parsehtml.py 文件源码

def findHTMLMeta(stream):
    """Look for a meta http-equiv tag with the YADIS header name.

    @param stream: Source of the html text
    @type stream: Object that implements a read() method that works
        like file.read

    @return: The URI from which to fetch the XRDS document
    @rtype: str

    @raises MetaNotFound: raised with the content that was
        searched as the first parameter.
    """
    parser = YadisHTMLParser()
    chunks = []

    while 1:
        chunk = stream.read(CHUNK_SIZE)
        if not chunk:
            # End of file
            break

        chunks.append(chunk)
        try:
            parser.feed(chunk)
        except HTMLParseError, why:
            # HTML parse error, so bail
            chunks.append(stream.read())
            break
        except ParseDone, why:
            uri = why[0]
            if uri is None:
                # Parse finished, but we may need the rest of the file
                chunks.append(stream.read())
                break
            else:
                return uri

    content = ''.join(chunks)
    raise MetaNotFound(content)