|
|
from crawlers.MembersParliamentCrawler import *
|
|
|
|
from wikidata.wdPEP import *
|
|
|
|
config = 'crawlers/config.yaml'
|
|
listOfCountries = ['nicaragua']
|
|
|
|
|
|
|
|
# doing the crawling of government websites
|
|
|
|
#Crawler = membersParliamentCrawler(config)
|
|
|
|
#Crawler.downloadMemberListPagesOfCountries(listOfCountries)
|
|
|
|
#Crawler.parseMemberListData2dictionary(listOfCountries)
|
|
|
|
#Crawler.downloadMemberDataHtmls(listOfCountries)
|
|
|
|
#Crawler.parseMemberData2dictionary(listOfCountries)
|
|
|
|
# processing the resulted dictionary and create wikidata queries
|
|
|
|
wikidataPEP = WikidataPEP(config)
|
|
|
|
#wikidataPEP.importMembersOfParliamentDict(listOfCountries)
|
|
|
|
#wikidataPEP.checkForEntityIds(listOfCountries)
|
|
|
|
#wikidataPEP.createMemberOnWikidata()
|
|
|
|
#wikidataPEP.editMemberOnWikidata()
|