From: Oleg Broytman <phd@phdru.name>
Date: Fri, 17 Nov 2023 23:54:46 +0000 (+0300)
Subject: Fix(parse_html): Do not parse empty strings
X-Git-Tag: 5.0.0~20
X-Git-Url: https://git.phdru.name/?a=commitdiff_plain;h=3dcc828780e34c685703def5278607cfd283fb72;p=bookmarks_db.git

Fix(parse_html): Do not parse empty strings
---

diff --git a/parse_html/bkmk_ph_beautifulsoup.py b/parse_html/bkmk_ph_beautifulsoup.py
index ac880cc..0aad3dd 100644
--- a/parse_html/bkmk_ph_beautifulsoup.py
+++ b/parse_html/bkmk_ph_beautifulsoup.py
@@ -62,6 +62,8 @@ def _parse_html(html_text, charset):
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     root = _parse_html(html_text, charset)
     if root is None:
         return None
diff --git a/parse_html/bkmk_ph_beautifulsoup4.py b/parse_html/bkmk_ph_beautifulsoup4.py
index 6549683..faafca2 100644
--- a/parse_html/bkmk_ph_beautifulsoup4.py
+++ b/parse_html/bkmk_ph_beautifulsoup4.py
@@ -39,6 +39,8 @@ def _parse_html(html_text, charset):
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     root = _parse_html(html_text, charset)
     if root is None:
         return None
diff --git a/parse_html/bkmk_ph_etreetidy.py b/parse_html/bkmk_ph_etreetidy.py
index 95f2071..eadcca3 100644
--- a/parse_html/bkmk_ph_etreetidy.py
+++ b/parse_html/bkmk_ph_etreetidy.py
@@ -16,6 +16,8 @@ from .bkmk_ph_util import HTMLParser
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     try:
         html_tree = TidyHTMLTreeBuilder.parseString(html_text)
     except:
diff --git a/parse_html/bkmk_ph_html5.py b/parse_html/bkmk_ph_html5.py
index 1fabd82..d973b72 100644
--- a/parse_html/bkmk_ph_html5.py
+++ b/parse_html/bkmk_ph_html5.py
@@ -16,6 +16,8 @@ from .bkmk_ph_util import HTMLParser
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     parser = HTML5Parser()
     if isinstance(html_text, bytes):
         html_tree = parser.parse(
diff --git a/parse_html/bkmk_ph_htmlparser.py b/parse_html/bkmk_ph_htmlparser.py
index fd7b687..c0f89b4 100644
--- a/parse_html/bkmk_ph_htmlparser.py
+++ b/parse_html/bkmk_ph_htmlparser.py
@@ -89,6 +89,8 @@ class HTMLParser(_HTMLParser):
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     parser = HTMLParser(charset)
 
     try: