insta_scrape 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: abbaf8a5b61d0f1d25d3480a64b16eedacd32b58
-  data.tar.gz: a67b9a14e265d90f47dbd566b21d64e42694fe43
+  metadata.gz: 05c519af7d4c14f15487b131afd234e2cd0c6435
+  data.tar.gz: 66aee1224c0a0c9d931f864d331d698f35b0b60d
 SHA512:
-  metadata.gz: 5a2cf697cafb2e5a46ac4dad8453666cb50d4c2923dae7d6344b9fd35aef517798d4a45c8b0d260c7f780b1036505eafd6efaa716f3b0759892ed5b6f97fd1fd
-  data.tar.gz: 235eb28eee937dfa4350ef708b1117b96f49689d89a2c65f95bc3fcd3e4514f170cb491544c58507225ba71a1a7403c235bd1e72543e775119f8d2da19bb0ca0
+  metadata.gz: 8f5bb16a646d4a73f1b226b206d19b53edf5b8cc9b1bb88b6ac27bf9b302bc39096eee6a367870553a07f2b8560946fc6cc0cc1c1f36ce1d1a5a1e112caa13a8
+  data.tar.gz: 50a190f914e87580b97293595cc60bc78a0f037871b9a0a11b9ca0bbb33cef8af5c3571fd4087c3ea5c093b003da8bf4711bdfbdbadc78932563a46f5efe1fd5

data/README.md

@@ -7,21 +7,23 @@ This gem is dependent on Capybara, PhantomJS, and Poltergeist.
 
 Using this gem you can access multiple facets of the instagram API without needing authorization, most importantly the hashtag.
 
+v.1.1.0 introducing "long_scrape" methods! Now with more instgram posts!
+
 ## Note
 
 The number of results may vary when using certain methods as this isn't an official endpoint.
 
 ## Todo
 
-* Pagination
-* Assess infinite scroll
+* Built-in Pagination
+
 
 ## Installation
 
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'insta_scrape'
+gem "insta_scrape"
 ```
 
 And then execute:
@@ -36,25 +38,47 @@ Or install it yourself as:
 
 ###Available methods
 
-As of right now, each method accepts only one argument - a hashtag or a username.
+Long scrape method take two arguments -- (hashtag || username, time_in_seconds)
+Each other method accepts only one argument - a hashtag or a username.
 
+
+####Long Scrape Methods
+```ruby
+#These can take a while but produce the best results
+#I would recommend running a background job to pull these scrapes
+
+#long scrape a user and their posts
+#depending on how long you run the scrape
+#you can pull an entire user profile and all of their posts
+#30 seconds is enough for a casual user (maybe less)
+InstaScrape.long_scrape_user_info_and_posts('foofighters', 30)
+#this does the same without pulling user info
+InstaScrape.long_scrape_user_posts('foofighters', 30)
+
+#pull all posts from a hashtag
+#infinite scroll will run as long as the time passed in
+InstaScrape.long_scrape_hashtag('test', 60)
+#=> > 2k instagram posts! Tested in specs!
+```
+
+####Regular Methods
 ```ruby
 #scrape a hashtag for as many results as possible
 InstaScrape.hashtag("test")
 #scrape all user info
-InstaScrape.user_info("dannyvassallo")
+InstaScrape.user_info("foofighters")
 #scrape all user info and posts
-InstaScrape.user_info_and_posts('foofighters')
+InstaScrape.user_info_and_posts("foofighters")
 #scrape just a users posts (as many as possible)
-InstaScrape.user_posts('foofighters')
+InstaScrape.user_posts("foofighters")
 #scrape a users follower count
-InstaScrape.user_follower_count('foofighters')
+InstaScrape.user_follower_count("foofighters")
 #scrape a users following count
-InstaScrape.user_following_count('foofighters')
+InstaScrape.user_following_count("foofighters")
 #scrape a users post count
-InstaScrape.user_post_count('foofighters')
+InstaScrape.user_post_count("foofighters")
 #scrape a users description
-InstaScrape.user_description('foofighters')
+InstaScrape.user_description("foofighters")
 ```
 
 ####Hashtag, User Post, and Nested Posts Scrape
@@ -62,8 +86,8 @@ InstaScrape.user_description('foofighters')
 ```ruby
 #basic use case
 
-#scrape_result = InstaScrape.user_info_and_posts('foofighters').posts
-#scrape_result = InstaScrape.user_posts('foofighters')
+#scrape_result = InstaScrape.user_info_and_posts("foofighters").posts
+#scrape_result = InstaScrape.user_posts("foofighters")
 scrape_result = InstaScrape.hashtag("test")
 scrape_result.each do |post|
   puts post.image
@@ -76,8 +100,8 @@ Here is a `.erb` example using MaterializeCSS to render the posts as cards:
 ```ruby
 #in your controller or helper assuming you aren't storing the posts
 
-#@posts = InstaScrape.user_info_and_posts('foofighters').posts
-#@posts = InstaScrape.user_posts('foofighters')
+#@posts = InstaScrape.user_info_and_posts("foofighters").posts
+#@posts = InstaScrape.user_posts("foofighters")
 @posts = InstaScrape.hashtag("test")
 ```
 
