playing around https://docs.python.org/3/library/ with devTools coding for fun

#list-libraries-by-index-doc.js

/* TEST: URL == 'https://docs.python.org/3/library/'*/
[
  ...new Set(
    Array.from(
      document.querySelectorAll("a")
    ).map(
      (x)=>x.href
    ).filter(
      (x)=>x.includes('https://docs.python.org/3/library/')
    ).map(
      (x)=>x.substring(
        "https://docs.python.org/3/library/".length
      ).split(
        ".html"
      )
    ).filter(
      (x)=>x.length==2
    ).map(
      (x)=>x[0]
    )
  )
]
//for me above code returns array with 268 elements, 
//including 'intro' and 'index' that are not libraries, 
//these are common introduction and index list
//to filter out laminal spaces like that among docs we will need some kind of checking method
// I have 2 proposals of next step:
// - **test it in environment**: usage of Pyodide that acts as python emulator sandbox for webassembly (https://pyodide.org/en/stable/)
// - **read these docs more**: usage of Puppeteer that acts as nodejs web browser automation tool (https://pptr.dev/)

about-library-paragraphs.js

/* TEST: URL == 'https://docs.python.org/3/library/inspect.html#inspect.getfile'*/
[
  ...new Set(
    Array.from(
      document.querySelectorAll("a")
    ).map(
      (x)=>x.href
    ).filter(
      (x)=>x.includes(
        document.location.href.split("#")[0]
      )
    )
  )
]
//v2
[
  ...new Set(
    Array.from(
      document.querySelectorAll("a")
    ).map(
      (x)=>x.href
    ).filter(
      (x)=>(
        x.split("#").length > 1
        &&
        x.includes(
          document.location.href.split("#")[0]
        )
      )
    ).map(
      x=>x.split("#")[1]
    )
  )
]
// instead of writting updated "v2" addon it can be handled by secong git commit next time
// remember to use familiar with what you do descriptions - you adds that commit messages for your own self

python-docs-library-crawling.js

/* TEST: URL == 'https://docs.python.org/3/library/index.html#library-index'*/
HREF_LIST = Array.from(
      document.querySelectorAll("a")
    ).map(
      (x)=>x.href
    );
//what to use
console.log(HREF_LIST.filter(
  x=>x.match(
    new RegExp(/^https\:\/\/docs\.python\.org\/3\/library\/([\w\d\.]+)\.html$/, "i")
  )
))
//or
console.log(HREF_LIST.filter(
  x=>x.includes(
    'https://docs.python.org/3/library/'
  )
))
//these methods are same direction but not same targeting
//both methods can lead to same results but example 
//with regexp will ignore links with paragraph pointing 
/*(
  includes alike 'https://docs.python.org/3/library/termios.html' 
  excludes alike 'https://docs.python.org/3/library/termios.html#termios.tcsetattr'
  )*/