instagram_crawler 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 102e0a0d0693b707f49b4392482feb4b72d32c5f
+  data.tar.gz: 209c7a644d8f0eefb0e951e1140f0ba1b024e9a9
+SHA512:
+  metadata.gz: 8be6c2cdfcc542a2997aa450df890f745cb040e9761fad4ecf0a452197bd62d0d6c8afbcf90bef6613d4db253823748b82cf1dc9388e1f1e978cab38588b1671
+  data.tar.gz: 159850335a25e6ee2e1ad2e5ee32d0c54f544e5f5156cf2269c4a1675d61d499817d5c0cc2bf9528288227eef68faf4bf2a1c7044564d5f406e9041d6e98e39e

data/.gitignore

@@ -0,0 +1,8 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in instagram_crawler.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,20 @@
+PATH
+  remote: .
+  specs:
+    instagram_crawler (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    rake (10.4.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  instagram_crawler!
+  rake (~> 10.0)
+
+BUNDLED WITH
+   1.16.1

data/README.md

@@ -0,0 +1,35 @@
+# InstagramCrawler
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/instagram_crawler`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'instagram_crawler'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install instagram_crawler
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/instagram_crawler.

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "instagram_crawler"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/instagram_crawler.gemspec

@@ -0,0 +1,34 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "instagram_crawler/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "instagram_crawler"
+  spec.version       = InstagramCrawler::VERSION
+  spec.authors       = ["plusquality"]
+  spec.email         = ["plus.quolity@gmail.com"]
+
+  spec.summary       = %q{image download from instagram}
+  spec.description   = %q{image download from instagram}
+  spec.homepage      = "https://www.plusq.life/"
+
+  # # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # # to allow pushing to a single host or delete this section to allow pushing to any host.
+  # if spec.respond_to?(:metadata)
+  #   spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+  # else
+  #   raise "RubyGems 2.0 or newer is required to protect against " \
+  #     "public gem pushes."
+  # end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/lib/instagram_crawler.rb

@@ -0,0 +1,147 @@
+require "instagram_crawler/version"
+require 'logger'
+require 'json'
+require 'net/http'
+
+module InstagramCrawler
+  class Client
+    def initialize(hashtag)
+      @hashtag = hashtag
+      @crawler = GetHashTagUrl.new(@hashtag)
+    end
+
+    def get_image_urls(limit = 1000)
+       @crawler.download_hashtag(limit)
+    end
+  end
+end
+
+module InstagramCrawler
+  class GetHashTagUrl
+    attr_accessor :images
+    def initialize(hashtag)
+      @logger = Logger.new(STDOUT)
+      @hashtag = hashtag
+      @images = []
+    end
+
+    def info(message)
+      @logger.info(message)
+    end
+
+    def error(message)
+      @logger.error(message)
+    end
+
+    def download_hashtag(limit)
+      next_page = nil
+      number = 0
+      loop do
+        get_number, next_page = download_hashtag_page(@hashtag, next_page)
+        number += get_number
+        info "getting #{number} ##{@hashtag} images...."
+        break if next_page.nil? || number > limit
+      end
+      @images = @images.take(limit) if @images.count > limit
+      return @images
+    end
+
+    def download_hashtag_page(hashtag, page)
+      json_result = download_per_page(hashtag, page)
+      return [0, nil] if json_result.nil?
+      hashtag_info = json_result['graphql']['hashtag']
+      size = 0
+      %w(media top_posts).each do |part|
+        next if part == 'top_posts' && page
+        edges = hashtag_info["edge_hashtag_to_#{part}"]['edges']
+        edges.each do |edge|
+          hashtag_format = format_edge(edge)
+          @images << hashtag_format
+        end
+        next if edges.empty?
+        size += edges.size
+      end
+      if hashtag_info['edge_hashtag_to_media']['page_info']['has_next_page']
+        [size, hashtag_info['edge_hashtag_to_media']['page_info']['end_cursor']]
+      else
+        [size, nil]
+      end
+    end
+
+    # retuen result_hash
+    def format_edge(edge)
+      return if edge.nil?
+      {
+        id: edge["node"]["id"].to_i,
+        text: edge["node"]["edge_media_to_caption"]["edges"][0]["node"]["text"],
+        shortcode: edge["node"]["shortcode"],
+        dimensions: edge["node"]["dimensions"],
+        image_url: edge["node"]["display_url"],
+        owner: edge["node"]["owner"],
+        thumbnail_url: edge["node"]["thumbnail_src"],
+        hashtag: edge["node"]["edge_media_to_caption"]["edges"][0]["node"]["text"].scan(%r|\s?(#[^\s　]+)\s?|).flatten,
+        thumnail_images: edge["node"]["thumbnail_resources"]
+      }
+    rescue => e
+      return nil
+    end
+
+    def download_per_page(hashtag, page, use_cookie = false)
+      download_uri = hashtag_page_url(hashtag, page)
+      return if download_uri.nil?
+      result = http_access(download_uri, use_cookie)
+      JSON.parse(result)
+    rescue JSON::ParserError => e
+      error "JSON parsing failed for URI: #{download_uri}, not retrying"
+      return nil
+    rescue => e
+      error "Download failed for URI: #{download_uri} retrying ..."
+      sleep 1
+      retry
+    end
+
+    def http_access(uri, use_cookie = false, try = 3, first = true)
+      response = if use_cookie
+                   http = Net::HTTP.new(uri.hostname, uri.port)
+                   http.use_ssl = true
+                   http.get(uri, 'Cookie' => false)
+                 else
+                   Net::HTTP.get_response uri
+                 end
+      if response.code.to_i >= 399
+        if try > 0
+          warn "Downloading #{uri} ended in #{response.code} Retrying #{try} times."
+          if response.code == 429
+            sleep 5
+            return http_access(uri, use_cookie, 10, false) if first
+          else
+            sleep 1
+          end
+          http_access(uri, use_cookie, try -1 , first)
+        else
+          response.body
+        end
+      else
+        response.body
+      end
+    rescue => e
+      if try > 0
+        warn "Downlading #{uri} ended in #{e}. Retring #{try} times"
+        sleep 1
+        http_access(uri, use_cookie, try -1, first)
+      else
+        ""
+      end
+    end
+
+    def hashtag_page_url(hashtag, page)
+      if page
+        URI.parse URI.encode "https://www.instagram.com/explore/tags/#{hashtag}/?__a=1&max_id=#{page}"
+      else
+        URI.parse URI.encode "https://www.instagram.com/explore/tags/#{hashtag}/?__a=1"
+      end
+    rescue URI::InvalidURIError
+      error "Invalid hashtag #{hashtag} .."
+    end
+  end
+end

data/lib/instagram_crawler/version.rb

@@ -0,0 +1,3 @@
+module InstagramCrawler
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,81 @@
+--- !ruby/object:Gem::Specification
+name: instagram_crawler
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- plusquality
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-04-29 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: image download from instagram
+email:
+- plus.quolity@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- instagram_crawler.gemspec
+- lib/instagram_crawler.rb
+- lib/instagram_crawler/version.rb
+homepage: https://www.plusq.life/
+licenses: []
+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: 2.5.2
+signing_key: 
+specification_version: 4
+summary: image download from instagram
+test_files: []