facebook_scrapper 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 26d91e0a8dbf79232c734882341127301ac516a29d3524462be0b56f3a8727b7
+  data.tar.gz: 813d8e43fd8857d7882b6c6fc6873a4b873ed630192107c945bca0e0d2b74f2b
+SHA512:
+  metadata.gz: 208d4f649abbe1025b98acc8250038ab04da99de42248e5b87ca7912c9fd3e1ea80a8085119e85c6a9093a76f671b00d75cb4d2446f07fa01b70101dee6d0f1d
+  data.tar.gz: 034df0dbf1b23e915cf65c3c1b639124ec880c3a3e806cc91f50f6de06eb5ffd54f8ce8cdf06acb9c8a62454d9847e1b3a5a17babec50be933aaa137c03826a9

data/lib/facebook_scrapper.rb

@@ -0,0 +1,201 @@
+require "selenium-webdriver"
+
+class FacebookScrapper
+  def initialize
+    @driver = Selenium::WebDriver.for :chrome
+  end
+
+  def toBasicUrl(url)
+    if url.include? "m.facebook.com"
+      return url.gsub!("m.facebook.com", "mbasic.facebook.com")
+    elsif url.include? "www.facebook.com"
+      return url.gsub!("www.facebook.com", "mbasic.facebook.com")
+    else
+      return url
+    end
+  end
+
+  def get(url)
+    @driver.get(toBasicUrl(url))
+  end
+
+  def get_driver
+    return @driver
+  end
+
+  def login(email, password)
+    url = "https://mbasic.facebook.com"
+    get(url)
+    email_box = @driver.find_element(name: "email")
+    email_box.send_keys(email)
+    password_box = @driver.find_element(name: "pass")
+    password_box.send_keys(password)
+    password_box.submit
+    # Bypass facebook OneClick Login
+    if @driver.find_element(class: "bi")
+      @driver.find_element(class: "bp").click()
+    end
+    begin
+      @driver.find_element(name: "xc_message")
+      puts "Logged in"
+      return true
+    rescue Selenium::WebDriver::Error::NoSuchElementError => e
+      body = @driver.find_element(tag_name: "body").text
+      if (body.include?("Enter login code to continue"))
+        puts "You 2 factor is turned on. Authenticate it and try again"
+      else
+        puts "Failed to login"
+        @driver.save_screenshot("login_failed.png")
+      end
+      return false
+    end
+  end
+
+  def logout
+  end
+
+  def write_post_to_url(url, text)
+    begin
+      get(url)
+      textBox = @driver.find_element(name: "xc_message")
+      textBox.send_keys(text)
+      textbox.submit
+      return true
+    rescue => e
+      puts "Failed to post in #{url} for error of #{e}"
+      return false
+    end
+  end
+
+  def get_posts_group(url)
+    get(url)
+    posts = []
+    all_posts = @driver.find_element(id: "m_group_stories_container").find_elements(css: "div[role='article']")
+    puts "Found #{all_posts.length} posts"
+    all_posts.each do |raw_post|
+      new_post = get_post_object(raw_post)
+      puts new_post
+      posts.push(new_post.to_json) if new_post
+    end
+    return posts
+  end
+
+  def get_posts_from_home
+    get("https://mbasic.facebook.com")
+    posts = []
+    all_posts = @driver.find_elements(css: "div[role='article']")
+    puts "Found #{all_posts.length} posts"
+    all_posts.each do |raw_post|
+      new_post = get_post_object(raw_post)
+      posts.push(new_post) if new_post
+    end
+    return posts
+  end
+
+  def post_in_group(group_url, text)
+    get(group_url)
+    begin
+      text_box = @driver.find_element(name: "xc_message")
+    rescue Selenium::WebDriver::Error::NoSuchElementError
+      @driver.save_screenshot("no_group_found.png")
+      puts "Group url dosnt exist"
+      return false
+    end
+    text_box.send_keys(text)
+    text_box.submit
+    return true
+  end
+
+  def get_post_object(raw_post)
+    begin
+      new_post = raw_post.find_element(css: "div[role='article']")
+      like_data = raw_post
+    rescue
+      new_post = raw_post
+      like_data = raw_post
+    end
+    post = Post.new
+    all_links = like_data.find_elements(tag_name: "a")
+
+    # # dont track not post things
+    return nil unless all_links[-7].text.include?("Like")
+
+    post.owner = new_post.find_elements(tag_name: "a")[0].text
+    post.text = new_post.find_element(tag_name: "p").text
+    post.like_count = all_links[-7].text.to_i
+    post.comment_count = all_links[-4].text.to_i
+    post.time = new_post.find_element(tag_name: "abbr").text
+    post.post_owner_link = all_links[0].attribute("href")
+    post.comment_link = all_links[-4].attribute("href")
+    post.like_link = like_data.find_element(link_text: "Like").attribute("href")
+    post.more_link = all_links[-1].attribute("href")
+    return post.to_h
+  rescue
+    return nil
+  end
+end
+
+class Person
+  attr_accessor :name, :pofile_link, :add_as_friend_link
+
+  def initialize
+    self.name = ""
+    self.pofile_link = ""
+    self.add_as_friend_link = ""
+  end
+
+  def to_str
+    s = ""
+    s += "#{self.name}:\n"
+    s += "Profile Link: #{self.pofile_link}"
+    if self.add_as_friend_link != ""
+      s += "Addlink ->: #{self.add_as_friend_link}"
+    end
+    return s
+  end
+end
+
+class Post
+  attr_accessor :owner, :text, :like_count, :comment_count, :like_link, :time, :post_owner_link, :comment_link, :more_link
+
+  def initialize
+    self.owner = ""
+    self.text = ""
+    self.like_count = 0
+    self.comment_count = 0
+    self.time = ""
+    self.post_owner_link = ""
+    self.comment_link = ""
+    self.like_link = ""
+    self.more_link = ""
+  end
+
+  def to_h
+    hash = {}
+    instance_variables.each do |var|
+      hash[var.to_s.delete("@")] = instance_variable_get(var)
+    end
+    return hash
+  end
+
+  def to_json
+    to_h.to_json
+  end
+
+  def to_str
+    s = "\nPost by #{self.owner}: "
+    s += "#{self.text} \n"
+    s += "Likes: #{self.like_count.to_s} - "
+    s += "Comments: #{self.comment_count.to_s} - "
+    s += "#{self.time} "
+    s += " - Privacy: #{self.privacy}\n-"
+    s += "\n Comment -> #{self.comment_link}\n"
+    return s
+  end
+end
+
+# def get_posts(url)
+#   driver.get(url)
+#   driver.find_element(id:'m_group_stories_container').find_elements(css: "div[role='article']")[0].find_element(tag_name: 'p').text
+#   driver.find_element(id:'m_group_stories_container').find_elements(css: "div[role='article']")[1].find_element(link_text: 'Full Story').attribute('href')
+# end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: facebook_scrapper
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Mujadded Al Rabbani Alif
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-09-14 00:00:00.000000000 Z
+dependencies: []
+description: This is a facebook scrapper bot that dosent require api to scrap facebook
+  data
+email: mujadded.alif@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/facebook_scrapper.rb
+homepage: https://rubygems.org/gems/facebook_scrapper
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: scrap data from fb without api
+test_files: []