Last active
August 18, 2018 03:57
-
-
Save ixtgorilla/3aec7a651c5546481770e351be1fff08 to your computer and use it in GitHub Desktop.
TwitterProfileCrawler
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
module Requestor | |
module Https | |
# Net::HTTP for Get Wrapper | |
# | |
# @param [String] url | |
# @return [Net] | |
def self.execute(url, attributes = {}) | |
uri = URI.parse(url) | |
https = Net::HTTP.new(uri.host, uri.port) | |
https.use_ssl = true | |
request = Net::HTTP::Get.new(uri.request_uri) | |
attributes.each do |key, value| | |
request[key] = value | |
end | |
https.request(request) | |
end | |
end | |
end |
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
require 'nokogiri' | |
class TwitterCrawler | |
def initialize(url) | |
@url = url | |
end | |
def execute | |
{ | |
screen_name: screen_name, | |
twitter_screen_name: twitter_screen_name, | |
icon_image_url_cache: twitter_icon_image_url, | |
cover_image_url_cache: twitter_cover_image_url, | |
bio: twitter_bio | |
} | |
end | |
private | |
def twitter_cover_image_url | |
twitter_xpath | |
.xpath('//*[@id="page-container"]/div[1]/div/div[1]/div[1]/img')[0] | |
.attributes['src'] | |
.value | |
end | |
def twitter_icon_image_url | |
twitter_xpath | |
.xpath('//*[@id="page-container"]/div[1]/div/div[1]/div[2]/div[1]/div/a/img')[0] | |
.attributes['src'] | |
.value | |
end | |
def screen_name | |
twitter_xpath | |
.xpath('//*[@id="page-container"]/div[2]/div/div/div[1]/div/div/div/div[1]/h1/a')[0] | |
.children[0] | |
.text | |
end | |
def twitter_screen_name | |
twitter_xpath | |
.xpath('//*[@id="page-container"]/div[2]/div/div/div[1]/div/div/div/div[1]/h2/a/span/b')[0] | |
.children[0] | |
.text | |
end | |
def twitter_bio | |
bio_tags = twitter_xpath | |
.xpath('//*[@id="page-container"]/div[2]/div/div/div[1]/div/div/div/div[1]/p')[0] | |
.children | |
bio_tags.map do |elem| | |
if elem.name == 'img' | |
elem.attributes['alt'] | |
else | |
elem.text | |
end | |
end.join('') | |
end | |
def twitter_xpath | |
@twitter_xpath ||= Nokogiri::HTML.parse(twitter_html) | |
end | |
def twitter_html | |
@twitter_html ||= Requestor::Https.execute(@url).body | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment