Created
April 10, 2015 05:33
-
-
Save kingwrcy/c0c2f07ec70d284af121 to your computer and use it in GitHub Desktop.
my wife need some imgs on http://www.tjftbc.com , so i have made this script,backup here.
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 cheerio = require('cheerio'); | |
var request = require('request'); | |
var fs = require('fs'); | |
var baseurl = 'http://www.tjftbc.com/product/'; | |
var $,category = []; | |
request(baseurl,function(error,response,body){ | |
if (!error && response.statusCode == 200) { | |
$ = cheerio.load(body); | |
var cates = $('.productclass_dolphin>a'); | |
for (var i = 1; i < cates.length; i++) { | |
// if(i>0)break; | |
create_category({ | |
name:cates.eq(i).text(), | |
url:baseurl+cates.eq(i).attr('href').substring(11) | |
}); | |
}; | |
} | |
}); | |
function start(cate){ | |
request(cate.url,function(error,response,body){ | |
var p = cheerio.load(body); | |
var pagenow = p('li.pagesnow'); | |
save_img(p('#Gallery img'),cate.name); | |
while(!pagenow.next().is('.pbutton')){ | |
start({ | |
name:cate.name, | |
url:baseurl + pagenow.next().find('a').attr('href').substring(9) | |
}); | |
pagenow = pagenow.next(); | |
} | |
}) | |
} | |
function save_img(imgs,name){ | |
for (var i = 0; i < imgs.length; i++) { | |
var imgurl = baseurl + imgs.eq(i).attr('src').substring(14); | |
var imgname = imgs.eq(i).attr('src').split("/")[5]; | |
request(imgurl).pipe(fs.createWriteStream('/tmp/xia/'+name+'/'+imgname)) | |
} | |
} | |
function create_category(cate){ | |
fs.mkdir('/tmp/xia/'+cate.name,function(){ | |
start(cate); | |
}) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment