Repository: scotch-io/node-web-scraper
Branch: master
Commit: 044071bccf27
Files: 4
Total size: 2.0 KB

Directory structure:
gitextract_g72w4jjs/

├── .gitignore
├── README.md
├── package.json
└── server.js

================================================
FILE CONTENTS
================================================

================================================
FILE: .gitignore
================================================
lib-cov
*.seed
*.log
*.csv
*.dat
*.out
*.pid
*.gz

pids
logs
results

npm-debug.log
node_modules


================================================
FILE: README.md
================================================
node-web-scraper
================

Simple web scraper to get a movie name, release year and community rating from IMDB.
To run this example use the following commands:

``` shell
$ npm install
$ node server.js
```

 Then it will start up our node server, navigate to http://localhost:8081/scrape and see what happens.


================================================
FILE: package.json
================================================
{
  "name"         : "node-web-scrape",
  "version"      : "0.0.1",
  "description"  : "Scrape le web.",
  "main"         : "server.js",
  "author"       : "Scotch",
  "repository"   : {
    "type" : "git",
    "url"  : "https://github.com/scotch-io/node-web-scraper"
  },
  "dependencies" : {
    "express"    : "latest",
    "request"    : "latest",
    "cheerio"    : "latest"
  }
}


================================================
FILE: server.js
================================================
var express = require('express');
var fs      = require('fs');
var request = require('request');
var cheerio = require('cheerio');
var app     = express();

app.get('/scrape', function(req, res){
  // Let's scrape Anchorman 2
  url = 'http://www.imdb.com/title/tt1229340/';

  request(url, function(error, response, html){
    if(!error){
      var $ = cheerio.load(html);

      var title, release, rating;
      var json = { title : "", release : "", rating : ""};

      $('.title_wrapper').filter(function(){
        var data = $(this);
        title = data.children().first().text().trim();
        release = data.children().last().children().last().text().trim();

        json.title = title;
        json.release = release;
      })

      $('.ratingValue').filter(function(){
        var data = $(this);
        rating = data.text().trim();

        json.rating = rating;
      })
    }

    fs.writeFile('output.json', JSON.stringify(json, null, 4), function(err){
      console.log('File successfully written! - Check your project directory for the output.json file');
    })

    res.send('Check your console!')
  })
})

app.listen('8081')
console.log('Magic happens on port 8081');
exports = module.exports = app;