[Marketplace Contribution] Common Scripts - Content Pack Update

Packs/CommonScripts/ReleaseNotes/1_11_90.md

@@ -0,0 +1,5 @@
+#### Scripts
+##### TextFromHTML
+
+- Added an optional argument ***html_tag*** to extract text from within this tag.
+- Updated the Docker image to: *demisto/python3:3.10.12.63474*.

Packs/CommonScripts/Scripts/TextFromHTML/TextFromHTML.py

@@ -1,22 +1,28 @@
 import demistomock as demisto  # noqa: F401
 from CommonServerPython import *  # noqa: F401
 
+
 import re
 
 
-def text_from_html(args):
-    html = args['html']
-    body = re.search(r'<body.*/body>', html, re.M + re.S + re.I + re.U)
-    if body and body.group(0):
-        data = re.sub(r'<.*?>', '', body.group(0))
+def get_plain_text(html_regex):
+    data = ''
+    if html_regex and html_regex.group(0):
+        data = re.sub(r'<.*?>', '', html_regex.group(0))
         entities = {'quot': '"', 'amp': '&', 'apos': "'", 'lt': '<', 'gt': '>', 'nbsp': ' ',
                     'copy': '(C)', 'reg': '(R)', 'tilde': '~', 'ldquo': '"', 'rdquo': '"', 'hellip': '...'}
         for e in entities:
-            data = data.replace('&' + e + ';', entities[e])
+            data = data.replace(f'&{e};', entities[e])
+    return data
+
+
+def text_from_html(args):
+    html = args['html']
+    html_tag = args.get('html_tag', 'body')
 
-        return data
-    else:
-        return 'Could not extract text'
+    body = re.search(fr'<{html_tag}.*/{html_tag}>', html, re.M + re.S + re.I + re.U)
+    data = get_plain_text(body)
+    return data if data != '' else 'Could not extract text'
 
 
 if __name__ in ["__builtin__", "builtins"]:

Packs/CommonScripts/Scripts/TextFromHTML/TextFromHTML.yml

@@ -14,9 +14,18 @@ args:
   required: true
   default: true
   description: The HTML to strip tags from
+- name: html_tag
+  required: false
+  default: true
+  defaultValue: body
+  description: Specify HTML tag to extract the text from within.
 scripttarget: 0
 runonce: false
 fromversion: 5.0.0
-dockerimage: demisto/python3:3.10.6.33415
+dockerimage: demisto/python3:3.10.12.63474
 tests:
 - TextFromHTML_test_playbook
+contentitemexportablefields:
+  contentitemfields:
+    fromServerVersion: ''
+runas: DBotWeakRole

Packs/CommonScripts/Scripts/TextFromHTML/TextFromHTML_test.py

@@ -69,7 +69,7 @@
         'html': html
     }
     res = TextFromHTML.text_from_html(args)
 
     assert res == '\nמשפט בעברית לבדיקה\n'
 
 
@@ -155,3 +155,26 @@
     res = TextFromHTML.text_from_html(args)
 
     assert res == '\n\nHTML Links\nHTML links are defined with the a tag:\n\nThis is a link\n\n'
+
+
+def test_extract_text_from_specific_tag():
+    """
+    Given
+    - html string:
+        <p>HTML links are defined with the a tag:</p>
+    When
+    - extracting text from the html
+    Then
+    - ensure we return "HTML links are defined with the a tag:"
+    """
+    import TextFromHTML
+
+    html = """<p>HTML links are defined with the a tag:</p>"""
+
+    args = {
+        'html': html,
+        'html_tag': 'p'
+    }
+    res = TextFromHTML.text_from_html(args)
+
+    assert res == 'HTML links are defined with the a tag:'

Packs/CommonScripts/pack_metadata.json

@@ -2,7 +2,7 @@
     "name": "Common Scripts",
     "description": "Frequently used scripts pack.",
     "support": "xsoar",
-    "currentVersion": "1.11.89",
+    "currentVersion": "1.11.90",
     "author": "Cortex XSOAR",
     "url": "https://www.paloaltonetworks.com/cortex",
     "email": "",