Examples with Source net.htmlparser.jericho.Source used on opensource projects

Example 11 with Source

use of net.htmlparser.jericho.Source in project zaproxy by zaproxy.

the class SpiderHtmlParserUnitTest method shouldFindUrlsInCommentsWithoutElements.

@Test
public void shouldFindUrlsInCommentsWithoutElements() {
    // Given
    SpiderHtmlParser htmlParser = new SpiderHtmlParser(new SpiderParam());
    TestSpiderParserListener listener = createTestSpiderParserListener();
    htmlParser.addSpiderParserListener(listener);
    HttpMessage messageHtmlResponse = createMessageWith("CommentWithoutElementsSpiderHtmlParser.html");
    Source source = createSource(messageHtmlResponse);
    // When
    boolean completelyParsed = htmlParser.parseResource(messageHtmlResponse, source, BASE_DEPTH);
    // Then
    assertThat(completelyParsed, is(equalTo(false)));
    assertThat(listener.getNumberOfUrlsFound(), is(equalTo(10)));
    assertThat(listener.getUrlsFound(), contains("http://plaincomment.example.com/", "http://plaincomment.example.com/z.php?x=y", "http://plaincomment.example.com/c.pl?x=y", "https://plaincomment.example.com/d.asp?x=y", "https://plaincomment.example.com/e/e1/e2.html?x=y", "https://plaincomment.example.com/surrounded/with/parenthesis", "https://plaincomment.example.com/surrounded/with/brackets", "https://plaincomment.example.com/surrounded/with/curly/brackets", "http://plaincomment.example.com/variant1", "http://plaincomment.example.com/variant2"));
}

Example 12 with Source

use of net.htmlparser.jericho.Source in project zaproxy by zaproxy.

the class SpiderHtmlParserUnitTest method shouldFindUrlsInCommentsWithElements.

@Test
public void shouldFindUrlsInCommentsWithElements() {
    // AKA shouldNotFindPlainUrlsInCommentsWithElements
    // Given
    SpiderHtmlParser htmlParser = new SpiderHtmlParser(new SpiderParam());
    TestSpiderParserListener listener = createTestSpiderParserListener();
    htmlParser.addSpiderParserListener(listener);
    HttpMessage messageHtmlResponse = createMessageWith("CommentWithElementsSpiderHtmlParser.html");
    Source source = createSource(messageHtmlResponse);
    // When
    boolean completelyParsed = htmlParser.parseResource(messageHtmlResponse, source, BASE_DEPTH);
    // Then
    assertThat(completelyParsed, is(equalTo(false)));
    assertThat(listener.getNumberOfUrlsFound(), is(equalTo(9)));
    assertThat(listener.getUrlsFound(), contains("http://a.example.com/", "http://area.example.com/", "http://frame.example.com/", "http://iframe.example.com/", "http://img.example.com/", "http://link.example.com/", "http://meta.example.com/refresh/", "http://meta.example.com/location/", "http://script.example.com/"));
}

Example 13 with Source

use of net.htmlparser.jericho.Source in project zaproxy by zaproxy.

the class SpiderHtmlParserUnitTest method shouldNotFindUrlsInCommentsWithElementsIfNotEnabledToParseComments.

@Test
public void shouldNotFindUrlsInCommentsWithElementsIfNotEnabledToParseComments() {
    // Given
    SpiderParam spiderOptions = createSpiderParamWithConfig();
    spiderOptions.setParseComments(false);
    SpiderHtmlParser htmlParser = new SpiderHtmlParser(spiderOptions);
    TestSpiderParserListener listener = createTestSpiderParserListener();
    htmlParser.addSpiderParserListener(listener);
    HttpMessage messageHtmlResponse = createMessageWith("CommentWithElementsSpiderHtmlParser.html");
    Source source = createSource(messageHtmlResponse);
    // When
    boolean completelyParsed = htmlParser.parseResource(messageHtmlResponse, source, BASE_DEPTH);
    // Then
    assertThat(completelyParsed, is(equalTo(false)));
    assertThat(listener.getNumberOfUrlsFound(), is(equalTo(0)));
    assertThat(listener.getUrlsFound(), is(empty()));
}

Example 14 with Source

use of net.htmlparser.jericho.Source in project zaproxy by zaproxy.

the class SpiderHtmlParserUnitTest method shouldFindUrlsInAreaElements.

@Test
public void shouldFindUrlsInAreaElements() throws Exception {
    // Given
    SpiderHtmlParser htmlParser = new SpiderHtmlParser(new SpiderParam());
    TestSpiderParserListener listener = createTestSpiderParserListener();
    htmlParser.addSpiderParserListener(listener);
    HttpMessage messageHtmlResponse = createMessageWith("AreaElementsSpiderHtmlParser.html");
    Source source = createSource(messageHtmlResponse);
    // When
    boolean completelyParsed = htmlParser.parseResource(messageHtmlResponse, source, BASE_DEPTH);
    // Then
    assertThat(completelyParsed, is(equalTo(false)));
    assertThat(listener.getNumberOfUrlsFound(), is(equalTo(7)));
    assertThat(listener.getUrlsFound(), contains("http://area.example.com/base/scheme", "http://area.example.com:8000/b", "https://area.example.com/c?a=b", "http://example.com/sample/area/relative", "http://example.com/sample/", "http://example.com/area/absolute", "ftp://area.example.com/"));
}

Example 15 with Source

use of net.htmlparser.jericho.Source in project zaproxy by zaproxy.

the class SpiderHtmlParserUnitTest method shouldFindUrlsInImgElements.

@Test
public void shouldFindUrlsInImgElements() {
    // Given
    SpiderHtmlParser htmlParser = new SpiderHtmlParser(new SpiderParam());
    TestSpiderParserListener listener = createTestSpiderParserListener();
    htmlParser.addSpiderParserListener(listener);
    HttpMessage messageHtmlResponse = createMessageWith("ImgElementsSpiderHtmlParser.html");
    Source source = createSource(messageHtmlResponse);
    // When
    boolean completelyParsed = htmlParser.parseResource(messageHtmlResponse, source, BASE_DEPTH);
    // Then
    assertThat(completelyParsed, is(equalTo(false)));
    assertThat(listener.getNumberOfUrlsFound(), is(equalTo(7)));
    assertThat(listener.getUrlsFound(), contains("http://img.example.com/base/scheme", "http://img.example.com:8000/b", "https://img.example.com/c?a=b", "http://example.com/sample/img/relative", "http://example.com/sample/", "http://example.com/img/absolute", "ftp://img.example.com/"));
}