X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_beautifulsoup.py;h=f2f042e33b18aae1303f5fdbfa5f365f7aeeca78;hb=cb9c36b39ed72cd1fa272130d2bcf162a89c3013;hp=e1969f3250aa73d6e46e24883dd264f6df7ccd94;hpb=b9c8d112b8d8d0f7c726ee7dd07a89b6569c90a1;p=bookmarks_db.git

diff --git a/parse_html/bkmk_ph_beautifulsoup.py b/parse_html/bkmk_ph_beautifulsoup.py
index e1969f3..f2f042e 100644
--- a/parse_html/bkmk_ph_beautifulsoup.py
+++ b/parse_html/bkmk_ph_beautifulsoup.py
@@ -65,7 +65,8 @@ def parse_html(html_text, charset=None, log=None):
         return None
 
     _charset = root.originalEncoding
-    if _charset in ("ISO-8859-2", "windows-1252", "MacCyrillic"):  # Replace default
+    if _charset in ("ISO-8859-2", "windows-1252", "MacCyrillic"):
+        # Replace with default and re-parse
         _charset = DEFAULT_CHARSET
         root = _parse_html(html_text, _charset)
         if root is None:
@@ -104,7 +105,8 @@ def parse_html(html_text, charset=None, log=None):
         try:
             meta_content = meta.get("content")
             if meta_content:
-                __charset = meta_content.lower().split('charset=')[1].split(';')[0]
+                __charset = meta_content.lower().split('charset=')[1].\
+                    split(';')[0]
             else:
                 __charset = False
         except IndexError:  # No charset in the META Content-Type