corrected link glueing for pdf links for loop

main.py

@@ -5,20 +5,21 @@ import sys
 
 config = "spiders/config.yaml"
 #list_of_fdbs = eval(sys.argv[1])
-list_of_fdbs = ["giz","evergabe-online"]
+#list_of_fdbs = ["giz","evergabe-online"]
+list_of_fdbs = ["giz"]
 
 
 # doing the crawling of government websites
 
 spider = fdb_spider(config)
 
-spider.download_entry_list_pages_of_funding_databases(list_of_fdbs)
+#spider.download_entry_list_pages_of_funding_databases(list_of_fdbs)
 
 #spider.find_config_parameter(list_of_fdbs)
 
-spider.parse_entry_list_data2dictionary(list_of_fdbs)
+#spider.parse_entry_list_data2dictionary(list_of_fdbs)
 
-spider.download_entry_data_htmls(list_of_fdbs)
+#spider.download_entry_data_htmls(list_of_fdbs)
 
 spider.parse_entry_data2dictionary(list_of_fdbs)
 

spiders/config.yaml

@@ -57,8 +57,8 @@ giz:
     link1:  'https://ausschreibungen.giz.de/Satellite/company/welcome.do?method=showTable&fromSearch=1&tableSortPROJECT_RESULT=2&tableSortAttributePROJECT_RESULT=publicationDate&selectedTablePagePROJECT_RESULT='
     link2:  ''
     jsdomain: 'None'
-    iteration-var-list:  "[1,2,3,4,5,6,7]"
-    #iteration-var-list:  "[1,2]"
+    #iteration-var-list:  "[1,2,3,4,5,6,7]"
+    iteration-var-list:  "[1,2]"
     #parent:  "//html//body//div//main//div//div[@class='row']//div[@class='large-12']//a[@class='c-teaser']"
     parent:  "//html//body//div//div//table[contains(@class, 'csx-new-table')]//tbody//tr"
     child-name:  "//td[3]//text()"

