Created
May 20, 2015 05:31
-
-
Save ishiduca/5c728078a32fb597698c to your computer and use it in GitHub Desktop.
trumpetでスクレイピングの試作。複雑な構造をパースするには骨が折れる
This file contains hidden or 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
| {"code":"aaa","product":"AAA","price":1000} | |
| {"code":"abc","product":"ABC","price":1100} | |
| {"code":"xyz","product":"XYZ","price":10000} |
This file contains hidden or 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 fs = require('fs') | |
| var trumpet = require('trumpet') | |
| var es = require('event-stream') | |
| var duplexer = require('duplexer') | |
| var merge = require('deepmerge') | |
| var rsAll = es.through() | |
| var trp = trumpet() | |
| trp.selectAll('table>tr', function (elTr) { | |
| var tr = trumpet() | |
| var r = {} | |
| var rs = es.through(function ondata (data) { | |
| r = merge(r, data) | |
| done() | |
| }, function () { | |
| rsAll.write(r) | |
| }) | |
| rs.setMaxListeners(0) | |
| tr.select('td.code').createReadStream() | |
| .pipe(es.through(function (code) { | |
| this.queue({code: String(code)}) | |
| })).pipe(rs, {end: false}) | |
| tr.select('td.product').createReadStream() | |
| .pipe(es.through(function (product) { | |
| this.queue({product: String(product)}) | |
| })).pipe(rs, {end: false}) | |
| tr.select('td.price').createReadStream() | |
| .pipe(es.through(function (price) { | |
| this.queue({price: Number(price)}) | |
| })).pipe(rs, {end: false}) | |
| elTr.createReadStream().pipe(tr) | |
| function done () { | |
| Object.keys(r).length === 3 && rs.end() | |
| } | |
| }) | |
| fs.createReadStream(__dirname + '/table.html') | |
| .pipe(duplexer(trp, rsAll)) | |
| .pipe(es.stringify()) | |
| .pipe(process.stdout) |
This file contains hidden or 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
| <body> | |
| <table> | |
| <tr> | |
| <th class="code">code</th> | |
| <th class="product">product</th> | |
| <th class="price">price</th> | |
| </tr> | |
| <tr> | |
| <td class="code">aaa</td> | |
| <td class="product">AAA</td> | |
| <td class="price">1000</td> | |
| </tr> | |
| <tr> | |
| <td class="code">abc</td> | |
| <td class="product">ABC</td> | |
| <td class="price">1100</td> | |
| </tr> | |
| <tr> | |
| <td class="code">xyz</td> | |
| <td class="product">XYZ</td> | |
| <td class="price">10000</td> | |
| </tr> | |
| </table> | |
| </body> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment