Keyword Search Engine, Website Crawler NLP-NLG location-wise
The Project has 2 parts. (1) Web crawling where more than 1000+ website is downloading using Httrack. Whole internal website and External 4 levels of depth. (2) keyword searching using elastic Search from crawled data which might be in any language - Chinese, Arabic, Urdu, English, etc. The output shown in dashboard and consist of three parts using NLP & NLG location-wise (1) The paragraphs containing keywords that we searched for both original text and English translation (2) Tree of websites traversed showing links as depth (3) Frequency statistics of keywords. The user has an option of directing the program to crawl sites at a stipulated time like say every 2 3 6 12 hours or one day. 10 results each page. We have tested project on websites of below links where data is more than 50 GB and Searching Speed is 1-2 Second. zhifu.cnki.net xb.81.cn db.81.cn nb.81.cn www.haohanfw.com bbs.tiexue.net www.360doc.com blog.sina.com.cn military.cnr.cn www.weibo.com mil.sina.cn lt.cjdby
เกี่ยวกับฉัน
The Company name is Zplus Software Technology Private Limited . We have 11 years experience in Machine Learning (ML), Artificial Intelligence (AI), Natural Language Processing (NLP), Image Processing, Remote Sensing, Computer Vision, Research Paper Thesis with Java, Python, Django, SQL, PROLOG, C++, R-Programming in Desktop, Mobile Apps and Web Development using SEO Content Management System. We have successfully completed 400+ projects of Object Recognition, LLM , Deep learning, Web crawler, Scraping, Phishing Detection, OCR, Big data, Data Mining, Data Analysis, Statistics, Stock Trading, Semantic Text Analysis, Feature Selection, Image Multi-class Classification using Azure ML, Tensorflow, PyTorch, Amazon, google, Microsoft cloud computing. Networking project (TCP UDP) with Encryption Decryption and Technical Research Writing. We are looking for long-term projects and do contract work with Business Corporates and Individual Client. We have professional developers team for that.
