X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html.py;h=23f53e49cae938701e02a6b39db4538080ef5ffb;hb=a38eb2c9d04e866177c80cb961712ed3d4574f5e;hp=fd8dc927c0d78d7adcd8394457774450ff9dd403;hpb=83ac2470649ec5932119ee66dd1ce6829278977c;p=bookmarks_db.git

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index fd8dc92..23f53e4 100755
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -2,7 +2,7 @@
 """
    HTML Parsers wrapper
 
-   Written by Broytman. Copyright (C) 1997-2008 PhiloSoft Design
+   Written by Broytman. Copyright (C) 1997-2010 PhiloSoft Design
 """
 
 import codecs
@@ -11,6 +11,14 @@ universal_charset = "utf-8"
 DEFAULT_CHARSET = "cp1251" # Stupid default for Russian Cyrillic
 
 parsers = []
+
+try:
+   import parse_html_html5
+except ImportError:
+   pass
+else:
+   parsers.append(parse_html_html5.parse_html)
+
 try:
    import parse_html_beautifulsoup
    parse_html_beautifulsoup.DEFAULT_CHARSET = DEFAULT_CHARSET
@@ -19,8 +27,12 @@ except ImportError:
 else:
    parsers.append(parse_html_beautifulsoup.parse_html)
 
-from parse_html_htmlparser import parse_html
-parsers.append(parse_html)
+try:
+   from parse_html_htmlparser import parse_html
+except ImportError:
+   pass
+else:
+    parsers.append(parse_html)
 
 
 import re
@@ -35,11 +47,9 @@ def recode_entities(title, charset):
       if part not in ("&", "<", ">", """) and \
             entity_re.match(part):
          _part = name2codepoint.get(part[1:-1], None)
-         if _part is None:
-             _part = part
-         else:
-             _part = unichr(_part).encode(charset)
-      output.append(_part)
+         if _part is not None:
+             part = unichr(_part).encode(charset)
+      output.append(part)
    title = ''.join(output)
 
    output = []
@@ -55,6 +65,9 @@ def recode_entities(title, charset):
 
 
 def parse_html(filename, charset=None, log=None):
+   if not parsers:
+       return None
+
    if charset:
       try:
          codecs.lookup(charset) # In case of unknown charset...
@@ -64,8 +77,9 @@ def parse_html(filename, charset=None, log=None):
    charsets = [universal_charset, DEFAULT_CHARSET]
    if charset:
       charset = charset.lower().replace("windows-", "cp")
-      if charset not in charsets:
-         charsets.insert(0, charset)
+      if charset in charsets:
+         charsets.remove(charset)
+      charsets.insert(0, charset)
 
    for p in parsers:
       parser = None