illyism/instagram-scraper — explained in plain English
Analysis updated 2026-05-18
Download and rank a public creator's Reel transcripts by play count to study strong video hooks.
Feed a bank of transcribed hooks into an AI tool like Cursor or Claude to write new Reel scripts.
Export a single combined transcript file ready to paste into ChatGPT or Google AI Studio.
| illyism/instagram-scraper | agi-ruby/ai-gpt_image2-seedance_2.0-video-skills | arindam200/wisprgemma | |
|---|---|---|---|
| Stars | 10 | 10 | 10 |
| Language | JavaScript | JavaScript | JavaScript |
| Setup difficulty | easy | easy | moderate |
| Complexity | 2/5 | 1/5 | 3/5 |
| Audience | general | vibe coder | general |
Figures from each repo's GitHub metadata at analysis time.
Requires a free Scrape Creators API key added to a .env file before running.
This tool downloads transcripts from a public Instagram creator's Reels, sorts them by how many plays they got, and saves everything into a local folder you can paste directly into an AI chat tool like Cursor, Claude, or Google AI Studio. It relies on a third party service called Scrape Creators to fetch public Instagram data, so there is no need to log into Instagram or run a browser automation setup. The idea behind the project is that writing an attention grabbing opening line for a short video is a skill you can learn by studying examples, rather than something you either have or do not. The suggested process is to pick a creator whose videos already hold attention well, download their top performing Reels along with AI generated transcripts, pull out just the first line of each one, and then feed that collection of opening lines into a language model along with a focused prompt for writing new ones. This repository handles the first three steps, and includes a folder of prompt templates for the fourth. To use it, you clone the repository, copy an example environment file, get a free API key from the Scrape Creators website, and run a single command pointing at the creator's Instagram handle. The tool then produces several output files, including a ranked list of hook lines, a single combined file of all transcripts ready to paste into an AI tool, individual transcript files per video, and machine readable index and profile files. The tool only works on public Instagram profiles and Reels shorter than about two minutes, and transcripts will come back empty for videos that are silent or only contain music. The README explicitly states this is meant for studying patterns in short video writing, not for copying someone's voice or claiming their personal stories as your own, and asks users to respect Instagram's terms of service. The project is released under the MIT license.
A tool that downloads a public Instagram creator's Reel transcripts, ranks them by plays, and builds a local hook bank you can feed into an AI writing tool.
Mainly JavaScript. The stack also includes JavaScript, Node.js.
Permissive open-source license, use freely for personal or commercial purposes.
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.