fix: typing annotation for set python 3.8

newspaper/article.py

@@ -8,7 +8,7 @@
 import os
 import glob
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Set
 from urllib.parse import urlparse
 import lxml
 
@@ -98,7 +98,7 @@ class Article:
             the first config.MAX_KEYWORDS keywords.
         meta_keywords (List[str]):  A list of keywords provided by the meta data.
             It will be truncated to the first config.MAX_KEYWORDS keywords.
-        tags (set[str]): Extracted tag list from the article body
+        tags (Set[str]): Extracted tag list from the article body
         authors (List[str]): The author list parsed from the article. It will
             be truncated to the first config.MAX_AUTHORS authors.
         publish_date (str): The parsed publishing date from the article. If no
@@ -233,7 +233,7 @@ def __init__(
         self.meta_keywords: List[str] = []
 
         # `tags` are also extracted via parse() from <meta> tags
-        self.tags: set[str] = set()
+        self.tags: Set[str] = set()
 
         # List of authors who have published the article, via parse()
         self.authors: List[str] = []

newspaper/extractors/metadata_extractor.py

@@ -1,5 +1,5 @@
 import re
-from typing import Any, Dict, Optional
+from typing import Any, Dict, Optional, Set
 from urllib.parse import urlparse, urlunparse
 
 import lxml
@@ -165,7 +165,7 @@ def _get_metadata(self, doc: lxml.html.Element) -> Dict[str, Any]:
                 ref = ref[part]
         return data
 
-    def _get_tags(self, doc: lxml.html.Element) -> set[str]:
+    def _get_tags(self, doc: lxml.html.Element) -> Set[str]:
         """Extracts tags from the article's HTML"""
 
         elements = self.parser.css_select(

newspaper/nlp.py

@@ -11,11 +11,11 @@
 import math
 from pathlib import Path
 from collections import Counter
-from typing import List
+from typing import List, Set
 
 from . import settings
 
-stopwords: set[str] = set()
+stopwords: Set[str] = set()
 
 
 def load_stopwords(language):