From 937302fb5d8e1e6704ab954d673faf463dd40731 Mon Sep 17 00:00:00 2001
From: jsclose <jsclose@umich.edu>
Date: Wed, 21 Feb 2018 20:04:16 -0500
Subject: [PATCH] working on converting urls to ParsedUrl instances, trying to
fill buffer
---
crawler/SocketReader.h | 2 +-
crawler/spider.cpp | 25 ++--
crawler/spider.h | 8 +-
crawlerOutput/en.wikipedia.org.txt | 31 +++++
crawlerOutput/www.nytimes.com.txt | 214 +++++++++++++++++++++++++++++
docMap.txt | Bin 3423 -> 3941 bytes
shared/documentMap.h | 2 +-
shared/url.h | 1 +
8 files changed, 264 insertions(+), 19 deletions(-)
create mode 100755 crawlerOutput/en.wikipedia.org.txt
create mode 100755 crawlerOutput/www.nytimes.com.txt
diff --git a/crawler/SocketReader.h b/crawler/SocketReader.h
index 1a1bfdf..9c36a0e 100644
--- a/crawler/SocketReader.h
+++ b/crawler/SocketReader.h
@@ -11,7 +11,7 @@
class SocketReader : public StreamReader
{
public:
- SocketReader( string url_in ) : url( ParsedUrl( url_in ) ) { }
+ SocketReader( ParsedUrl url_in ) : url( url_in ) { }
virtual void fillBuffer();
void httpRequest();
void httpsRequest();
diff --git a/crawler/spider.cpp b/crawler/spider.cpp
index 0569993..3aee786 100644
--- a/crawler/spider.cpp
+++ b/crawler/spider.cpp
@@ -35,9 +35,9 @@ void Spider::FuncToRun()
{
- string currentUrl = getUrl( ); //get url from url frontier
+ string stringUrl = getUrl( ); //get url from url frontier
char *fileMap;
-
+ ParsedUrl currentUrl = ParsedUrl(stringUrl);
//url has not seen before or time since seen is past certain criteria
if ( shouldURLbeCrawled( currentUrl ))
{
@@ -47,9 +47,9 @@ void Spider::FuncToRun()
StreamReader *reader = request( currentUrl );
- string pathToDisk = util::GetCurrentWorkingDir() + "/crawlerOutput/" + string(url.Host, strlen(url.Host)) + ".txt";
+ string pathToDisk = util::GetCurrentWorkingDir() + "/crawlerOutput/" + currentUrl.Host + ".txt";
int fd = util::writeToNewFileToLocation( reader->buffer, pathToDisk);
-
+
//parser.parse(reader);
cond = true;
}
@@ -76,7 +76,7 @@ Takes a URL. Hashes it. Checks if the url is in the docMapLookup. If it is, chec
-bool Spider::writeDocToDisk(string url)
+bool Spider::writeDocToDisk(ParsedUrl url)
{
Document d(url);
int resultPosition = d.WriteToDocMap();
@@ -84,7 +84,7 @@ bool Spider::writeDocToDisk(string url)
return false;
}
- this->docMapLookup->insert( std::pair < string, int >( url, resultPosition ));
+ this->docMapLookup->insert( std::pair < string, int >( url.CompleteUrl, resultPosition ));
for ( auto it = this->docMapLookup->begin( ); it != this->docMapLookup->end( ); ++it )
std::cout << it->first << " => " << it->second << '\n';
@@ -93,10 +93,10 @@ bool Spider::writeDocToDisk(string url)
-bool Spider::shouldURLbeCrawled( string url )
+bool Spider::shouldURLbeCrawled( ParsedUrl url )
{
//search for url in doc cache
- auto locationOnDisk = this->docMapLookup->find( url );
+ auto locationOnDisk = this->docMapLookup->find( url.CompleteUrl );
//bool protectedByRobots = checkRobots( url );
//if it doesnt find anything for that url key
@@ -107,16 +107,15 @@ bool Spider::shouldURLbeCrawled( string url )
else
{
//Just for testing
- Document::PrintDocMap(url, locationOnDisk->second);
+ Document::PrintDocMap(url.CompleteUrl, locationOnDisk->second);
}
return false;
