# Settings for the PEP crawler per country to crawl # Follow the syntax and dont use tbody as it gets added by the browser (when researching xpath through inspector) # xpath syntax: https://www.w3schools.com/xml/xpath_syntax.asp # lxml xpath syntax: https://www.geeksforgeeks.org/web-scraping-using-lxml-and-xpath-in-python/ nicaragua: domain: 'http://legislacion.asamblea.gob.ni' memberList: link: 'http://legislacion.asamblea.gob.ni/Tablas%20Generales.nsf/Main.xsp' parent: '//html//body//form//table//tr//td//table//tr' child-name: '//td//a/text()' child-link: '//td//a/@href' member: info-1: parent: html/body/form/table child-name: html/body/form/table/tr.0/td.1/span child-image: html/body/form/table/tr.1/td.0/span/img child-role: html/body/form/table/tr.1/td.2/span + label.1 child-politicalParty: html/body/form/table/tr.4/td/span