Created
April 24, 2014 02:30
-
-
Save gasolin/11239472 to your computer and use it in GitHub Desktop.
http://axe.g0v.tw/level/3 crawer result test in http://jsonlint.com/
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 request = require("request"); | |
var cheerio = require("cheerio"); | |
var jar = request.jar(); | |
var request = request.defaults({ | |
jar: jar, | |
followRedirect: true, | |
maxRedirects: 10 | |
}); | |
/** | |
* Utility function that downloads a URL and invokes | |
* callback with the data. | |
*/ | |
function download(url, callback) { | |
request.get(url, function(error, response, body) { | |
if (!error && response.statusCode == 200) { | |
callback(body); | |
} | |
}); | |
} | |
// DO THE JOB | |
var baseUrl = "http://axe-level-1.herokuapp.com"; | |
var levelUrl = "/lv3/"; | |
var urlNext = "?page=next"; | |
var resultJson = []; | |
var column_title = ["town", "village", "name"]; | |
var queue = []; | |
var TOTAL = 76; | |
request({url: baseUrl}, function () { | |
for (var i = TOTAL; i >= 0; i--) { | |
queue.push(i); | |
} | |
scheduler(); | |
}); | |
function scheduler() { | |
var count = queue.pop(); | |
if (count < TOTAL) { console.log(count); | |
if (count === 0) { | |
parse(baseUrl + levelUrl); | |
} else { | |
parse(baseUrl + levelUrl + urlNext); | |
} | |
} else { | |
console.log(JSON.stringify(resultJson)); | |
} | |
} | |
function parse(path) { | |
download(path, function(data) { | |
if (data) { | |
// console.log(data); | |
var $ = cheerio.load(data); | |
$("tr").each(function(i, e) { | |
if(i > 0) { | |
var columns = $(e).find("td"); | |
// column holder | |
var person = {}; | |
columns.each(function(j, e) { | |
person[column_title[j]] = $(e).text(); | |
}); | |
resultJson.push(person); | |
} | |
}); | |
} | |
scheduler(); | |
}); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment