If we have sv:WIkipedia article linking SBL and compare with Wikidata records with P3217 but no sv:WIkipedia article

Find Wikidata duplicates linking SBL

#Find duplicate SBL WD records .....
# SBL but no sv article https://w.wiki/NUT
#Version 0.2 add blacklist
__version__ = "0.2"
__author__ = "Magnus Sälgö"

print ("version: ",__version__)
import requests
from bs4 import BeautifulSoup

# pip install sparqlwrapper
# https://rdflib.github.io/sparqlwrapper/

import sys
from SPARQLWrapper import SPARQLWrapper, JSON

endpoint_url = "https://query.wikidata.org/sparql"

query = """SELECT ?item ?SBL
WHERE {
    ?item wdt:P3217 ?SBL.
    ?item wdt:P31 wd:Q5.
    minus { ?languagelink schema:about ?item.
           ?languagelink schema:inLanguage "sv"}
  SERVICE wikibase:label { bd:serviceParam wikibase:language "sv" }
} """

noWikipediaArticleList = []
def get_results(endpoint_url, query):
    user_agent = "CheckSBLduplicates/%s.%s" % (sys.version_info[0], sys.version_info[1])
    sparql = SPARQLWrapper(endpoint_url, agent=user_agent)
    sparql.setQuery(query)
    sparql.setReturnFormat(JSON)
    return sparql.query().convert()


results = get_results(endpoint_url, query)

for result in results["results"]["bindings"]:
    SBLvalue= (result["SBL"]["value"])
    #print(SBLvalue)
    noWikipediaArticleList.append(SBLvalue);

urls = ["https://sv.wikipedia.org/w/index.php?title=Special:L%C3%A4nks%C3%B6kning&limit=7000&offset=0&target=http%3A%2F%2Fsok.riksarkivet.se%2Fsbl%2FPresentation.aspx%3Fid%3D",
        "https://sv.wikipedia.org/w/index.php?title=Special:L%C3%A4nks%C3%B6kning&limit=5000&offset=5000&target=http%3A%2F%2Fsok.riksarkivet.se%2Fsbl%2FPresentation.aspx%3Fid%3D"]
searchURLWikipedia = "https://sv.wikipedia.org/w/index.php?title=Special%3AL%C3%A4nks%C3%B6kning&target=http%3A%2F%2Fsok.riksarkivet.se%2Fsbl%2FPresentation.aspx%3Fid%3D"
searchURLWikidata = "https://www.wikidata.org/wiki/Special:Search?fulltext=S%C3%B6k+efter+%2710922%27&fulltext=Search&ns0=1&ns120=1&search=haswbstatement%3AP3217%3D"
nr_found = 0

blackList = ["18073"] # example page Malldiskussion:SBL
blackList.append("16788") # släktartikel
blackList.append("19122") # släktartikel
blackList.append("5552") # släktartikel
blackList.append("5910") # diskussionssida
blackList.append("7585") # Malldiskussion:SBL


for url in urls:
    response = requests.get(url)
    soup = BeautifulSoup(response.text, "html.parser")
    soup.findAll('a')
    one_a_tag = soup.findAll('a')[0]
    for i in range(1, len(soup.findAll('a'))):
        one_a_tag = soup.findAll('a')[i]
        one_a_tag_href = one_a_tag['href']
        if  str("sok.riksarkivet.se/sbl/Presentation.aspx?id=").lower() in str(one_a_tag_href).lower():
            SBLid = one_a_tag.text.replace("http://sok.riksarkivet.se/sbl/Presentation.aspx?id=","")
            if (SBLid  in noWikipediaArticleList) and (SBLid not in blackList):
                print ("SBL: " + str(SBLid))
                print ("\t", searchURLWikidata + str(SBLid), " ")
                print ("\t", searchURLWikipedia + str(SBLid), " ")
                nr_found = nr_found + 1

print(f'Nr possible duplicates found: {nr_found}')

/usr/local/bin/python3.8 /Users/magnus/Library/Preferences/PyCharmCE2019.2/scratches/scratch_42.py
version: 0.2
Nr possible duplicates found: 0

Process finished with exit code 0