node. JS (iv) "HTTP crawler"

HTTP Source code Interpretation

HTTP Performance Test

1 varHTTP = require (' http ');2 3 http4. Createserver (function(Request, response) {5Response.writehead, {' Content-type ': ' Text/plain '});6Response.Write (' Hello Nodejs ');7 Response.End ();8     })9. Listen (2016);Ten  OneConsole.log (' Success '); A  - //Access localhost:2016 will see the return of Hello Nodejs

HTTP small Reptile

Installing Cheerio
NPM Install Cheerio

/**********************************/

1 varHTTP = require (' http ');2 varurl = ' http://www.imooc.com/learn/348 ';3 4Http.get (URL,function(response) {5     varhtml = ' ';6 7Response.on (' Data ',function(data) {8HTML + =data;9     });Ten  OneResponse.on (' End ',function () { A Console.log (HTML); -     }); -}). On (' Error ',function () { theConsole.log (' Error getting course data ')); -});

/**********************************/

1 /**2 * Nodejs crawler instances, crawl Imooc*/3 4 varHTTP = require (' http ');5 //install Cheerio, and bring in6 varCheerio = require (' Cheerio '));7 varurl = ' http://www.imooc.com/learn/348 ';8 9 functionFilterchapter (HTML) {Ten     var$ =cheerio.load (HTML); One     varChapters = $ ('. Chapter ')); A  -     //[{ -     //chaptertitle: ", the     //Videos: [ -     //title: ", -     //ID: " -     //    ] +     //}] -  +     varCoursedata = []; A  atChapters.each (function(item) { -         varChapter = $ ( This); -         varChaptertitle = Chapter.find (' strong ')). text (); -         varVideos = Chapter.find ('. Video '). Children (' Li ')); -  -         varChapterdata = { in Chaptertitle:chaptertitle, - videos: [] to         }; +  -Videos.each (function(item) { the             varVideo = $ ( This). Find (' a '); *             varVideotitle =Video.text (); $             varid = video.attr (' href '));Panax Notoginseng  - ChapterData.videos.push ({ the Videotitle:videotitle, + Id:id A             }); the         }); +         //Console.log (chapterdata); -  $ Coursedata.push (chapterdata); $     }); -     //Console.log (coursedata); -     //Console.log (Coursedata.videos); the  -     /*Coursedata.foreach (function (item) {Wuyi //console.log (Item.videos); the var videotitle = item.videos[0].videotitle; - var id = item.videos[0].id; Wu console.log (' [' + ID + '] ' + videotitle); -     });*/ About  $     returnCoursedata; - } -  - functionPrintcourseinfo (coursedata) { A     //Coursedata is an array +Coursedata.foreach (function(item) { the         varChaptertitle =Item.chaptertitle; -Console.log (chaptertitle + ' \ n ')); $     }); the  theCoursedata.foreach (function(item) { the         varVideotitle = Item.videos[0].videotitle; the         varid = item.videos[0].id; -Console.log (' [' + ID + '] ' +videotitle); in     }); the     //console.log (' test '); the     //Console.log (Coursedata.videos); About } the  theHttp.get (URL,function(response) { the     varhtml = ' '; +  -Response.on (' Data ',function(data) { theHTML + =data;Bayi     }); the  theResponse.on (' End ',function () { -         varCoursedata =filterchapter (HTML); -  the Printcourseinfo (coursedata); the         //Console.log (coursedata); the     }); the}). On (' Error ',function () { -Console.log (' Error getting course data ')); the});

node. JS (iv) "HTTP crawler"