Created
February 20, 2013 12:46
-
-
Save billynyh/4995295 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var $ = require('jquery'); | |
var http = require('http'); | |
var Sync = require('sync'); | |
var URIjs = require('./URI.js'); // http://medialize.github.com/URI.js/ | |
var fs = require('fs'); | |
var DEBUG = false; | |
var INFO = true; | |
var Log = { }; | |
Log.d = function (str){ if (DEBUG){ console.log(str); } } | |
Log.i = function (str){ if (INFO){ console.log(str); } } | |
Log.e = function (str){ console.log(str); } | |
function get_page(url, callback){ | |
Log.d("get_page " + url); | |
var html = ""; | |
http.get(url, function(res){ | |
res.on('data', function(data) { | |
html += data; | |
}).on('end', function() { | |
callback(null, html); | |
}); | |
}); | |
} | |
function crawl_notice_home(){ | |
Log.d("crawl_notice_home"); | |
var url = "http://www.scout.org.hk/chi/notice/"; | |
var html = get_page.sync(null, url); | |
var menu = []; | |
$(html).find(".noticeshortcut a").each(function(){ | |
var a = $(this); | |
var uri = new URIjs(a.attr("href")); | |
menu.push({ | |
'title':a.text(), | |
'url':uri.absoluteTo(url).toString()+"/", | |
'label':a.attr("href") | |
}); | |
}); | |
// next | |
Scout.pages.push({ | |
"notices" : parse_page(html, url), | |
"label" : "_root", | |
"title" : "通告" | |
}); | |
Scout.menu = menu; | |
return; | |
for (var i=0, n=menu.length; i<n; i++){ | |
crawl_page(menu[i].label, menu[i].title, menu[i].url); | |
} | |
} | |
function crawl_page(label, title, url){ | |
Log.d("crawl_page " + url); | |
var html = get_page.sync(null, url); | |
Scout.pages.push({ | |
"notices" : parse_page(html, url), | |
"label" : label, | |
"title" : title | |
}); | |
} | |
function parse_page(html, base_url){ | |
Log.d("parse_page " + base_url); | |
var doc = $(html); | |
var page_items = []; | |
doc.find(".noticecontent tr").each(function(){ | |
var tr = $(this); | |
var a = tr.find("a"); | |
if (a.length > 0){ | |
// not header | |
var uri = new URIjs(a.attr("href")); | |
var tds = tr.find("td"); | |
var obj = { | |
'date' : $(tds[0]).text(), | |
'title' : $(tds[1]).text(), | |
'url' : uri.absoluteTo(base_url).toString() | |
}; | |
page_items.push(obj); | |
} | |
}); | |
return page_items; | |
} | |
function writeFileCallback(err){ | |
if (err) Log.e(err); | |
else Log.i("done"); | |
} | |
var Scout = {}; | |
Scout.pages = []; | |
Scout.menu = []; | |
Sync(function(){ | |
var encoding = "utf8"; | |
var fname = "./scout_hk.json"; | |
Log.i("start crawl"); | |
crawl_notice_home(); | |
Log.i("write file " + fname); | |
fs.writeFile(fname, JSON.stringify(Scout, null, 4), encoding, writeFileCallback); | |
/* | |
fname = "./scout_menu.json"; | |
Log.i("write file " + fname); | |
fs.writeFile(fname, unescape(encodeURIComponent(JSON.stringify(Scout.menu))), encoding, writeFileCallback); | |
*/ | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment