|
|
- # 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/
-
- foerderinfo.bund.de:
- domain: 'http://foerderinfo.bund.de'
- entry-list:
- link1: 'https://www.foerderinfo.bund.de/SiteGlobals/Forms/foerderinfo/expertensuche/Servicesuche_Formular.html?gtp=33498_list%253D'
- link2: '#searchResults'
- iteration-var-list: [1,2,3,4,5,6,7,8]
- parent: '//html//body//form//table//tr//td//table//tr'
- child-name: '//td//a/text()'
- child-link: '//td//a/@href'
- entry:
- info-1:
- parent: '//html//body//form//table'
- #child-name: '//html//body//form//table//tr[1]//td[2]//span'
- #child-sum: '//html//body//form//table//tr[2]//td[1]//span//img'
- #child-deadline: '//html/body/form/table/tr[2]/td[3]/span + label.1'
-
|
