Web scraping for Summer Teams

teams-web-scraping.xqy

(: Web Scraper for Summer Projects :)

declare option output:method "csv";
declare option output:csv "header=yes, separator=comma";

let $doc := fetch:text("https://www.library.vanderbilt.edu/projects") => html:parse()
let $mainContent := $doc//section[@id="maincontent"]
for $project in $mainContent//div[@class="media-body"]
let $projectName := $project/h3[@class="media-heading"]/text()
let $projectParticipants := $project//span[text()="Members"]/following-sibling::text()
let $participants := fn:translate($projectParticipants,":","") => fn:tokenize(",") 
for $participant in $participants
let $name := fn:replace($participant,"^(.+?) ([^\s,]+)(,? (?:[JS]r\.?|III?|IV))?$", "$2,$1$3")
return 
  <csv>
    <row>
      <project>{$projectName}</project>
      <participants>{$name}</participants>
    </row>
  </csv>