@@ -116,11 +140,17 @@ u.follower_count
 #returns  => "1.5m"
 u.following_count
 #returns => "35"
+u.description
+#returns => "Foo Fighters Rock band smarturl.it/sonic-highways"
+
+#and in the event you'd need it
+u.username
+#returns => "foofighters"
 ```
 
 Each of these attributes is accessible using the methods listed above as well.
 
-Using `u = InstaScrape.user_info_and_posts('foofighters')` will give access to the `u.posts` attribute and can be iterated through.
+Using `u = InstaScrape.user_info_and_posts("foofighters")` will give access to the `u.posts` attribute and can be iterated through.
 The example above covers this.
 
 ## Development

data/insta_scrape.gemspec

@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
   spec.email         = ["danielvassallo87@gmail.com"]
 
   spec.summary       = %q{Use Instagram Hashtag Embeds in 2016}
-  spec.description   = %q{A ruby scraper for instagram in 2016. Because the hashtag deprecation in the API is just silly. This gem is dependent on Capybara, PhantomJS, and Poltergeist.}
+  spec.description   = %q{A ruby scraper for instagram in 2016. Because the hashtag deprecation in the API is just silly. This gem is dependent on Capybara, PhantomJS, and Poltergeist. v.1.1.0 -- Introducing long_scrape methods! Get thousands of photo results on hashtags and full user profiles with ALL posts! See the documentation for API usage.}
   spec.homepage      = "https://github.com/dannyvassallo/insta_scrape"
   spec.license       = "MIT"
 

data/lib/insta_scrape.rb

@@ -10,6 +10,26 @@ module InstaScrape
     scrape_posts
   end
 
+  #long scrape a hashtag
+  def self.long_scrape_hashtag(hashtag, scrape_length)
+    visit "https://www.instagram.com/explore/tags/#{hashtag}/"
+    @posts = []
+    long_scrape_posts(scrape_length)
+  end
+
+  #long scrape a hashtag
+  def self.long_scrape_user_posts(username, scrape_length)
+    @posts = []
+    long_scrape_user_posts_method(username, scrape_length)
+  end
+
+  #get user info and posts
+  def self.long_scrape_user_info_and_posts(username, scrape_length)
+    scrape_user_info(username)
+    long_scrape_user_posts_method(username, scrape_length)
+    @user = InstaScrape::InstagramUserWithPosts.new(username, @image, @post_count, @follower_count, @following_count, @description, @posts)
+  end
+
   #get user info
   def self.user_info(username)
     scrape_user_info(username)
@@ -95,8 +115,35 @@ module InstaScrape
       iteration = 0
       while iteration < max_iteration do
         iteration += 1
-        5.times { page.execute_script "window.scrollBy(0,10000)" }
-        sleep 0.2
+        page.execute_script "window.scrollTo(0,document.body.scrollHeight);"
+        sleep 0.1
+        page.execute_script "window.scrollTo(0,(document.body.scrollHeight - 5000));"
+        sleep 0.1
+      end
+      iterate_through_posts
+    rescue Capybara::ElementNotFound => e
+      begin
+        iterate_through_posts
+      end
+    end
+  end
+
+  def self.long_scrape_posts(scrape_length_in_seconds)
+    begin
+      page.find('a', :text => "Load more", exact: true).click
+      max_iteration = (scrape_length_in_seconds / 0.3)
+      iteration = 0
+      @loader = "."
+      while iteration < max_iteration do
+        puts "InstaScrape is working. Please wait.#{@loader}"
+        iteration += 1
+        sleep 0.1
+        page.execute_script "window.scrollTo(0,document.body.scrollHeight);"
+        sleep 0.1
+        page.execute_script "window.scrollTo(0,(document.body.scrollHeight - 5000));"
+        sleep 0.1
+        @loader << "."
+        system "clear"
       end
       iterate_through_posts
     rescue Capybara::ElementNotFound => e
@@ -106,6 +153,12 @@ module InstaScrape
     end
   end
 
+  def self.long_scrape_user_posts_method(username, scrape_length_in_seconds)
+    @posts = []
+    visit "https://www.instagram.com/#{username}/"
+    long_scrape_posts(scrape_length_in_seconds)
+  end
+
   def self.scrape_user_posts(username)
     @posts = []
     visit "https://www.instagram.com/#{username}/"

data/lib/insta_scrape/version.rb

@@ -1,3 +1,3 @@
 module InstaScrape
-  VERSION = "1.0.0"
+  VERSION = "1.1.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: insta_scrape
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - dannyvassallo
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-06-11 00:00:00.000000000 Z
+date: 2016-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -174,6 +174,8 @@ dependencies:
         version: 1.9.0
 description: A ruby scraper for instagram in 2016. Because the hashtag deprecation
   in the API is just silly. This gem is dependent on Capybara, PhantomJS, and Poltergeist.
+  v.1.1.0 -- Introducing long_scrape methods! Get thousands of photo results on hashtags
+  and full user profiles with ALL posts! See the documentation for API usage.
 email:
 - danielvassallo87@gmail.com
 executables: []