private String getUrlContent(CachedUrl url) throws IOException {
   InputStream content = url.getUnfilteredInputStream();
   ByteArrayOutputStream baos = new ByteArrayOutputStream();
   StreamUtil.copy(content, baos);
   content.close();
   String contentStr = new String(baos.toByteArray());
   baos.close();
   return contentStr;
 }
示例#2
0
  private void buildUrlSets(String url) {

    try {
      outputMessage("\nFetching " + url, TEST_SUMMARY_MESSAGE);
      URL srcUrl = new URL(url);
      //       URLConnection conn = srcUrl.openConnection();
      //       String type = conn.getContentType();
      //       type = conn.getHeaderField("content-type");
      //       InputStream istr = conn.getInputStream();

      LockssUrlConnection conn = UrlUtil.openConnection(url, connectionPool);
      if (proxyHost != null) {
        conn.setProxy(proxyHost, proxyPort);
      }
      if (userAgent != null) {
        conn.setRequestProperty("user-agent", userAgent);
      }
      try {
        conn.execute();
        int resp = conn.getResponseCode();
        if (resp != 200) {
          outputMessage("Resp: " + resp + ": " + conn.getResponseMessage(), TEST_SUMMARY_MESSAGE);
          return;
        }
        depth_fetched[m_curDepth - 1]++;
        String cookies = conn.getResponseHeaderValue("Set-Cookie");
        if (cookies != null) {
          outputMessage("Cookies: " + cookies, PLAIN_MESSAGE);
        }
        String type = conn.getResponseContentType();
        if (type == null || !type.toLowerCase().startsWith("text/html")) {
          outputMessage("Type: " + type + ", not parsing", URL_SUMMARY_MESSAGE);
          return;
        }
        outputMessage("Type: " + type + ", extracting Urls", URL_SUMMARY_MESSAGE);
        InputStream istr = conn.getResponseInputStream();
        InputStreamReader reader = new InputStreamReader(istr);
        //       MyMockCachedUrl mcu = new MyMockCachedUrl(srcUrl.toString(), reader);
        GoslingHtmlLinkExtractor extractor = new GoslingHtmlLinkExtractor();
        extractor.extractUrls(null, istr, null, srcUrl.toString(), new MyLinkExtractorCallback());
        istr.close();
        depth_parsed[m_curDepth - 1]++;
      } finally {
        conn.release();
      }
    } catch (MalformedURLException murle) {
      murle.printStackTrace();
      outputErrResults(url, "Malformed URL:" + murle.getMessage());
    } catch (IOException ex) {
      ex.printStackTrace();
      outputErrResults(url, "IOException: " + ex.getMessage());
    }
  }
  protected void checkFilter(SimulatedArchivalUnit sau) throws Exception {
    log.debug("checkFilter()");
    CachedUrl cu = sau.makeCachedUrl(sau.getUrlRoot() + "/001file.html");

    enableFilter(sau, true);
    InputStream is = cu.openForHashing();
    String expected = "001file.html This is file 1, depth 0, branch 0. foobar ";
    assertEquals(expected, StringUtil.fromInputStream(is));
    is.close();
    enableFilter(sau, false);
    cu = sau.makeCachedUrl(sau.getUrlRoot() + "/001file.html");
    is = cu.openForHashing();
    expected =
        "<HTML><HEAD><TITLE>001file.html</TITLE></HEAD><BODY>\n"
            + "This is file 1, depth 0, branch 0.<br><!-- comment -->    "
            + "Citation String   foobar<br><script>"
            + "(defun fact (n) (cond ((= n 0) 1) (t (fact (sub1 n)))))</script>\n"
            + "</BODY></HTML>";
    assertEquals(expected, StringUtil.fromInputStream(is));
    is.close();
  }