instagram-crawler 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 27b1cbc3574a62d01153ab0dd3854eadd933347f9bd10c32488c7b5500b55d4a
-  data.tar.gz: 3aa03c9d8c81dd633fc1f57bd3cce5a268bfaf8d0faa54aa0b7af7329aed0123
+  metadata.gz: 5bbb0b173538ea3c0c43142545fe645f5651e59733f6286b40e97df437b66619
+  data.tar.gz: 1626445eb2a4a8e64e64373c3fa4099d046c0d7fbf5c62057dfbe440d438ca59
 SHA512:
-  metadata.gz: 64dce2e2e24e0a80b79e1213acc46535e006044ee5902dbd06068d718908c9b96917bb15e9566592192b9e609b60f8bdb7de5e3801f52496b72242df70d773a2
-  data.tar.gz: d9ac14681c7731f1d4a6c75bd387b540f68492ed7f1e8c87161e1abdfaf402aef5041835caed0c1d544da73892d512066346f80b35dcf1c8fdcf5bbadfcd12cd
+  metadata.gz: 4b48b5098fa06a70e85a0ccb6540aa428cc373f880b493be97f7ea3535547cd3ce2ce4f83605bc515010af1f9d1287729d03e6cfb3140461350d7fa9541b4e4e
+  data.tar.gz: 67ee453b7b5308796236ae2f758043e64277fc738b45e8a206a012230079ebc329ec87867f4e216547745bb56aadbca848120f27c2458d555c33bd0e1c327273

data/.travis.yml

@@ -1,7 +1,6 @@
----
 sudo: false
 language: ruby
-cache: bundler
 rvm:
   - 2.5.1
 before_install: gem install bundler -v 1.17.1
+script: bundle exec rspec --color

data/Dockerfile

@@ -0,0 +1,7 @@
+FROM ruby:2.5.1
+
+MAINTAINER leonji mgleon08@gmail.com
+
+RUN gem install instagram-crawler
+
+ENTRYPOINT ["instagram-crawler"]

data/Gemfile

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

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    instagram-crawler (0.1.0)
+    instagram-crawler (0.2.0)
       colorize (~> 0.8)
       http (~> 4.0)
       nokogiri (~> 1.8)
@@ -12,7 +12,14 @@ GEM
     addressable (2.5.2)
       public_suffix (>= 2.0.2, < 4.0)
     colorize (0.8.1)
+    coveralls (0.8.22)
+      json (>= 1.8, < 3)
+      simplecov (~> 0.16.1)
+      term-ansicolor (~> 1.3)
+      thor (~> 0.19.4)
+      tins (~> 1.6)
     diff-lcs (1.3)
+    docile (1.3.1)
     domain_name (0.5.20180417)
       unf (>= 0.0.5, < 1.0.0)
     http (4.0.0)
@@ -24,6 +31,7 @@ GEM
       domain_name (~> 0.5)
     http-form_data (2.1.1)
     http_parser.rb (0.6.0)
+    json (2.1.0)
     mini_portile2 (2.3.0)
     nokogiri (1.8.5)
       mini_portile2 (~> 2.3.0)
@@ -42,6 +50,15 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.8.0)
     rspec-support (3.8.0)
+    simplecov (0.16.1)
+      docile (~> 1.1)
+      json (>= 1.8, < 3)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.2)
+    term-ansicolor (1.7.0)
+      tins (~> 1.0)
+    thor (0.19.4)
+    tins (1.20.2)
     unf (0.1.4)
       unf_ext
     unf_ext (0.0.7.5)
@@ -51,6 +68,7 @@ PLATFORMS
 
 DEPENDENCIES
   bundler (~> 1.17)
+  coveralls
   instagram-crawler!
   rake (~> 10.0)
   rspec (~> 3.0)

data/README.md

@@ -1,5 +1,13 @@
 # Instagram Crawler
 
+[![Gem Version](https://badge.fury.io/rb/instagram-crawler.svg)](https://badge.fury.io/rb/instagram-crawler)
+[![Maintainability](https://api.codeclimate.com/v1/badges/a1625a5a812f515bdd91/maintainability)](https://codeclimate.com/github/mgleon08/instagram-crawler/maintainability)
+[![Build Status](https://travis-ci.org/mgleon08/instagram-crawler.svg?branch=master)](https://travis-ci.org/mgleon08/instagram-crawler)
+[![Coverage Status](https://coveralls.io/repos/github/mgleon08/instagram-crawler/badge.svg?branch=master)](https://coveralls.io/github/mgleon08/instagram-crawler?branch=master)
+[![security](https://hakiri.io/github/mgleon08/instagram-crawler/master.svg)](https://hakiri.io/github/mgleon08/instagram-crawler/master)
+[![MIT licensed](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/mgleon08/instagram-crawler/blob/master/LICENSE.txt)
+
+
 > The easiest way to download instagram photos, posts and videos.
 
