Package org.apache.nutch.net.protocols

Examples of org.apache.nutch.net.protocols.Response

128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
  public ProtocolOutput getProtocolOutput(String url, WebPage page) {

    try {
      URL u = new URL(url);
      Response response = getResponse(u, page, false); // make a request
      int code = response.getCode();
      byte[] content = response.getContent();
      Content c = new Content(u.toString(), u.toString(),
          (content == null ? EMPTY_CONTENT : content),
          response.getHeader("Content-Type"),
          response.getHeaders(), mimeTypes);

      if (code == 200) { // got a good response
        return new ProtocolOutput(c); // return it
      } else if (code == 410) { // page is gone
        return new ProtocolOutput(c,
            ProtocolStatusUtils.makeStatus(ProtocolStatusCodes.GONE, "Http: " + code + " url=" + url));
      } else if (code >= 300 && code < 400) { // handle redirect
        String location = response.getHeader("Location");
        // some broken servers, such as MS IIS, use lowercase header name...
        if (location == null) location = response.getHeader("location");
        if (location == null) location = "";
        u = new URL(u, location);
        int protocolStatusCode;
        switch (code) {
        case 300:   // multiple choices, preferred value in Location
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
   
    if (robotRules == null) {                     // cache miss
      URL redir = null;
      if (LOG.isTraceEnabled()) { LOG.trace("cache miss " + url); }
      try {
        Response response = ((HttpBase)http).getResponse(new URL(url, "/robots.txt"),
                                             new WebPage(), true);
        // try one level of redirection ?
        if (response.getCode() == 301 || response.getCode() == 302) {
          String redirection = response.getHeader("Location");
          if (redirection == null) {
            // some versions of MS IIS are known to mangle this header
            redirection = response.getHeader("location");
          }
          if (redirection != null) {
            if (!redirection.startsWith("http")) {
              // RFC says it should be absolute, but apparently it isn't
              redir = new URL(url, redirection);
            } else {
              redir = new URL(redirection);
            }
           
            response = ((HttpBase)http).getResponse(redir, new WebPage(), true);
          }
        }

        if (response.getCode() == 200)               // found rules: parse them
          robotRules =  parseRules(url.toString(), response.getContent(),
                                   response.getHeader("Content-Type"),
                                   agentNames);

        else if ( (response.getCode() == 403) && (!allowForbidden) )
          robotRules = FORBID_ALL_RULES;            // use forbid all
        else if (response.getCode() >= 500) {
          cacheRule = false;
          robotRules = EMPTY_RULES;
        }else                                       
          robotRules = EMPTY_RULES;                 // use default rules
      } catch (Throwable t) {
View Full Code Here
207
208
209
210
211
212
213
214
215
216
217
   * @throws Exception
   *             When an error occurs or test case fails.
   */
  private void fetchPage(String page, int expectedCode) throws Exception {
    URL url = new URL("http", "127.0.0.1", port, page);
    Response response = null;
    response = http.getResponse(url, new WebPage(), true);

    int code = response.getCode();
    assertEquals("HTTP Status Code for " + url, expectedCode, code);
  }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
   *          HTTP response status code expected while fetching the page.
   */
  private void fetchPage(String page, int expectedCode) throws Exception {
    URL url = new URL("http", "127.0.0.1", port, page);
    CrawlDatum crawlDatum = new CrawlDatum();
    Response response = http.getResponse(url, crawlDatum, true);
    ProtocolOutput out = http.getProtocolOutput(new Text(url.toString()),
        crawlDatum);
    Content content = out.getContent();
    assertEquals("HTTP Status Code for " + url, expectedCode,
        response.getCode());

    if (page.compareTo("/nonexists.html") != 0
        && page.compareTo("/brokenpage.jsp") != 0
        && page.compareTo("/redirection") != 0) {
      assertEquals("ContentType " + url, "application/xhtml+xml",
View Full Code Here
TOP

Related Classes of org.apache.nutch.net.protocols.Response

  • org.apache.nutch.protocol.http.api.HttpBase
  • org.apache.nutch.protocol.http.api.HttpRobotRulesParser
  • org.apache.nutch.protocol.http.api.RobotRulesParser
  • org.apache.nutch.protocol.http.TestProtocolHttp
  • org.apache.nutch.protocol.httpclient.TestProtocolHttpClient
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.