XML Site Scraper and Link Evaluator

I need someone to scrape XML sites (https://www.egoscue.com/WebMenus/ePeteInstructions/10.xml to https://www.egoscue.com/WebMenus/ePeteInstructions/55000.xml), and evaluate the quality of the links. Discard any of these sites that go to a bad link or go directly to https://egoscue.com/. Attention to detail is crucial for this role. The ideal candidate should have experience in web scraping and data extraction. These sites have exercises on them. I'd like the name and description on each site.