}
//check if path in url is in the robots txt
-bool Spider::checkRobots(string url_in)
+bool Spider::checkRobots(ParsedUrl url)
{
- ParsedUrl url = ParsedUrl(url_in);
string pathToRobots = util::GetCurrentWorkingDir() + "/robots/" + string(url.Host, strlen(url.Host)) + ".txt";
int robotsFileD = util::getFileDescriptor(pathToRobots , "R");
//File does not exist yet
@@ -163,14 +162,14 @@ returns true if fileMap was created, otherwise false
Modifies the filemap to be a char* of the file of the url passed
*/
-StreamReader* Spider::request( string url )
+StreamReader* Spider::request( ParsedUrl url )
{
string localFile;
StreamReader *newReader;
if ( this->mode == "local" )
{
- newReader = new LocalReader( url );
+ newReader = new LocalReader( url.CompleteUrl );
}
else if ( this->mode == "web" )
{
diff --git a/crawler/spider.h b/crawler/spider.h
index 4dbff98..c12e6e1 100644
--- a/crawler/spider.h
+++ b/crawler/spider.h
@@ -32,14 +32,14 @@ public:
//Makes request to given url
// if successful, writes file to disk, stores location to memeber value
// else return false and error information, retry if necessary
- StreamReader *request( string url );
+ StreamReader *request( ParsedUrl url );
- bool writeDocToDisk(string url);
+ bool writeDocToDisk(ParsedUrl url);
- bool shouldURLbeCrawled( string URL );
+ bool shouldURLbeCrawled( ParsedUrl URL );
int getRobots(ParsedUrl url );
- bool checkRobots(string url);
+ bool checkRobots(ParsedUrl url);
private:
diff --git a/crawlerOutput/en.wikipedia.org.txt b/crawlerOutput/en.wikipedia.org.txt
new file mode 100755
index 0000000..2bd2d09
--- /dev/null
+++ b/crawlerOutput/en.wikipedia.org.txt
@@ -0,0 +1,31 @@
+t":{"value":4,"limit":500},"entityaccesscount":{"value":0,"limit":400},"timingprofile":["100.00% 237.721 1 -total"," 40.32% 95.841 1 Template:Reflist"," 33.35% 79.290 1 Template:Infobox_film_awards"," 30.80% 73.221 8 Template:Cite_web"," 26.88% 63.910 1 Template:Infobox"," 11.62% 27.620 1 Template:EngvarB"," 6.65% 15.797 2 Template:DMCA"," 6.32% 15.026 1 Template:BAFTA_Film_Awards_Chron"," 6.04% 14.360 2 Template:Dated_maintenance_category"," 5.18% 12.316 1 Template:Navbox"]},"scribunto":{"limitreport-timeusage":{"value":"0.100","limit":"10.000"},"limitreport-memusage":{"value":3947757,"limit":52428800}},"cachereport":{"origin":"mw1312","timestamp":"20180221214801","ttl":1900800,"transientcontent":false}}});});</script><script>(window.RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgBackendResponseTime":96,"wgHostname":"mw1330"});});</script>
+ </body>
+</html>
+/div>
+ </div>
+ </div>
+ </div>
+ <div id="footer" role="contentinfo">
+ <ul id="footer-info">
+ <li id="footer-info-lastmod"> This page was last edited on 21 February 2018, at 21:48.</li>
+ <li id="footer-info-copyright">Text is available under the <a rel="license" href="//en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License">Creative Commons Attribution-ShareAlike License</a><a rel="license" href="//creativecommons.org/licenses/by-sa/3.0/" style="display:none;"></a>;
+additional terms may apply. By using this site, you agree to the <a href="//wikimediafoundation.org/wiki/Terms_of_Use">Terms of Use</a> and <a href="//wikimediafoundation.org/wiki/Privacy_policy">Privacy Policy</a>. Wikipedia® is a registered trademark of the <a href="//www.wikimediafoundation.org/">Wikimedia Foundation, Inc.</a>, a non-profit organization.</li>
+ </ul>
+ <ul id="footer-places">
+ <li id="footer-places-privacy"><a href="https://wikimediafoundation.org/wiki/Privacy_policy" class="extiw" title="wmf:Privacy policy">Privacy policy</a></li>
+ <li id="footer-places-about"><a href="/wiki/Wikipedia:About" title="Wikipedia:About">About Wikipedia</a></li>
+ <li id="footer-places-disclaimer"><a href="/wiki/Wikipedia:General_disclaimer" title="Wikipedia:General disclaimer">Disclaimers</a></li>
+ <li id="footer-places-contact"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us">Contact Wikipedia</a></li>
+ <li id="footer-places-developers"><a href="https://www.mediawiki.org/wiki/Special:MyLanguage/How_to_contribute">Developers</a></li>
+ <li id="footer-places-cookiestatement"><a href="https://wikimediafoundation.org/wiki/Cookie_statement">Cookie statement</a></li>
+ <li id="footer-places-mobileview"><a href="//en.m.wikipedia.org/w/index.php?title=71st_British_Academy_Film_Awards&mobileaction=toggle_view_mobile" class="noprint stopMobileRedirectToggle">Mobile view</a></li>
+ </ul>
+ <ul id="footer-icons" class="noprint">
+ <li id="footer-copyrightico">
+ <a href="https://wikimediafoundation.org/"><img src="/static/images/wikimedia-button.png" srcset="/static/images/wikimedia-button-1.5x.png 1.5x, /static/images/wikimedia-button-2x.png 2x" width="88" height="31" alt="Wikimedia Foundation"/></a> </li>
+ <li id="footer-poweredbyico">
+ <a href="//www.mediawiki.org/"><img src="/static/images/poweredby_mediawiki_88x31.png" alt="Powered by MediaWiki" srcset="/static/images/poweredby_mediawiki_132x47.png 1.5x, /static/images/poweredby_mediawiki_176x62.png 2x" width="88" height="31"/></a> </li>
+ </ul>
+ <div style="clear: both;"></div>
+ </div>
+ <script>(window.RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgPageParseReport":{"limitreport":{"cputime":"0.264","walltime":"0.328","ppvisitednodes":{"value":1822,"limit":1000000},"ppgeneratednodes":{"value":0,"limit":1500000},"postexpandincludesize":{"value":44633,"limit":2097152},"templateargumentsize":{"value":2117,"limit":2097152},"expansiondepth":{"value":12,"limit":40},"expensivefunctioncoun
\ No newline at end of file
diff --git a/crawlerOutput/www.nytimes.com.txt b/crawlerOutput/www.nytimes.com.txt
new file mode 100755
index 0000000..f13bf72
--- /dev/null
+++ b/crawlerOutput/www.nytimes.com.txt
@@ -0,0 +1,214 @@
+
+ <li>
+ <a href="https://store.nytimes.com/?action=click&contentCollection=NYT%20Store&contentPlacement=2&module=SectionsNav&pgtype=Homepage®ion=TopBar&t=qry542&utm_campaign=NYT-HP&utm_content=hp_browsetree&utm_medium=HPB&utm_source=nytimes&version=BrowseTree">NYT Store</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/times-journeys/?utm_source=nytimes&utm_medium=HPLink&utm_content=hp_browsetree&utm_campaign=NYT-HP">Times Journeys</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/seeallnav">Subscribe</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/membercenter">Manage My Account</a>
+ </li>
+
+
+ <li>
+ <a href="http://www.nytco.com">NYTCo</a>
+ </li>
+
+
+ </ul>
+ </div><!-- close column -->
+
+
