(Unicode C) Avoid URLs Matching Any of a Set of Patterns

Demonstrates how to use "avoid patterns" to prevent spidering any URL that matches a wildcarded pattern. This example avoids URLs containing the substrings "java", "python", or "perl".

Chilkat C/C++ Library Downloads
MS Visual C/C++ C++ Builder Linux C/C++ Alpine Linux C/C++	MacOS C/C++ iOS C/C++ Android C/C++ MinGW C/C++

#include <C_CkSpiderW.h>

void ChilkatSample(void)
    {
    HCkSpiderW spider;
    int i;
    BOOL success;

    spider = CkSpiderW_Create();

    // The spider object crawls a single web site at a time.  As you'll see
    // in later examples, you can collect outbound links and use them to 
    // crawl the web.  For now, we'll simply spider 10 pages of chilkatsoft.com
    CkSpiderW_Initialize(spider,L"www.chilkatsoft.com");

    // Add the 1st URL:
    CkSpiderW_AddUnspidered(spider,L"http://www.chilkatsoft.com/");

    // Avoid URLs matching these patterns:
    CkSpiderW_AddAvoidPattern(spider,L"*java*");
    CkSpiderW_AddAvoidPattern(spider,L"*python*");
    CkSpiderW_AddAvoidPattern(spider,L"*perl*");

    // Begin crawling the site by calling CrawlNext repeatedly.

    for (i = 0; i <= 9; i++) {

        success = CkSpiderW_CrawlNext(spider);
        if (success == TRUE) {
            // Show the URL of the page just spidered.
            wprintf(L"%s\n",CkSpiderW_lastUrl(spider));
            // The HTML is available in the LastHtml property
        }
        else {
            // Did we get an error or are there no more URLs to crawl?
            if (CkSpiderW_getNumUnspidered(spider) == 0) {
                wprintf(L"No more URLs to spider\n");
            }
            else {
                wprintf(L"%s\n",CkSpiderW_lastErrorText(spider));
            }

        }

        // Sleep 1 second before spidering the next URL.
        CkSpiderW_SleepMs(spider,1000);
    }



    CkSpiderW_Dispose(spider);

    }