Extract and order sections from 10-K annual reports

I am a researcher at Wharton. I need to extract the text from the 10-K annual reports of the companies (available online at the EDGAR database). The problem is that there is no single format required, so many companies post text files, while others do HTML or XML. The 10-Ks are divided into sections, [login to view URL] , and I would need the text for each section and the code to extract these sections. I have been using Regex to obtain these sections so far.