+ <div class="column last-column">
+
+<h3 class="menu-heading">Subscribe</h3>
+
+<ul class="menu primary-menu">
+ <li class="menu-label">Subscribe</li>
+ <li class="home-delivery">
+ <i class="icon sprite-icon"></i>
+ <a class="nyt-home-delivery" href="https://www.nytimes.com/hdleftnav">Home Delivery</a>
+ </li>
+ <li class="digital-subscriptions">
+ <i class="icon sprite-icon"></i>
+ <a class="digital-subscription" href="https://www.nytimes.com/digitalleftnav">Digital Subscriptions</a>
+ </li>
+ <li class="nyt-crossword last-item">
+ <i class="icon sprite-icon"></i>
+ <a id="nyt-crossword" href="https://www.nytimes.com/crosswords/index.html">Crossword</a>
+ </li>
+</ul>
+
+<ul class="menu secondary-menu">
+
+ <li class="email-newsletters">
+ <a href="https://www.nytimes.com/marketing/newsletters">Email Newsletters</a>
+ </li>
+ <li>
+ <a href="https://myaccount.nytimes.com/mem/tnt.html">Alerts</a>
+ </li>
+ <li class="gift-subscription">
+ <a href="https://www.nytimes.com/giftleftnav">Gift Subscriptions</a>
+ </li>
+ <li>
+ <a href="https://www.nytimes.com/corporateleftnav">Group Subscriptions</a>
+ </li>
+ <li>
+ <a href="https://www.nytimes.com/educationleftnav">Education Rate</a>
+ </li>
+
+</ul>
+<ul class="menu secondary-menu">
+ <li>
+ <a href="https://www.nytimes.com/services/mobile/index.html">Mobile Applications</a>
+ </li>
+ <li>
+ <a href="http://eedition.nytimes.com/cgi-bin/signup.cgi?cc=37FYY">Replica Edition</a>
+ </li>
+
+</ul>
+ </div><!-- close column -->
+
+ </div><!-- close split-6-layout -->
+
+ </nav><!-- close nav -->
+
+</section><!-- close site-index -->
+
+ <footer id="page-footer" class="page-footer" role="contentinfo">
+ <nav>
+ <h2 class="visually-hidden">Site Information Navigation</h2>
+ <ul>
+ <li>
+ <a href="https://www.nytimes.com/content/help/rights/copyright/copyright-notice.html" itemprop="copyrightNotice">
+ © <span itemprop="copyrightYear">2018</span><span itemprop="copyrightHolder provider sourceOrganization" itemscope itemtype="http://schema.org/Organization" itemid="http://www.nytimes.com"><span itemprop="name"> The New York Times Company</span><meta itemprop="tickerSymbol" content="NYSE NYT"/></span>
+ </a>
+ </li>
+ <li class="wide-viewport-item"><a href="https://www.nytimes.com/ref/membercenter/help/infoservdirectory.html">Contact Us</a></li>
+ <li class="wide-viewport-item"><a href="http://www.nytco.com/careers">Work With Us</a></li>
+ <li class="wide-viewport-item"><a href="http://nytmediakit.com/">Advertise</a></li>
+ <li class="wide-viewport-item"><a href="https://www.nytimes.com/content/help/rights/privacy/policy/privacy-policy.html#pp">Your Ad Choices</a></li>
+ <li><a href="https://www.nytimes.com/privacy">Privacy</a></li>
+ <li><a href="https://www.nytimes.com/ref/membercenter/help/agree.html" itemprop="usageTerms">Terms of Service</a></li>
+ <li class="wide-viewport-item last-item"><a href="https://www.nytimes.com/content/help/rights/sale/terms-of-sale.html">Terms of Sale</a></li>
+ </ul>
+ </nav>
+ <nav class="last-nav">
+ <h2 class="visually-hidden">Site Information Navigation</h2>
+ <ul>
+ <li><a href="http://spiderbites.nytimes.com">Site Map</a></li>
+ <li><a href="https://www.nytimes.com/membercenter/sitehelp.html">Help</a></li>
