X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;ds=sidebyside;f=parse_html%2Fbkmk_parse_html.py;h=6afb7f9df735f6a487b6b7537fc23f2c3daa71c2;hb=cb9c36b39ed72cd1fa272130d2bcf162a89c3013;hp=7bdc5664470b2c2ae4499be6f7519689daae4ae6;hpb=4255ead7de9ed5069f94b90cb134a077387d43c1;p=bookmarks_db.git

diff --git a/parse_html/bkmk_parse_html.py b/parse_html/bkmk_parse_html.py
index 7bdc566..6afb7f9 100644
--- a/parse_html/bkmk_parse_html.py
+++ b/parse_html/bkmk_parse_html.py
@@ -12,11 +12,7 @@ __all__ = ['parse_html', 'parse_filename', 'universal_charset']
 
 
 import codecs
-
-universal_charset = "utf-8"
-DEFAULT_CHARSET = "cp1251"  # Stupid default for Russian Cyrillic
-
-parsers = []
+import os
 
 try:
     from . import bkmk_ph_beautifulsoup4
@@ -66,9 +62,15 @@ else:
 import re
 from htmlentitydefs import name2codepoint
 
+universal_charset = "utf-8"
+DEFAULT_CHARSET = "cp1251"  # Stupid default for Russian Cyrillic
+
+parsers = []
+
 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):
@@ -92,9 +94,9 @@ def recode_entities(title, charset):
     return ''.join(output)
 
 
-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
@@ -184,12 +186,19 @@ def parse_html(html_text, charset=None, log=None):
             if log: log("   title          : %s" % title)
             if parser.charset != universal_charset:
                 try:
-                    converted_title = unicode(title, parser.charset).encode(universal_charset)
+                    converted_title = unicode(title, parser.charset).\
+                        encode(universal_charset)
                 except UnicodeError:
-                    if log: log("   incorrect conversion from %s, converting from %s" % (parser.charset, DEFAULT_CHARSET))
-                    converted_title = unicode(title, DEFAULT_CHARSET, "replace").encode(universal_charset, "replace")
+                    if log:
+                        log("   incorrect conversion from %s,"
+                            "converting from %s"
+                            % (parser.charset, DEFAULT_CHARSET))
+                    converted_title = \
+                        unicode(title, DEFAULT_CHARSET, "replace").\
+                        encode(universal_charset, "replace")
                     parser.charset = DEFAULT_CHARSET
-            if log and (converted_title != title): log("   converted title: %s" % converted_title)
+            if log and (converted_title != title):
+                log("   converted title: %s" % converted_title)
         except LookupError:
             if log: log("   unknown charset: '%s'" % parser.charset)
     else:
@@ -199,7 +208,8 @@ def parse_html(html_text, charset=None, log=None):
         final_title = recode_entities(converted_title, universal_charset)
         parts = [s.strip() for s in final_title.replace('\r', '').split('\n')]
         final_title = ' '.join([s for s in parts if s])
-        if log and (final_title != converted_title): log("   final title    : %s" % final_title)
+        if log and (final_title != converted_title):
+            log("   final title    : %s" % final_title)
         parser.title = final_title
 
     icon = parser.icon
@@ -211,6 +221,7 @@ 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: