Web Scraping and Text Extraction
- PPT : Link
- Beautiful Soup and Flipkart Mini Project : Link
- Text Extraction Code and Text from Multiple Images Detection Mini Project : Link
- Sample File : Open Sample Files Folder above and download required file type
- Self Learning Web Scraping Book Resource : Link
Star and fork this repository for future help
For any queries : Link
Projects/opportunities for future
- Share Predictor: Live share/stock market graph data scraping, implimenting basic machine learning models and then making a web application telling me probability to buy a particular share or not, or suggeting me the right time to buy or sell.
- Handwriting Recogniser: Train your own OCR model to read handwritings in different languages like English, Hindi, Punjabi etc. Try cursive text, doctor's handwriting, any bill which has something handwritten on it.
- Your Own Google Lens: Merge many ocr models to extract text, qr codes, images. Compare the scraped data together. Search the most repeated words or images on backend and show most relavent searches.
- Kaggle Dataset Master: Scrape different websites, get relavent filtered information, upload datasets on kaggle like platform. Ask your friends to upvote you, add comments on dataset. If dataset is good and big upto 10k entries ask RANA SIR to host a kaggle competition with your dataset.
- Cold Emailing: Write a code - just put a url, and scrape all email IDs. And automatically cold email them. Use filter like hr@company.com