Gabin Desserprit gahabeen
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
| <!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"> |
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
| company | |
| |_ name | |
| |_ description | |
| |_ url | |
| |_ contact | |
| |_ telephone | |
| |_ employee | |
| |_ name | |
| |_ jobTitle | |
| |_ email |
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
| 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
/ barecheerioextractdata.js
Last active
February 2, 2018 20:06
Bare Cheerio Code to Extract Data
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
| 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'); |
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
| 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
/ barecheerioextractdataoutput.js
Created
January 27, 2017 22:47
Bare Cheerio Code to Extract Data Output
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
| // Here is the output data: | |
| // [ | |
| // { | |
| // "name": " Tessera ", | |
| // "description": " Proud of our wide range of product\n\t\t\t\twe developped many project in the past 4 years. You can find the company \n\t\t\t\tin 14 different countries ", | |
| // "contact": { | |
| // "telephone": " Phone: (841) 467-168 ", | |
| // "employee": { | |
| // "name": " Mike Layn ", | |
| // "jobTitle": " Marketing Assistant", |
gahabeen
/ jsonframedataextractionoutput.js
Created
January 27, 2017 22:50
jsonframe data extraction output
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
| // Here is the output data: | |
| // { | |
| // "companies": [ | |
| // { | |
| // "name": "Tessera", | |
| // "description": "Proud of our wide range of product we developped many project in the past 4 years. You can find the company in 14 different countries in the world. Blablabla.", | |
| // "url": "/comp/tessera", | |
| // "contact": { | |
| // "telephone": "841467168", | |
| // "employee": { |
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
| let cheerio = require('cheerio'); | |
| let jsonframe = require('jsonframe-cheerio'); | |
| request('https://www.growthhacking.fr', function (error, response, html) { | |
| if (!error && response.statusCode == 200) { | |
| let $ = cheerio.load('https://www.growthhacking.fr'); | |
| jsonframe($); // initializes the plugin | |
| var frame = { | |
| "post": { // setting the parent item as "companies" |
gahabeen
/ producthunt_structure.txt
Created
January 30, 2017 17:19
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
| product | |
| |_ name | |
| |_ description | |
| |_ image | |
| |_ upvotes | |
| |_ comments |
gahabeen
/ producthunt_selectors.txt
Created
January 30, 2017 17:22
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
| product : ul.postsList_3n2Ck li | |
| |_ name : .content_3Qj0y .title_24w6f | |
| |_ description : .content_3Qj0y .subtle_fyrho | |
| |_ image : img (attr: src) | |
| |_ upvotes : [data-test=vote-button] .buttonContainer_1ROJn | |
| |_ comments : [data-test=vote-button] + a .buttonContainer_1ROJn |
OlderNewer