Gabin Desserprit gahabeen

Automating the web @ Vobile.

gahabeen / jsonframedataextraction.js

Last active January 28, 2017 10:41

jsonframe data extraction

	let cheerio = require('cheerio');
	let jsonframe = require('jsonframe-cheerio');

	let $ = cheerio.load('our html page url here');
	jsonframe($); // initializes the plugin

	var frame = {
	"companies": { // setting the parent item as "companies"
	"selector": ".item", // defines the elements to search for
	"data": [{ // "data": [{}] defines a list of items

gahabeen / barecheerioextractdata.js

Last active February 2, 2018 20:06

Bare Cheerio Code to Extract Data

	let cheerio = require('cheerio')
	let $ = cheerio.load('our html page url here')

	var companiesList = [];

	// For each .item, we add all the structure of a company to the companiesList array
	// Don't try to understand what follows because we will do it differently.
	$('.list.items .item').each(function(index, element){
	companiesList[index] = {};
	var header = $(element).find('.header');

gahabeen / selectorsofdata.txt

Last active January 27, 2017 22:45

Selectors Structure of Data

	company : .list.items .item
	\|_ name : .header [itemprop=name]
	\|_ description : .header [rel=description]
	\|_ url : .header [itemprop=name] a
	\|_ contact : .contact
	\|_ telephone : [itemprop=telephone]
	\|_ employee
	\|_ name : [itemprop=employeeName]
	\|_ jobTitle : [itemprop=employeeJobTitle]
	\|_ email : [itemprop=email]

gahabeen / structureofdata.txt

Last active January 27, 2017 22:45

Companies Structure

gahabeen / index.html

Last active January 27, 2017 22:43

List of companies

	<!DOCTYPE html>
	<html lang="en">
	<head>
	</head>

	<body>
	<!-- Data we want to scrape starts here -->
	<div class="list items">
	<div class="item">
	<div class="header">