From 0f3e97e48cc0a4b42b60c2160b9a7049440fc9fa Mon Sep 17 00:00:00 2001
From: aboutaaron <aaron.colby.williams@gmail.com>
Date: Sun, 19 Aug 2012 15:15:39 -0700
Subject: [PATCH] combined old code to one file

---
 keywords.rb | 17 ++++++++++++---
 refactor.rb | 63 -----------------------------------------------------
 2 files changed, 14 insertions(+), 66 deletions(-)
 delete mode 100644 refactor.rb

diff --git a/keywords.rb b/keywords.rb
index 0272bb5..514d20e 100755
--- a/keywords.rb
+++ b/keywords.rb
@@ -15,10 +15,12 @@
 a = Mechanize.new
 
 # Login
+username = ""
+password = ""
 x = a.get(base_url).forms.first
 p "Submitting login info..."
-x["name"] = "jevon.phillips"
-x["password"] = "marvel"
+x["name"] = username
+x["password"] = password
 x.submit
 
 # open keyword section w/ appropriate parameters
@@ -34,7 +36,11 @@
         image_page = base_url + link['href']
         a.get(image_page)
         # Grab Descriptions, remove whitespace, store in variable photo_info and write to photo.txt
-        file_name = a.page.link_with(:href => /\-sxga.jpg/).text
+        begin
+            file_name = a.page.link_with(:href => /\-sxga.jpg/).text
+        rescue  StandardError => e
+            puts "Error: #{e}"
+        end
         photo_info = a.page.search("#image_description, #image_caption, #image_title").map(&:text).map(&:strip)
 
         open("captions_keywords.txt", "a") do |f|
@@ -82,8 +88,13 @@
         end
     end
 end
+
 exec "figlet 'Finished keywords'"
+
 puts
+
+a.get("http://laiac1b5z1-int.latimes.com/images?content_partial=global%2Fcontent_list&filter_by=title&filter_status=all&filter_val=&limit=1000&offset=20&search_published=false&sort_asc=desc&sort_by=modified")
+
 p "Opening up the 'Images' section with all images. This will take a while..."
 # URL with maximum photo size
 a.get("http://laiac1b5z1-int.latimes.com/images?content_partial=global%2Fcontent_list&filter_by=title&filter_status=all&filter_val=&limit=1000&offset=20&search_published=false&sort_asc=desc&sort_by=modified")
diff --git a/refactor.rb b/refactor.rb
deleted file mode 100644
index f9c6380..0000000
--- a/refactor.rb
+++ /dev/null
@@ -1,63 +0,0 @@
-require "rubygems"
-require "mechanize"
-require "open-uri"
-require "fileutils"
-
-# Files
-IMAGES = "images"
-Dir.mkdir(IMAGES) unless File.exists?(IMAGES)
-File.open("captions.txt", "w"){ |somefile| somefile.puts "TOP"}
-
-
-
-# Structure
-base_url = "http://laiac1b5z1-int.latimes.com"
-
-# Initialize Mechanize
-a = Mechanize.new
-
-# Login
-x = a.get("http://laiac1b5z1-int.latimes.com/").forms.first
-p "Submitting login info..."
-x["name"] = "jevon.phillips"
-x["password"] = "marvel"
-x.submit
-
-# Click on Image page
-p "Opening up the 'Images' page with all images. This will take a while..."
-puts
-puts
-# URL with maximum photo size
-a.get("http://laiac1b5z1-int.latimes.com/images?content_partial=global%2Fcontent_list&filter_by=title&filter_status=all&filter_val=&limit=1000&offset=20&search_published=false&sort_asc=desc&sort_by=modified")
-
-# Boom
-p "Iterating through links..."
-a.page.search("td:nth-child(3) a").each do |link|
-    image_page = base_url + link['href']
-    p "Here's your full url..."
-    p image_page
-    puts
-    a.get(image_page)
-    # Grab Descriptions, remove whitespace, store in variable photo_info and write to photo.txt
-    photo_info = a.page.search("#image_description, #image_caption, #image_title").map(&:text).map(&:strip)
-
-    open("captions.txt", "a") do |f|
-        f << photo_info
-        f.puts "\n"
-        f.puts "The file name is " + a.page.link_with(:href => /\-sxga.jpg/).text
-        f.puts "\n"*2
-    end
-
-    # Click largest image
-    a.page.link_with(:href => /\-sxga.jpg/).click
-
-    # Setting variables for download
-    img_url = a.page.search("img")[0].attributes['src'].text
-
-    # Change to Images Directory and download file
-    Dir.chdir("images") do
-        a.get(base_url+img_url).save
-        # Sleepy time for the request
-
-    end
-end
\ No newline at end of file