 <img src="screenshots/logo.png" width="200" align="center">
@@ -48,6 +56,14 @@ instagram-crawler -u <user_name> -d -a 20181120
 instagram-crawler -u <user_name> -l
 ```
 
+### Proxy
+
+`-P || --proxyname ` `-p || --port`
+
+```ruby
+instagram-crawler -u <user_name> -P http://example.com -p 1234
+```
+
 ### Help
 
 `instagram-crawler -h | --help`
@@ -62,10 +78,26 @@ options:
     -d, --download                   Download files
     -a, --after DATE                 Download files after this date (YYYYMMDD)
     -l, --log                        Generate a log file in the current directory
+    -P, --proxyname PROXYNAME        Specify proxyname of your proxy server
+    -p, --port PORT                  Specify port of your proxy server (default port: 8080)
     -v, --version                    Show the instagram-crawler version
     -h, --help                       Show this message
 ```
 
+## Docker
+
+```docker
+# make sure already setting env variable
+# you can setting sessionid in local use $sessionid or pass sessionid to docker
+# $PWD/instagram-crawler is file store path
+
+# pull image
+docker pull mgleon08/instagram-crawler
+
+# docker run
+docker run -it --rm -v $PWD/instagram-crawler:/instagram-crawler -e sessionid=$sessionid --name marvel mgleon08/instagram-crawler -u marvel -a 20181124 -d -l
+```
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at [`https://github.com/mgleon08/instagram-crawler/pulls`](https://github.com/mgleon08/instagram-crawler/pulls)

data/bin/instagram-crawler

@@ -1,9 +1,8 @@
 #!/usr/bin/env ruby
 require_relative '../lib/instagram_crawler'
-
 begin
-  raise InstagramCrawler::Errors::EnvError if ENV["sessionid"].nil?
   args = InstagramCrawler::Parser::Args.new(ARGV)
+  raise InstagramCrawler::Errors::EnvError if ENV["sessionid"].nil?
   InstagramCrawler::Logger.setting(args.log)
   InstagramCrawler::Main.run
 rescue => e

data/lib/instagram_crawler/config.rb

@@ -4,7 +4,8 @@ module InstagramCrawler
     class << self
       attr_reader :default_url, :user_name, :base_url, :base_path,
                   :log_path, :after_date, :parse_date
-      attr_accessor :download
+      attr_accessor :download, :proxyname
+      attr_writer :port
 
       def user_name=(user_name)
         @user_name = user_name
@@ -17,6 +18,10 @@ module InstagramCrawler
         @after_date = after_date
         @parse_date = Time.parse(after_date).to_i
       end
+
+      def port
+        @port ? @port.to_i : 8080
+      end
     end
   end
 end

data/lib/instagram_crawler/file.rb

@@ -25,7 +25,8 @@ module InstagramCrawler
       private
 
       def get_binary_data(url)
-        res = HTTP.get(url)
+        res = Config.proxyname ?
+          HTTP.via(Config.proxyname, Config.port).get(url) : HTTP.get(url)
         raise Errors::HttpError, "#{res.code} #{res.reason}" if res.code != 200
         res.to_s
       end

data/lib/instagram_crawler/parser/args.rb

@@ -20,6 +20,8 @@ module InstagramCrawler
         opts.on('-d', '--download', 'Download files') { |download| Config.download = true }
         opts.on('-a', '--after DATE', 'Download files after this date (YYYYMMDD)') { |after_date| Config.after_date = after_date }
         opts.on('-l', '--log', 'Generate a log file in the current directory') { self.log = true }
+        opts.on('-P', '--proxyname PROXYNAME', 'Specify proxyname of your proxy server') { |proxyname| Config.proxyname = proxyname }
+        opts.on('-p', '--port PORT', 'Specify port of your proxy server (default port: 8080)') { |port| Config.port = port }
         opts.on('-v', '--version', 'Show the instagram-crawler version') { puts("instagram-crawler #{InstagramCrawler::VERSION}"); exit }
         opts.on('-h', '--help', 'Show this message') { puts(opts); exit }
         opts.parse!(@args)

data/lib/instagram_crawler/parser/html.rb

@@ -70,7 +70,8 @@ module InstagramCrawler
       end
 
       def get_html(url)
-        res = HTTP.get(url)
+        res = Config.proxyname ?
+          HTTP.via(Config.proxyname, Config.port).get(url) : HTTP.get(url)
         raise Errors::HttpError, "#{res.code} #{res.reason}" if res.code != 200
         res.to_s
       end

data/lib/instagram_crawler/parser/json.rb

@@ -47,7 +47,9 @@ module InstagramCrawler
       end
 
       def get_json(url)
-        res = HTTP.cookies(sessionid: ENV["sessionid"]).get(url)
+        http = HTTP.cookies(sessionid: ENV["sessionid"])
+        res = Config.proxyname ?
+          http.via(Config.proxyname, Config.port).get(url) : http.get(url)
         raise Errors::HttpError, "#{res.code} #{res.reason}" if res.code != 200
         res.to_s
       end

data/lib/instagram_crawler/version.rb

@@ -1,3 +1,3 @@
 module InstagramCrawler
-  VERSION = "0.1.1".freeze
+  VERSION = "0.2.0".freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: instagram-crawler
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Leon Ji
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-23 00:00:00.000000000 Z
+date: 2018-12-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -105,6 +105,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- Dockerfile
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt