org.jsoup.helper.DataUtil Java Examples

/**
 * Creates an instance based on the HTML fragment read from the stream. The
 * fragment must have exactly one root element.
 * <p>
 * A best effort is done to parse broken HTML but no guarantees are given
 * for how invalid HTML is handled.
 * <p>
 * Any heading or trailing whitespace is removed while parsing but any
 * whitespace inside the root tag is preserved.
 *
 * @param stream
 *            the input stream which provides the HTML in UTF-8
 * @throws UncheckedIOException
 *             if reading the stream fails
 */
public Html(InputStream stream) {
    super(null);
    if (stream == null) {
        throw new IllegalArgumentException("HTML stream cannot be null");
    }
    try {
        /*
         * Cannot use any of the methods that accept a stream since they all
         * parse as a document rather than as a body fragment. The logic for
         * reading a stream into a String is the same that is used
         * internally by JSoup if you strip away all the logic to guess an
         * encoding in case one isn't defined.
         */
        setOuterHtml(UTF_8.decode(DataUtil.readToByteBuffer(stream, 0))
                .toString());
    } catch (IOException e) {
        throw new UncheckedIOException("Unable to read HTML from stream",
                e);
    }
}
 

/**
 * 将流读取为 jsoup Document
 *
 * @param inputStream InputStream
 * @return Document
 */
public static Document readDocument(InputStream inputStream) {
	try {
		return DataUtil.load(inputStream, StandardCharsets.UTF_8.name(), "");
	} catch (IOException e) {
		throw Exceptions.unchecked(e);
	}
}
 

/**
 Parse the contents of a file as HTML.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(File in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Parse the contents of a file as HTML. The location of the file is used as the base URI to qualify relative URLs.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 @see #parse(File, String, String)
 */
public static Document parse(File in, String charsetName) throws IOException {
    return DataUtil.load(in, charsetName, in.getAbsolutePath());
}
 

/**
 Read an input stream, and parse it to a Document.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Read an input stream, and parse it to a Document. You can provide an alternate parser, such as a simple XML
 (non-HTML) parser.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @param parser alternate {@link Parser#xmlParser() parser} to use.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri, Parser parser) throws IOException {
    return DataUtil.load(in, charsetName, baseUri, parser);
}
 

/**
 Parse the contents of a file as HTML.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(File in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Parse the contents of a file as HTML. The location of the file is used as the base URI to qualify relative URLs.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 @see #parse(File, String, String)
 */
public static Document parse(File in, String charsetName) throws IOException {
    return DataUtil.load(in, charsetName, in.getAbsolutePath());
}
 

/**
 Read an input stream, and parse it to a Document.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Read an input stream, and parse it to a Document. You can provide an alternate parser, such as a simple XML
 (non-HTML) parser.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @param parser alternate {@link Parser#xmlParser() parser} to use.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri, Parser parser) throws IOException {
    return DataUtil.load(in, charsetName, baseUri, parser);
}
 

/**
 Parse the contents of a file as HTML.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(File in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Parse the contents of a file as HTML. The location of the file is used as the base URI to qualify relative URLs.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 @see #parse(File, String, String)
 */
public static Document parse(File in, String charsetName) throws IOException {
    return DataUtil.load(in, charsetName, in.getAbsolutePath());
}
 

/**
 Read an input stream, and parse it to a Document.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Read an input stream, and parse it to a Document. You can provide an alternate parser, such as a simple XML
 (non-HTML) parser.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @param parser alternate {@link Parser#xmlParser() parser} to use.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri, Parser parser) throws IOException {
    return DataUtil.load(in, charsetName, baseUri, parser);
}
 

/**
 Parse the contents of a file as HTML.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(File in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Parse the contents of a file as HTML. The location of the file is used as the base URI to qualify relative URLs.

 @param in          file to load HTML from
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 @see #parse(File, String, String)
 */
public static Document parse(File in, String charsetName) throws IOException {
    return DataUtil.load(in, charsetName, in.getAbsolutePath());
}
 

/**
 Read an input stream, and parse it to a Document.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri) throws IOException {
    return DataUtil.load(in, charsetName, baseUri);
}
 

/**
 Read an input stream, and parse it to a Document. You can provide an alternate parser, such as a simple XML
 (non-HTML) parser.

 @param in          input stream to read. Make sure to close it after parsing.
 @param charsetName (optional) character set of file contents. Set to {@code null} to determine from {@code http-equiv} meta tag, if
 present, or fall back to {@code UTF-8} (which is often safe to do).
 @param baseUri     The URL where the HTML was retrieved from, to resolve relative links against.
 @param parser alternate {@link Parser#xmlParser() parser} to use.
 @return sane HTML

 @throws IOException if the file could not be found, or read, or if the charsetName is invalid.
 */
public static Document parse(InputStream in, String charsetName, String baseUri, Parser parser) throws IOException {
    return DataUtil.load(in, charsetName, baseUri, parser);
}