Update Wikidata_Text_Parser.py

Wikidata_Text_Parser.py

@@ -870,8 +870,11 @@ def html2text(html_set):
     splitter = SentenceSplitter(language='en')
 
     seg = pysbd.Segmenter(language="en", clean=False)
+    
+    if not spacy.util.is_package("en_core_web_lg"):
+        os.system("python -m spacy download en_core_web_lg")
 
-    nlp = spacy.load("base/en_core_web_lg")
+    nlp = spacy.load("en_core_web_lg")
 
     text = reference_html_df.loc[0,'extracted_text']