自定义编码方式抓取页面

public static String getHtml(String link, String encode) throws IOException {

URL url = new URL(link);

HttpURLConnection conn = (HttpURLConnection) url.openConnection();

InputStream is = conn.getInputStream();

InputStreamReader isr = new InputStreamReader(is, encode);

BufferedReader br = new BufferedReader(isr);

String line = null;

StringBuffer html = new StringBuffer();

while ((line = br.readLine()) != null) {

html.append(line);

html.append("\n\r");

}

is.close();

isr.close();

br.close();

return html.toString();

}

抓取gzip编码格式的页面

public static String getHtmlByGzip(String link, String encode) throws IOException {

URL url = new URL(link);

HttpURLConnection conn = (HttpURLConnection) url.openConnection();

GZIPInputStream gis = new GZIPInputStream(conn.getInputStream());

byte[] data = new byte[1024];

int len = 0;

StringBuffer html = new StringBuffer();

while ((len = (gis.read(data))) != 0) {

html.append(new String(data, 0, len, encode));

}

return html.toString();

}