor research, and integration scouting. 🤖
Pricing
from $3.99 / 1,000 results
Rating
0.0
(0)
Developer
EasyApi
Maintained by CommunityActor stats
1
Bookmarked
2
Total users
1
Monthly active users
12 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# Check preinstalled packagesRUN npm ls crawlee apify puppeteer playwright
# 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": "discord-bot-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": "Discord Bot Search Scraper Input", "type": "object", "schemaVersion": 1, "properties": { "keywords": { "title": "Search Keywords", "type": "array", "description": "Keywords to search Discord bots by name", "editor": "stringList", "default": [ "ai" ], "prefill": [ "ai" ], "uniqueItems": true, "minItems": 1 }, "from_created": { "title": "Created After", "type": "string", "description": "Bot created on or after this date (YYYY-MM-DD)", "editor": "textfield", "default": "", "prefill": "" }, "to_created": { "title": "Created Before", "type": "string", "description": "Bot created on or before this date (YYYY-MM-DD)", "editor": "textfield", "default": "", "prefill": "" }, "from_invites": { "title": "Min Invites", "type": "string", "description": "Minimum invite count", "editor": "textfield", "default": "", "prefill": "" }, "to_invites": { "title": "Max Invites", "type": "string", "description": "Maximum invite count", "editor": "textfield", "default": "", "prefill": "" }, "from_servers": { "title": "Min Servers", "type": "string", "description": "Minimum server count", "editor": "textfield", "default": "", "prefill": "" }, "to_servers": { "title": "Max Servers", "type": "string", "description": "Maximum server count", "editor": "textfield", "default": "", "prefill": "" }, "maxItems": { "title": "Maximum Results", "type": "integer", "description": "Maximum number of bots to scrape per keyword", "default": 50, "prefill": 50, "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';3import * as cheerio from 'cheerio';4
5const API_BASE = 'https://disdex.io/bots';6const SITE_BASE = 'https://disdex.io';7
8const DEFAULT_HEADERS = {9 accept: '*/*',10 'accept-language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',11 'cache-control': 'no-cache',12 'hx-request': 'true',13 pragma: 'no-cache',14 'sec-ch-ua': '"Chromium";v="148", "Google Chrome";v="148", "Not/A)Brand";v="99"',15 'sec-ch-ua-mobile': '?0',16 'sec-ch-ua-platform': '"macOS"',17 'sec-fetch-dest': 'empty',18 'sec-fetch-mode': 'cors',19 'sec-fetch-site': 'same-origin',20 'user-agent':21 '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',22};23
24const FILTER_FIELDS = [25 'from_created',26 'to_created',27 'from_invites',28 'to_invites',29 'from_servers',30 'to_servers',31];32
33class DiscordBotSearchScraper {34 normalizeFilterValue(value) {35 if (value === undefined || value === null) return '';36 return String(value).trim();37 }38
39 buildFilters(input) {40 const filters = {};41
42 for (const field of FILTER_FIELDS) {43 filters[field] = this.normalizeFilterValue(input[field]);44 }45
46 return filters;47 }48
49 buildQueryParams(keyword, page) {50 const params = new URLSearchParams({51 q: keyword,52 ...this.filters,53 });54
55 if (page) {56 params.set('page', String(page));57 }58
59 return params;60 }61
62 buildSearchUrl(keyword) {63 return `${SITE_BASE}/bots?${this.buildQueryParams(keyword).toString()}`;64 }65
66 buildApiUrl(keyword, page) {67 return `${API_BASE}?${this.buildQueryParams(keyword, page).toString()}`;68 }69
70 getAxiosConfig(proxyUrl) {71 if (!proxyUrl) return {};72
73 const parsed = new URL(proxyUrl);74 return {75 proxy: {76 protocol: parsed.protocol.replace(':', ''),77 host: parsed.hostname,78 port: Number(parsed.port),79 ...(parsed.username80 ? {81 auth: {82 username: decodeURIComponent(parsed.username),83 password: decodeURIComponent(parsed.password),84 },85 }86 : {}),87 },88 };89 }90
91 parseNumber(text) {92 if (!text) return null;93 const value = Number(String(text).replace(/,/g, '').trim());94 return Number.isFinite(value) ? value : null;95 }96
97 parseBots(html, keyword) {98 const $ = cheerio.load(`<table>${html}</table>`);99 const results = [];100
