|
|
- # 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/
-
- greenjobs:
- domain: 'https://www.greenjobs.de'
- entry-list:
- link1: 'https://www.greenjobs.de/angebote/index.html?s=&loc=&countrycode=de&dist='
- link2: '0&lng=&lat='
- jsdomain: 'NONE'
- #jslink1: '/html/body/div[8]/main/div[4]/div/div/div[2]/table/thead/tr[1]/td/div[2]/div/span['
- #jslink2: ']'
- #jsiteration-var-list: "[1,2, 3, 4, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,6,7,8,9,10]"
- iteration-var-list: "['1']"
- parent: "/html/body/div/div/div/div/main/div[2]/table/tbody//tr"
- child-name: "//td[1]/a/text()"
- child-link: "//td[1]/a/@href"
- #javascript-link: ""
- child-info: "//td[5]/text()"
- child-period: "//td[6]/text()"
- child-sponsor: "//td[3]/text()"
- entry:
- general:
- uniform: 'TRUE'
- unitrue:
- #parent: '//html//body//form//table'
- text: '/html/body/div[2]/div[4]/div/div[5]/div/table/tbody/tr/td[5]/a/@href'
- #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'
- unifalse:
- wordlist: "['Mobilität', 'Energie', 'Off-grid', 'regenerative Energien', 'Solar', 'Energienetze', 'Elektromobilität']"
|
