An automated tool that identifies people from images using reverse image search and gathers detailed information about them from the internet.
- Reverse Image Search: Uses Google Lens (via SerpApi) to identify people from provided images.
- Automated Info Gathering: Once identified, it searches for biographies and key information about the person.
- Point-wise Results: Presents gathered information in a clear, bulleted list.
- Error Handling: Notifies if the person cannot be identified or if no information is available online.
- Language: TypeScript
- Runtime: Node.js
- API: SerpApi (Google Lens & Google Search)
- Libraries:
axios,dotenv
- Node.js (v16 or higher)
- A SerpApi Account to get your API key.
-
Clone the repository:
git clone <repository-url> cd information-scrapper
-
Install dependencies:
npm install
-
Configure Environment:
-
Add Images: Place the images you want to scrape into the
images/folder. Supported formats:.jpg,.jpeg,.png. -
Run the Tool:
npm start
information-scrapper/
├── images/ # Target images for identification
├── src/
│ ├── index.ts # Main entry point and file handler
│ └── scraper.ts # Core logic for API interaction and data extraction
├── .env # Private API keys (ignored by git)
├── .env.example # Template for environment variables
├── package.json # Scripts and dependencies
└── tsconfig.json # TypeScript configuration
The Google Lens API requires images to be accessible via a public URL.
Current implementation:
- The tool scans the
images/folder. - To successfully identify people, the image paths provided to the API must be public URLs.
- Recommendation: For local images, integrate a cloud upload service (like Imgur or AWS S3) to host the image temporarily before passing the URL to the scraper.
ISC License