101 $('tr').each((_, element) => {102 const row = $(element);103 const href = row.find('a.row-link.user-display').attr('href') || '';104 const botId = href.split('/').pop() || null;105 const nameText = row.find('a.row-link.user-display').text().trim();106 const badges = [];107
108 row.find('.badges .badge-icon').each((__, badge) => {109 badges.push({110 title: $(badge).attr('title') || null,111 icon: $(badge).attr('src') || null,112 });113 });114
115 results.push({116 searchKeyword: keyword,117 botId,118 name: nameText.replace(/^@/, '') || null,119 avatar: row.find('img.icon-xs').attr('src') || null,120 badges,121 createdAt: row.find('[data-col="created"] .date-full').text().trim() || null,122 servers: this.parseNumber(row.find('[data-col="servers"]').text()),123 invites: this.parseNumber(row.find('[data-col="invites"]').text()),124 scrapedAt: new Date().toISOString(),125 });126 });127
128 return results;129 }130
131 async run(input) {132 const { keywords, maxItems = Infinity, maxPages = Infinity, proxyConfiguration } = input;133
134 if (!Array.isArray(keywords) || keywords.length === 0) {135 throw new Error('Input must include a non-empty keywords array');136 }137
138 this.maxItems = maxItems;139 this.maxPages = maxPages;140 this.filters = this.buildFilters(input);141
142 const proxyConfig = proxyConfiguration143 ? await Actor.createProxyConfiguration(proxyConfiguration)144 : undefined;145
146 for (const rawKeyword of keywords) {147 const keyword = String(rawKeyword || '').trim();148 if (!keyword) continue;149
150 const proxyUrl = proxyConfig ? await proxyConfig.newUrl() : undefined;151 const axiosConfig = this.getAxiosConfig(proxyUrl);152
153 await this.scrapeKeyword(keyword, axiosConfig);154 await this.randomDelay(500, 1500);155 }156 }157
158 async scrapeKeyword(keyword, axiosConfig) {159 const searchUrl = this.buildSearchUrl(keyword);160 const seenIds = new Set();161 let page = 1;162 let totalSaved = 0;163
164 console.log(`Searching Discord bots for "${keyword}"...`);165
166 while (page <= this.maxPages && totalSaved < this.maxItems) {167 const apiUrl = this.buildApiUrl(keyword, page);168 console.log(`Fetching page ${page} for "${keyword}"...`);169
170 let html;171 try {172 const response = await axios.get(apiUrl, {173 ...axiosConfig,174 headers: {175 ...DEFAULT_HEADERS,176 'hx-current-url': searchUrl,177 Referer: searchUrl,178 },179 timeout: 60000,180 });181 html = response.data;182 } catch (error) {183 const message = error.response?.data?.message || error.message;184 console.error(`API request failed for "${keyword}" page ${page}:`, message);185 if (totalSaved === 0) {186 await Actor.pushData([187 {188 searchKeyword: keyword,189 error: message,190 scrapedAt: new Date().toISOString(),191 },192 ]);193 }194 break;195 }196
197 const bots = this.parseBots(html, keyword);198 if (bots.length === 0) {199 console.log(`No more bots on page ${page}`);200 break;201 }202
203 const currentData = [];204 for (const bot of bots) {205 if (totalSaved >= this.maxItems) break;206
207 const dedupeKey = bot.botId || `${bot.name}`;208 if (seenIds.has(dedupeKey)) continue;209 seenIds.add(dedupeKey);210
211 currentData.push(bot);212 totalSaved++;213 }214
215 if (currentData.length > 0) {216 console.log(`Saved ${currentData.length} bots from page ${page}`);217 await Actor.pushData(currentData);218 }219
220 if (totalSaved >= this.maxItems) break;221
222 page++;223 await this.randomDelay(500, 1200);224 }225
226 console.log(`Finished "${keyword}" with ${totalSaved} bots`);227 }228
229 async randomDelay(min = 1000, max = 3000) {230 const delay = Math.floor(Math.random() * (max - min + 1) + min);231 await new Promise((resolve) => setTimeout(resolve, delay));232 }233}234
235await Actor.init();236
237Actor.main(async () => {238 const input = await Actor.getInput();239
240 const scraper = new DiscordBotSearchScraper();241 await scraper.run(input);242});# 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.ideanode_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", "axios": "^1.7.7", "cheerio": "^1.0.0", "crypto-js": "^4.1.1" }, "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"}