Remove HTML tags from content.

Do this as early as processing the entry so later steps can count
on it (esp. when counting characters)

Also add a new requirement: beautifulsoup4.

feediverse.py

@@ -6,10 +6,12 @@ import argparse
 import yaml
 import dateutil
 import feedparser
+from bs4 import BeautifulSoup
 
 from mastodon import Mastodon
 from datetime import datetime, timezone
 
+
 DEFAULT_CONFIG_FILE = os.path.join("~", ".feediverse")
 
 def main():
@@ -74,10 +76,11 @@ def get_entry(entry):
     for tag in entry.get('tags', []):
         for t in tag['term'].split(' '):
             hashtags.append('#{}'.format(t))
+    summary = entry.get('summary', '')
     return {
         'url': entry.id,
-        'title': entry.title,
-        'summary': entry.get('summary', ''),
+        'title': BeautifulSoup(entry.title, 'html.parser').get_text(),
+        'summary': BeautifulSoup(summary, 'html.parser').get_text(),
         'hashtags': ' '.join(hashtags),
         'updated': dateutil.parser.parse(entry['updated']),
     }

setup.py

@@ -14,6 +14,10 @@ setup(
     description='Connect an RSS Feed to Mastodon',
     long_description=long_description,
     long_description_content_type="text/markdown",
-    install_requires=['feedparser', 'mastodon.py', 'python-dateutil', 'pyyaml'],
+    install_requires=['beautifulsoup4',
+                      'feedparser',
+                      'mastodon.py',
+                      'python-dateutil',
+                      'pyyaml'],
     entry_points={'console_scripts': ['feediverse = feediverse:main']}
 )