X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_parse_html.py;h=07fe32e3e7e6a658ec82f0123acff746a7ac0b01;hb=9faa13f6f8199790cf01533e857c593520559649;hp=af9395b0d8d735689288a02071a0e1aee80814de;hpb=7fc9a9ac1bfa749aa30e3ae1d730ac4f266db950;p=bookmarks_db.git

diff --git a/parse_html/bkmk_parse_html.py b/parse_html/bkmk_parse_html.py
index af9395b..07fe32e 100644
--- a/parse_html/bkmk_parse_html.py
+++ b/parse_html/bkmk_parse_html.py
@@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot.
 """
 
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 1997-2017 PhiloSoft Design"
+__copyright__ = "Copyright (C) 1997-2023 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['parse_html', 'parse_filename', 'universal_charset']
@@ -14,7 +14,7 @@ __all__ = ['parse_html', 'parse_filename', 'universal_charset']
 import codecs
 
 universal_charset = "utf-8"
-DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
+DEFAULT_CHARSET = "cp1251"  # Stupid default for Russian Cyrillic
 
 parsers = []
 
@@ -56,12 +56,12 @@ else:
     parsers.append(bkmk_ph_htmlparser.parse_html)
 
 # ElementTidy often segfaults
-#try:
-#   from . import bkmk_ph_etreetidy
-#except ImportError:
-#   pass
-#else:
-#   parsers.append(bkmk_ph_etreetidy.parse_html)
+# try:
+#     from . import bkmk_ph_etreetidy
+# except ImportError:
+#     pass
+# else:
+#     parsers.append(bkmk_ph_etreetidy.parse_html)
 
 import re
 from htmlentitydefs import name2codepoint
@@ -69,6 +69,7 @@ from htmlentitydefs import name2codepoint
 entity_re = re.compile("(&\w+;)")
 num_entity_re = re.compile("(&#[0-9]+;)")
 
+
 def recode_entities(title, charset):
     output = []
     for part in entity_re.split(title):
@@ -86,7 +87,7 @@ def recode_entities(title, charset):
             try:
                 part = unichr(int(part[2:-1])).encode(charset)
             except UnicodeEncodeError:
-                pass # Leave the entity as is
+                pass  # Leave the entity as is
         output.append(part)
 
     return ''.join(output)
@@ -95,13 +96,14 @@ def recode_entities(title, charset):
 import os
 BKMK_DEBUG_HTML_PARSERS = os.environ.get("BKMK_DEBUG_HTML_PARSERS")
 
+
 def parse_html(html_text, charset=None, log=None):
     if not parsers:
         return None
 
     if charset:
         try:
-            codecs.lookup(charset) # In case of unknown charset...
+            codecs.lookup(charset)  # In case of unknown charset...
         except (ValueError, LookupError):
             charset = None         # ...try charset from HTML
 
@@ -180,7 +182,7 @@ def parse_html(html_text, charset=None, log=None):
                 if log: log("   META charset   : %s" % parser.charset)
             elif (not charset) or (charset != parser.charset):
                 if log: log("   guessed charset: %s" % parser.charset)
-            #if log: log("   current charset: %s" % universal_charset)
+            # if log: log("   current charset: %s" % universal_charset)
             if log: log("   title          : %s" % title)
             if parser.charset != universal_charset:
                 try:
@@ -211,6 +213,7 @@ def parse_html(html_text, charset=None, log=None):
                 parser.icon = icon.encode(parser.charset)
     return parser
 
+
 def parse_filename(filename, charset=None, log=None):
     fp = open(filename, 'r')
     try: