reelflow
Version:
Elegant and powerful Instagram video downloader for seamless content extraction
155 lines (154 loc) • 6.77 kB
JavaScript
;
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.InstagramDownloader = void 0;
const axios_1 = __importDefault(require("axios"));
const cheerio_1 = require("cheerio");
const types_js_1 = require('./types.cjs');
const utils_js_1 = require('./utils.cjs');
const constants_js_1 = require('./constants.cjs');
class InstagramDownloader {
async getPostPageHTML(postId) {
try {
const response = await axios_1.default.get(`${constants_js_1.INSTAGRAM_BASE_URL}${constants_js_1.INSTAGRAM_ENDPOINTS.POST}/${postId}`, {
headers: constants_js_1.WEBPAGE_HEADERS
});
return response.data;
}
catch (error) {
if (axios_1.default.isAxiosError(error)) {
throw new types_js_1.InstagramError(error.response?.data?.message || 'Failed to fetch Instagram page', error.response?.status || 500);
}
throw error;
}
}
async getPostGraphqlData(postId) {
try {
const encodedData = (0, utils_js_1.encodeGraphqlRequestData)(postId);
const response = await axios_1.default.post(`${constants_js_1.INSTAGRAM_BASE_URL}${constants_js_1.INSTAGRAM_ENDPOINTS.GRAPHQL}`, encodedData, {
headers: constants_js_1.GRAPHQL_HEADERS
});
return response.data;
}
catch (error) {
if (axios_1.default.isAxiosError(error)) {
throw new types_js_1.InstagramError(error.response?.data?.message || 'Failed to fetch GraphQL data', error.response?.status || 500);
}
throw error;
}
}
async getVideoInfoFromHTML(postId) {
const html = await this.getPostPageHTML(postId);
const $ = (0, cheerio_1.load)(html);
return (0, utils_js_1.formatPageJson)($);
}
async getVideoInfoFromGraphQL(postId) {
const data = await this.getPostGraphqlData(postId);
const mediaData = data.data?.xdt_shortcode_media;
if (!mediaData) {
return null;
}
if (!mediaData.is_video) {
throw new types_js_1.InstagramError('This post is not a video', 400);
}
return (0, utils_js_1.formatGraphqlJson)(mediaData);
}
async getVideoInfo(url) {
const validationError = (0, utils_js_1.validateInstagramURL)(url);
if (validationError) {
throw new types_js_1.InstagramError(validationError, 400);
}
const postId = (0, utils_js_1.getPostIdFromUrl)(url);
if (!postId) {
throw new types_js_1.InstagramError('Could not extract post ID from URL', 400);
}
// Get the HTML first to extract media info
const html = await this.getPostPageHTML(postId);
const mediaInfo = await this.extractMediaInfo(html);
// Try webpage method first
let videoInfo = await this.getVideoInfoFromHTML(postId);
if (videoInfo) {
return {
...videoInfo,
username: mediaInfo.username,
description: mediaInfo.description,
thumbnail: mediaInfo.thumbnail
};
}
// Fallback to GraphQL method
videoInfo = await this.getVideoInfoFromGraphQL(postId);
if (videoInfo) {
return {
...videoInfo,
username: mediaInfo.username,
description: mediaInfo.description,
thumbnail: mediaInfo.thumbnail
};
}
throw new types_js_1.InstagramError('Could not fetch video information', 404);
}
async extractMediaInfo(html) {
try {
const $ = (0, cheerio_1.load)(html);
// Get thumbnail URL
const thumbnail = $('meta[property="og:image"]').attr('content') || undefined;
// Get description and username from meta description
const rawDescription = $('meta[property="og:description"]').attr('content') || '';
let description = undefined;
let username = undefined;
// Try to extract username from likes format first (e.g., "2,420 likes, 13 comments - almas.graphi on...")
const likesMatch = rawDescription.match(/- (.*?) on/); // Match everything between "- " and " on"
if (likesMatch && likesMatch[1]) {
// Get the username part and remove any trailing spaces
username = likesMatch[1].replace(/\s+$/, '');
// Extract description by removing the likes/comments/date part
const descMatch = rawDescription.match(/^[^-]+ - [^\ ]+ on [^]+(.+)$/);
if (descMatch) {
// Remove quotes and trim
description = descMatch[1].trim().replace(/^["']|["']$/g, '') || undefined;
}
}
else {
// Fallback: try to extract username from description format (username: description)
const usernameMatch = rawDescription.match(/^([^:]+):/);
if (usernameMatch) {
username = usernameMatch[1].split(' on ')[0].trim();
// Remove username from description, quotes, and trim
description = rawDescription.replace(/^[^:]+:\s*/, '').trim().replace(/^["']|["']$/g, '') || undefined;
}
}
// Extract video or image URL
const videoUrl = $('meta[property="og:video"]').attr('content');
const videoWidth = $('meta[property="og:video:width"]').attr('content');
const videoHeight = $('meta[property="og:video:height"]').attr('content');
if (videoUrl && videoWidth && videoHeight) {
return {
url: videoUrl,
type: 'video',
width: videoWidth,
height: videoHeight,
username,
thumbnail,
description,
};
}
const imageUrl = $('meta[property="og:image"]').attr('content');
if (imageUrl) {
return {
url: imageUrl,
type: 'image',
username,
thumbnail,
description,
};
}
throw new Error('No media URL found');
}
catch (error) {
throw new Error(`Failed to extract media info: ${error.message}`);
}
}
}
exports.InstagramDownloader = InstagramDownloader;