From 094f0922916ef12370e3175179aa1aa88fd965d3 Mon Sep 17 00:00:00 2001 From: alpcentaur Date: Tue, 23 Jan 2024 17:17:40 +0100 Subject: [PATCH] deleted fdb entry that was a ghost for syntax reasons, but same syntax should be in other fdb anyway --- .../__pycache__/fdb_spider.cpython-311.pyc | Bin 41231 -> 41199 bytes spiders/config.yaml | 24 ++---------------- 2 files changed, 2 insertions(+), 22 deletions(-) diff --git a/spiders/__pycache__/fdb_spider.cpython-311.pyc b/spiders/__pycache__/fdb_spider.cpython-311.pyc index 29b9f66ea7ed57753b1a68756249d0f141287225..fd4f9608bb1edb1c8df9e1426da29624f79a406d 100644 GIT binary patch delta 33 ncmeA_#Pt3k6W4NHUM>b8NSL>g>oyacntoA!e#vHTW|nyXu-OUo delta 65 zcmaEVkg5L=6W4NHUM>b8SkSbQ>o${`n|?-qZmND_PC;^NUP)qUk$yo@epYIBiEg5P TT1t{`aY1HEYSHG`Of2&N+X5Fv diff --git a/spiders/config.yaml b/spiders/config.yaml index a8b25d3..176bb07 100644 --- a/spiders/config.yaml +++ b/spiders/config.yaml @@ -2,27 +2,7 @@ # 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]' - #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: domain: 'http://foerderinfo.bund.de' entry-list: @@ -95,7 +75,7 @@ evergabe-online: child-link: "//td[1]/div/a/@href" javascript-link: "" child-info: "//td[3]/div/text()" - child-period: "//td[5]/text()" + child-period: "//td[4]/text()" child-sponsor: "//td[2]/div/text()" entry: general: