# Article's title title: //h1[contains(concat(' ',normalize-space(@class),' '),' article__title ')] author: //span[contains(concat(' ',normalize-space(@class),' '),' Author__name ')] date: //span[contains(concat(' ',normalize-space(@class),' '),' Article__publishDate ')] # Article's main content body: //h2[contains(concat(' ',normalize-space(@class),' '),' Article__chapo ')] | //div[contains(concat(' ',normalize-space(@class),' '),' article__body ')] # Parts to strip in the content strip: //div[contains(concat(' ',normalize-space(@class),' '),' LinkParagraph ')] # A test URL, e.g. the article you used to write the file test_url: https://www.lequipe.fr/Velo-mag/Decouverte/Actualites/5-regles-d-or-pour-se-rendre-au-travail-a-velo/1143664