How to set the minimum text length in the Content Downloader, as well as prohibit inserting html tags?

Question

Parsing

Hello. 1) You need to parse text from sites. I decided to use the Content Downloader, but I ran into a problem that I just don’t understand how to set the minimum number of characters less than which the program simply won’t parse the text.
2) In those texts that I parsed, there are html tags and this is bad. How to remove html tags when parsing?