+ <li><a href="https://myaccount.nytimes.com/membercenter/feedback.html">Site Feedback</a></li>
+ <li class="wide-viewport-item last-item"><a href="https://www.nytimes.com/subscriptions/Multiproduct/lp5558.html?campaignId=37WXW">Subscriptions</a></li>
+ </ul>
+ </nav>
+
+ <div id="mobile-banner" class="mobile-banner hidden">
+ <a class="banner-message" href="https://mobile.nytimes.com/">View Mobile Version</a>
+ </div>
+
+ <div id="dfp-perf-test" class="ad hidden"></div>
+</footer>
+ </div><!-- close page -->
+ </div><!-- close shell -->
+ <script>
+require(['foundation/main'], function () {
+ require(['homepage/main']);
+
+
+
+
+ require(['jquery/nyt', 'foundation/views/page-manager'], function ($, pageManager) {
+ if (window.location.search.indexOf('disable_tagx') > 0) {
+ return;
+ }
+ $(document).ready(function () {
+ require(['https://a1.nyt.com/analytics/json-kidd.min.js'], function () {
+ pageManager.trackingFireEventQueue();
+ });
+ });
+ });
+});
+</script>
+<!--esi
+<esi:include src="/appconfig/https/show-modal.js" />
+-->
+<script>
+require(['foundation/main'], function() {
+ require(['shared/audio/instances/audio']);
+});
+</script>
+
+ <div id="Inv1" class="ad inv1-ad hidden"></div>
+<div id="Inv2" class="ad inv2-ad hidden"></div>
+<div id="Inv3" class="ad inv3-ad hidden"></div>
+<div id="ab1" class="ad ab1-ad hidden"></div>
+<div id="ab2" class="ad ab2-ad hidden"></div>
+<div id="ab3" class="ad ab3-ad hidden"></div>
+<div id="prop1" class="ad prop1-ad hidden"></div>
+<div id="prop2" class="ad prop2-ad hidden"></div>
+<div id="Anchor" class="ad anchor-ad hidden"></div>
+<div id="ADX_CLIENTSIDE" class="ad adx-clientside-ad hidden"></div>
+</body>
+</html>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/arts/design">Art & Design</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/books">Books</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/arts/dance">Dance</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/movies">Movies</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/arts/music">Music</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/events/">N.Y.C. Events Guide</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/arts/television">Television</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/section/theater">Theater</a>
+ </li>
+
+
+ <li>
+ <a href="https://www.nytimes.com/video/arts">Video: Arts</a>
+ </li>
+
+
+ </ul>
+ </div><!-- close column -->
+
+
\ No newline at end of file
diff --git a/docMap.txt b/docMap.txt
index 4806d35acdf8ff1ace8ffd6197e89ca69b84fe24..4edf9573b7533211a17b773b66f471eee4990903 100644
GIT binary patch
delta 35
hcmcaF^;B*{Jn!VSteul1d7LLVaN8r{kjej9Gy(p%4Qc=Y
delta 7
OcmaDVcVB8lJTCwaoC6sE
diff --git a/shared/documentMap.h b/shared/documentMap.h
index 720854e..9ae1058 100644
--- a/shared/documentMap.h
+++ b/shared/documentMap.h
@@ -31,7 +31,7 @@ class Document
//add more info fields here
public:
- Document(string url_in) : url(ParsedUrl(url_in)) {}
+ Document(ParsedUrl url_in) : url((url_in)) {}
string DocToString()
{
diff --git a/shared/url.h b/shared/url.h
index ed32a41..95c42e5 100644
--- a/shared/url.h
+++ b/shared/url.h
@@ -106,6 +106,7 @@ public:
~ParsedUrl( )
{
+ pathBuffer = 0;
delete [ ] pathBuffer;
}
--
GitLab