spiders/config.yaml.save

@@ -0,0 +1,110 @@
+# 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]'
+    #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:
+    link1:  'https://www.foerderinfo.bund.de/SiteGlobals/Forms/foerderinfo/bekanntmachungen/Bekanntmachungen_Formular.html?gtp=407348_list%253D'
+    link2:  '#searchResults'
+    # here jsdomain has to be specified None with this syntax, if html pages of entrylists are not depending on javascript actions
+    jsdomain: 'None'
+    iteration-var-list:  '[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30]'
+    #iteration-var-list:  '[1,2]'
+    #parent:  "//html//body//div//main//div//div[@class='row']//div[@class='large-12']//a[@class='c-teaser']"
+    parent:  "//html//body//div//main//div[@class='row']//a[contains(@class, 'c-teaser--announcement')]"
+    child-name:  "//div[@class='c-teaser__text-wrapper']//span[@class='c-teaser__title']/text()"
+    javascript-link: ""
+    child-link:  "/@href"
+    child-info:  "//div[@class='c-teaser__text-wrapper']//div[@class='c-teaser__text']/p/text()"
+    #child-period:  "//div[@class='c-teaser__text-wrapper']//small[@class='c-topline']/span[@class='c-topline__item']/text()"
+    child-period:  "//div[@class='c-teaser__text-wrapper']//small//span/time/text()"
+    child-sponsor: "//div[@class='c-teaser__text-wrapper']//small[@class='c-topline']//span[@class='c-topline__item']/span[@class='c-topline__category']/text()"
+  entry:
+    general:
+      uniform: 'FALSE'
+    unitrue:
+      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'
+    unifalse:
+      wordlist:  "['Mobilität', 'Energie', 'Off-grid', 'regenerative Energien', 'Solar', 'Energienetze', 'Elektromobilität']"
+giz:
+  domain: 'https://ausschreibungen.giz.de'
+  entry-list:
+    link1:  'https://ausschreibungen.giz.de/Satellite/company/welcome.do?method=showTable&fromSearch=1&tableSortPROJECT_RESULT=2&tableSortAttributePROJECT_RESULT=publicationDate&selectedTablePagePROJECT_RESULT='
+    link2:  ''
+    jsdomain: 'None'
+    #iteration-var-list:  "[1,2,3,4,5,6,7]"
+    iteration-var-list:  "[1,2]"
+    #parent:  "//html//body//div//main//div//div[@class='row']//div[@class='large-12']//a[@class='c-teaser']"
+    parent:  "//html//body//div//div//table[contains(@class, 'csx-new-table')]//tbody//tr"
+    child-name:  "//td[3]//text()"
+    child-link:  "//a/@href"
+    javascript-link: "/td[6]/a"
+    child-info:  "/td[4]/text()[1]"
+    child-period:  "//td[2]/abbr/text()"
+    #child-period:  "//div[@class='c-teaser__text-wrapper']//small//span/time/text()"
+    child-sponsor: "/tr/td[4]/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'
+      text:  '/html/body/div[2]/div[4]/div/div[5]/div/table/tbody/tr/td[5]/a
+      #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']"
+evergabe-online:
+  domain: 'https://www.evergabe-online.de/'
+  entry-list:
+    link1: 'https://www.evergabe-online.de/search.html?101-1.-searchPanel-results-searchResults-results-topToolbars-toolbars-1-span-navigator-navigation-'
+    link2: '-pageLink'
+    jsdomain: 'https://www.evergabe-online.de/search.html'
+    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]"
+    #jsiteration-var-list: "[1,2, 3]"
+    iteration-var-list: "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102]"
+    #iteration-var-list: "[1, 2, 3]"
+    parent:  "/html/body/div[8]/main/div[4]/div/div/div[2]/table/tbody//tr"
+    child-name:  "//td[1]/div/a/text()"
+    child-link:  "//td[1]/div/a/@href"
+    javascript-link: ""
+    child-info:  "//td[3]/div/text()"
+    child-period:  "//td[5]/text()"
+    child-sponsor: "//td[2]/div/text()"
+  entry:
+    general:
+      uniform: 'FALSE'
+    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']"

spiders/fdb_spider.py

@@ -718,6 +718,14 @@ class fdb_spider(object):
                                 
                                 file_name = "spiders/pages/" + fdb + str(i) + "/" + str(entry_id) + ".pdf"
                                 entry_link = dictionary_entry_list[entry_id]["link"]
+                                print('that is the child: ' + child)
+                                if 'http' in child:
+                                    try:
+                                        response = requests.get(child)
+                                    except Exception as e:
+                                        print(child + ' does not appear to be valid pdf link to download, original message is ' + e)
+                                        
+                                
                                 if 'http' not in child:
                                     if 'javascript' or 'js' not in entry_link and 'http' in entry_link:
                                         try:
@@ -731,15 +739,21 @@ class fdb_spider(object):
                                             if entry_domain[-1] == '/':
                                                 pdf_link = entry_domain[:-1] + child[1:]
                                             if entry_domain[-1] != '/':
+                                                #print('it got into OIOIOIOOIOI')
+                                                #print('before loop ', entry_domain)
+                                                cut_value = 0
                                                 for n in range(len(entry_domain)):
                                                     if entry_domain[-n] != '/':
-                                                        entry_domain = entry_domain[:-1]
+                                                        cut_value += 1
+                                                        
                                                     else:
                                                         break
-                                                        
                                                 
+                                                entry_domain = entry_domain[:-cut_value]
+                                                #print('after loop ', entry_domain)
                                                 
                                                 pdf_link = entry_domain + child[1:]
+                                                #print('the pdf link after recursive until slash: ', pdf_link)
                                             
                                         if child[0] == '/':
                                             if entry_domain[-1] == '/':