Strip perex from Aktuality perex text

Author: davidlukac

modules/rss.py

@@ -3,6 +3,7 @@
 from abc import ABC, abstractmethod
 from pprint import pprint
 from typing import Dict, List
+from bs4 import BeautifulSoup
 
 import feedparser
 
@@ -70,7 +71,7 @@ def parse(self) -> List[RssArticle]:
             title = entry.get('title', '')
             url = entry.get('link', '')
             keywords = entry.get('keywords', [])
-            perex = entry.get('description', '')
+            perex = BeautifulSoup(entry.get('description', '')).text.strip()
             res.append(RssArticle(title, url, keywords, perex, '', self.source))
         return res
 

requirements.txt

@@ -1,3 +1,4 @@
+beautifulsoup4==4.6.0
 certifi==2017.4.17
 chardet==3.0.4
 feedparser==5.2.1