- 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)
- except LookupError:
- if log: log(" unknown charset: '%s'" % parser.charset)
- else:
- if log: log(" title : %s" % title)
-
- if title:
- 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)
- parser.title = final_title
-
- icon = parser.icon
- if isinstance(icon, unicode):
- try:
- parser.icon = icon.encode('ascii')
- except UnicodeEncodeError:
- if parser.charset:
- parser.icon = icon.encode(parser.charset)
- return parser
+ pass
+ else:
+ if parser:
+ if BKMK_DEBUG_HTML_PARSERS:
+ if log: log(" Parser %s: ok" % p.__module__)
+ _parsers.append((p, parser))
+ break
+ else:
+ if log: log(" Parser %s: fail" % p.__module__)
+ if not BKMK_DEBUG_HTML_PARSERS and parser:
+ break
+
+ if BKMK_DEBUG_HTML_PARSERS:
+ if not _parsers:
+ if log: log(" All parsers have failed")
+ return None
+ elif not parser:
+ if log: log(" All parsers have failed")
+ return None
+
+ if BKMK_DEBUG_HTML_PARSERS:
+ p, parser = _parsers[0]
+ if log: log(" Using %s" % p.__module__)
+
+ #title = parser.title
+ #if isinstance(title, unicode):
+ # if parser.charset:
+ # parser.title = title.encode(parser.charset)
+ # else:
+ # try:
+ # parser.title = title.encode('ascii')
+ # except UnicodeEncodeError:
+ # try:
+ # parser.title = title.encode(DEFAULT_CHARSET)
+ # except UnicodeEncodeError:
+ # parser.title = title.encode(universal_charset)
+ # parser.charset = universal_charset
+ # else:
+ # parser.charset = DEFAULT_CHARSET
+ # else:
+ # parser.charset = 'ascii'
+
+ converted_title = title = parser.title
+ if title and isinstance(title, bytes) and (not parser.charset):
+ try:
+ title.decode("ascii")
+ except UnicodeDecodeError:
+ parser.charset = DEFAULT_CHARSET
+
+ if parser.charset:
+ parser.charset = parser.charset.lower().replace("windows-", "cp")
+
+ if title and parser.charset and (
+ (parser.charset != universal_charset) or
+ ((not charset) or (charset != parser.charset))):
+ try:
+ if parser.meta_charset:
+ 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(" title : %s" % title)
+ #if parser.charset != universal_charset:
+ # try:
+ # converted_title = title.decode(parser.charset).\
+ # encode(universal_charset)
+ # except UnicodeError:
+ # if log:
+ # log(" incorrect conversion from %s,"
+ # "converting from %s"
+ # % (parser.charset, DEFAULT_CHARSET))
+ # converted_title = \
+ # title.decode(DEFAULT_CHARSET, "replace").\
+ # encode(universal_charset, "replace")
+ # parser.charset = DEFAULT_CHARSET
+ #if log and (converted_title != title):
+ # log(" converted title: %s" % converted_title)
+ except LookupError:
+ if log: log(" unknown charset: '%s'" % parser.charset)
+ else:
+ if log: log(" title : %s" % title)
+
+ if title:
+ 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)
+ parser.title = final_title
+
+ #icon = parser.icon
+ #if isinstance(icon, unicode):
+ # try:
+ # parser.icon = icon.encode('ascii')
+ # except UnicodeEncodeError:
+ # if parser.charset:
+ # parser.icon = icon.encode(parser.charset)
+ return parser
+