X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html.py;h=ec93ea5acb0903e9557bc370559a0a0ebee4dd6e;hb=3cb1b83ad134cc67669ff52cfed5662c80bbade4;hp=680ad5573a741bb99402449a77d969202e49abde;hpb=e7035a2a59f6a2cb55aa7ca852e2cff3b66b59d9;p=bookmarks_db.git diff --git a/Robots/parse_html.py b/Robots/parse_html.py index 680ad55..ec93ea5 100755 --- a/Robots/parse_html.py +++ b/Robots/parse_html.py @@ -32,7 +32,7 @@ num_entity_re = re.compile("(&#[0-9]+;)") def recode_entities(title, charset): output = [] for part in entity_re.split(title): - if part not in ("&", "<", ">", ""e;", " ") and \ + if part not in ("&", "<", ">", ""e;") and \ entity_re.match(part): part = unichr(name2codepoint.get(part[1:-1], part)).encode(charset) output.append(part) @@ -57,10 +57,13 @@ def parse_html(filename, charset=None, log=None): except (ValueError, LookupError): charset = None # ...try charset from HTML - for p in parsers: - charsets = [universal_charset, DEFAULT_CHARSET] + charsets = [universal_charset, DEFAULT_CHARSET] + if charset: + charset = charset.lower().replace("windows-", "cp") if charset not in charsets: charsets.insert(0, charset) + + for p in parsers: parser = None for c in charsets: try: @@ -81,13 +84,13 @@ def parse_html(filename, charset=None, log=None): parser.charset = DEFAULT_CHARSET if parser.charset: - parser.charset = parser.charset.replace("windows-", "cp").lower() + parser.charset = parser.charset.lower().replace("windows-", "cp") if parser.charset and (parser.charset <> universal_charset): try: if parser.meta_charset: if log: log(" META charset : %s" % parser.charset) - else: + 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)