(Chilkat2-Python) A Simple Web Crawler

This demonstrates a very simple web crawler using the Chilkat Spider component.

Chilkat2 Python Downloads install with pip pip3 install chilkat2 or download... Python Module for Windows, Linux, Alpine Linux, MacOS, Solaris

import chilkat2

spider = chilkat2.Spider()

seenDomains = chilkat2.StringArray()
seedUrls = chilkat2.StringArray()

seenDomains.Unique = True
seedUrls.Unique = True

# You will need to change the start URL to something else...
seedUrls.Append("http://something.whateverYouWant.com/")

# Set outbound URL exclude patterns
# URLs matching any of these patterns will not be added to the 
# collection of outbound links.
spider.AddAvoidOutboundLinkPattern("*?id=*")
spider.AddAvoidOutboundLinkPattern("*.mypages.*")
spider.AddAvoidOutboundLinkPattern("*.personal.*")
spider.AddAvoidOutboundLinkPattern("*.comcast.*")
spider.AddAvoidOutboundLinkPattern("*.aol.*")
spider.AddAvoidOutboundLinkPattern("*~*")

# Use a cache so we don't have to re-fetch URLs previously fetched.
spider.CacheDir = "c:/spiderCache/"
spider.FetchFromCache = True
spider.UpdateCache = True

while seedUrls.Count > 0 :

    url = seedUrls.Pop()
    spider.Initialize(url)

    # Spider 5 URLs of this domain.
    # but first, save the base domain in seenDomains
    domain = spider.GetUrlDomain(url)
    seenDomains.Append(spider.GetBaseDomain(domain))

    for i in range(0,5):
        success = spider.CrawlNext()
        if (success == True):

            # Display the URL we just crawled.
            print(spider.LastUrl)

            # If the last URL was retrieved from cache,
            # we won't wait.  Otherwise we'll wait 1 second
            # before fetching the next URL.
            if (spider.LastFromCache != True):
                spider.SleepMs(1000)

        else:
            # cause the loop to exit..
            i = 999

    # Add the outbound links to seedUrls, except
    # for the domains we've already seen.
    for i in range(0,spider.NumOutboundLinks):

        url = spider.GetOutboundLink(i)
        domain = spider.GetUrlDomain(url)
        baseDomain = spider.GetBaseDomain(domain)
        if (seenDomains.Contains(baseDomain) == False):
            # Don't let our list of seedUrls grow too large.
            if (seedUrls.Count < 1000):
                seedUrls.Append(url)