started wikidataPEP class, based on wikibaseintegrator pip package

main.py

@@ -1,13 +1,16 @@
 
 from crawlers.MembersParliamentCrawler import *
 
-
+from wikidata.wdPEP import *
 
 config = 'crawlers/config.yaml'
 listOfCountries = ['nicaragua']
 
 
-Crawler = membersParliamentCrawler(config)
+
+# doing the crawling of government websites
+
+#Crawler = membersParliamentCrawler(config)
 
 #Crawler.downloadMemberListPagesOfCountries(listOfCountries)
 
@@ -15,4 +18,10 @@ Crawler = membersParliamentCrawler(config)
 
 #Crawler.downloadMemberDataHtmls(listOfCountries)
 
-Crawler.parseMemberData2dictionary(listOfCountries)
+#Crawler.parseMemberData2dictionary(listOfCountries)
+
+# processing the resulted dictionary and create wikidata queries
+
+wikidataPEP = WikidataPEP(config)
+
+wikidataPEP.importMembersOfParliamentDict(listOfCountries)

wikidata/wdPEP.py

@@ -0,0 +1,37 @@
+
+
+import os
+
+import yaml
+import json
+
+
+
+class WikidataPEP(object):
+    
+    def __init__(self, configFile):
+        
+        with open(configFile, "r") as stream:
+            try:
+                self.config = yaml.safe_load(stream)
+            except yaml.YAMLError as exc:
+                print(exc)
+  
+    
+    def importMembersOfParliamentDict(self, listOfCountries):
+        
+        self.fullDictionaryMemberLists = {}
+        
+        for country in listOfCountries:
+            
+            print('started to parse data of member of ' + country + ' ..')
+            
+            f = open('crawlers/output/' + country +'MemberList.txt')
+            text = f.read()
+            
+            self.fullDictionaryMemberLists[country] = eval(text)
+            
+        print(self.fullDictionaryMemberLists)
+            
+            
+