alpcentaur/fdb-spider
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

deleted fdb entry that was a ghost for syntax reasons, but same syntax should be in other fdb anyway

Browse source
This commit is contained in:
alpcentaur 2024-01-23 17:17:40 +01:00
parent d7d157bf42
commit 094f092291
2 changed files with 2 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

BIN
spiders/__pycache__/fdb_spider.cpython-311.pyc
View file

Binary file not shown.

24
spiders/config.yaml
View file

@ -2,27 +2,7 @@
# Follow the syntax and dont use tbody as it gets added by the browser (when researching xpath through inspector) # 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 # 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/ # 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]'
#iteration-var-list: '[1,2]'
parent: "//html//body//div//main//div//div[@class='row']//section[@class='l-search-result-list']//div[@class='l-search-result-list__item']"
child-name: "//div[@class='c-search-result__text-wrapper']//span[@class='c-search-result__title']/text()"
jsdomain: 'None'
javascript-link: ""
child-link: "/a[@class='c-search-result']/@href"
child-info: "//"
child-period: "/"
child-sponsor: "/"
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'
foerderinfo.bund.de-bekanntmachungen: foerderinfo.bund.de-bekanntmachungen:
domain: 'http://foerderinfo.bund.de' domain: 'http://foerderinfo.bund.de'
entry-list: entry-list:
@ -95,7 +75,7 @@ evergabe-online:
child-link: "//td[1]/div/a/@href" child-link: "//td[1]/div/a/@href"
javascript-link: "" javascript-link: ""
child-info: "//td[3]/div/text()" child-info: "//td[3]/div/text()"
child-period: "//td[5]/text()" child-period: "//td[4]/text()"
child-sponsor: "//td[2]/div/text()" child-sponsor: "//td[2]/div/text()"
entry: entry:
general: general: