forki 0.1.3 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a0667614af238aeb8089c1af60794918c0986b7f5e12fa6fe96d33a2a5c1a06f
-  data.tar.gz: 5668a5a6056bdf9bdd9c9fd8f119fa5ed754c5ee0b152d2764b26e9f9d7a8804
+  metadata.gz: 67f9dde3202683b68acd00f10ec572ba80bb4a749fa369251c5e512bb8304393
+  data.tar.gz: 55f099e3e63f174c4ae00aef56c27c77a44b5b49414dcfb7f37e32ae8bb9f47f
 SHA512:
-  metadata.gz: 509ffb30dada2666236ed0900e1def8a61413ee3ba2e8705e31bd01422f8d2baf2cd24479faf906b6374602fcb0c1dc7bb334b7e02a560c798eba6efab30a2c9
-  data.tar.gz: 3f79b804b5505222e06a49352807d92c95f13a8735bedcd1b32cbf079be72b0922052014ef82da8771db108f7b0b674cd132caf7d377084c57cf0d245eb049e1
+  metadata.gz: 35db430333dcc95259f49d1159e976f3d969b648f80c4af9a6b87c0ae0ff4ae67462f1942797da212861c26aeab7ee982f76b86e3af8563dca561e57d012aaa3
+  data.tar.gz: 40f0be4238a4b0bfd7fd23309403df139f82e728739211226c753e52ee96cb7ce2300ee4c0c81539c90761f05d8054b2f7a1b1d1e16cd9cd2744263df4ebf16e

data/lib/forki/scrapers/post_scraper.rb

@@ -100,7 +100,11 @@ module Forki
         begin
           find("span", wait: 5, text: "This Video Isn't Available Anymore", exact_text: false)
         rescue Capybara::ElementNotFound, Selenium::WebDriver::Error::StaleElementReferenceError
-          return true
+          begin
+            find("span", wait: 5, text: "This Page Isn't Available", exact_text: false)
+          rescue Capybara::ElementNotFound, Selenium::WebDriver::Error::StaleElementReferenceError
+            return true
+          end
         end
       end
 

data/lib/forki/scrapers/scraper.rb

@@ -112,18 +112,41 @@ module Forki
 
       url ||= "https://www.facebook.com"
 
-
       page.driver.browser.navigate.to(url)  # Visit the url passed in or the facebook homepage if nothing is
 
       # Look for "login_form" box, which throws an error if not found. So we catch it and run the rest of the tests
       begin
         login_form = first(id: "login_form", wait: 5)
       rescue Capybara::ElementNotFound
-        return unless page.title.downcase.include?("facebook - log in")
+        begin
+          login_form = find(:xpath, '//form[@data-testid="royal_login_form"]')
+        rescue Capybara::ElementNotFound
+          return unless page.title.downcase.include?("facebook - log in")
+        end
       end
 
-      # Since we're not logged in, let's do that quick
-      page.driver.browser.navigate.to("https://www.facebook.com") if login_form.nil?
+      # Since we're not logged in, let's do that quickly
+      if login_form.nil?
+        page.driver.browser.navigate.to("https://www.facebook.com")
+
+        # Find the login form... again (Yes, we could extract this out, but it's only ever used
+        # here, so it's not worth the effort)
+        begin
+          login_form = first(id: "login_form", wait: 5)
+        rescue Capybara::ElementNotFound
+          begin
+            login_form = find(:xpath, '//form[@data-testid="royal_login_form"]')
+          rescue Capybara::ElementNotFound
+            return unless page.title.downcase.include?("facebook - log in")
+          end
+        end
+      end
+
+      if login_form.nil?
+        # maybe we're already logged in?
+        sleep(rand * 10.3)
+        return
+      end
 
       login_form.fill_in("email", with: ENV["FACEBOOK_EMAIL"])
       login_form.fill_in("pass", with: ENV["FACEBOOK_PASSWORD"])
@@ -154,10 +177,19 @@ module Forki
     # If either of those two conditions are false, raises an exception
     def validate_and_load_page(url)
       Capybara.app_host = "https://www.facebook.com"
-      facebook_url = "https://www.facebook.com"
-      # visit "https://www.facebook.com" unless current_url.start_with?(facebook_url)
-      login(url)
-      raise Forki::InvalidUrlError unless url.start_with?(facebook_url)
+      facebook_hosts = ["facebook.com", "www.facebook.com", "web.facebook.com", "m.facebook.com"]
+      parsed_url = URI.parse(url)
+      host = parsed_url.host
+      raise Forki::InvalidUrlError unless facebook_hosts.include?(host)
+
+      # Replace the host with a default one to prevent redirect loops that can happen
+      unless parsed_url.host == "www.facebook.com"
+        parsed_url.host = "www.facebook.com"
+        url = parsed_url.to_s
+      end
+
+      visit "https://www.facebook.com"
+      login
       visit url unless current_url.start_with?(url)
     end
 

data/lib/forki/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Forki
-  VERSION = "0.1.3"
+  VERSION = "0.1.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: forki
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors:
 - ''
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-06-05 00:00:00.000000000 Z
+date: 2023-06-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: capybara
@@ -139,7 +139,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.26
+rubygems_version: 3.4.14
 signing_key:
 specification_version: 4
 summary: A gem to scrape Facebook pages for archive purposes.