omni_scrape 0.1.4.9

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    OTJkOGZlMjE4MGEyNGZjMzY4MTY4NjRhMGNlYzc2NGMzODUwZGMxNw==
+  data.tar.gz: !binary |-
+    YzA4ZTRkODRmNWEyNDcxNDdmM2FhYzM3OGI0NTg2MDZlMmQ4NmM3Ng==
+SHA512:
+  metadata.gz: !binary |-
+    NDhiNWY0MDU4OTUzZGFjZWU5MjQ1NDIzZjZhZTNkMTc2MmJlNmIyMzQ2NjBj
+    MzhjMjljYWIzNzZlOGQ1OTc1MDZhYmNkYWJjN2NhMWJhMDVlMTg0MTgzNjQ0
+    M2U4NmNhNjUwYmNkYjg3NTNjZTY3ZGU3MTUxNzVhNDY5NTJkNWQ=
+  data.tar.gz: !binary |-
+    MTU0OTRjYTIwODY1YTdjOGVhM2RmMTU2ZjJkZGExOGVjZmJlYjk5MmM1ZmRm
+    YTUzNjMwMDk4YzBlNjVmNjJhZDI0NjA2YjkyZDY2ZDAwNzFjZjI5NTlmMTFj
+    N2UxZGIyYzQ4NTk2Yjc1YmM1ZjU2OGI4N2Q4ZTFiNzdiYzIzZmY=

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.travis.yml

@@ -0,0 +1,3 @@
+language: ruby
+rvm:
+  - 1.9.3

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in omni_scrape.gemspec
+gemspec

data/README.md

@@ -0,0 +1,39 @@
+# OmniScrape
+
+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/omni_scrape`. 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 'omni_scrape'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install omni_scrape
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, 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` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/omni_scrape/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "omni_scrape"
+
+# 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

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/omni_scrape/version.rb

@@ -0,0 +1,3 @@
+module OmniScrape
+  VERSION = "0.1.4.9"
+end

data/lib/omni_scrape.rb

@@ -0,0 +1,77 @@
+require "omni_scrape/version"
+
+module OmniScrape
+def CrawlScrape(url, depth, sub_url)
+page = Nokogiri::HTML(open(url))
+
+links= page.css('a')
+
+refarr=[]
+titlearr=[]
+titles =[]
+hrefs = []
+x=0
+links.each do |link|
+			if(link['title']!=nil && link['title']!="" &&link['href']!=nil && link['href']!="")
+			# puts x
+			# puts (link['title'].split.join)
+			# x+=1
+			titles.push((link['title']).split.join)
+			hrefs.push((link['href']).split.join)
+				
+			end
+			
+    end
+	inc=0
+	while(!hrefs.empty?)
+		value= hrefs.pop
+		puts value
+		refarr.push(value)
+		refarr[inc]
+		inc+=1
+	end
+	inc=0
+    while(!titles.empty?)
+       value = titles.pop
+	   puts value
+	   titlearr.push(value)
+	   puts titlearr[inc]
+	   inc+=1
+	end
+	
+        refarr.push("-")
+  
+
+for i in 0..titlearr.length
+    if(refarr[i]!="-")
+    url=sub_url+refarr[i]
+	fourofour=false
+	
+		begin
+			if(fourofour==false)
+			pagina = Nokogiri::HTML(open(url))
+			end
+		rescue Exception =>ex
+			puts "got a 404"
+			fourofour=true
+			retry
+		end
+		if (fourofour==false)
+		trimval=titlearr[i]
+		finval=trimval.gsub!(/[!:\/-]/, '')
+        puts titlearr[i]
+		if(finval==nil && titlearr[i]!=nil)
+		finval=titlearr[i]
+		end
+		puts finval
+		if(finval!=nil)
+		crfile=File.new((finval+".html").chomp,"w")
+    crfile.puts pagina
+    crfile.close
+	end
+	end
+        end
+end
+
+	end#def crawlscrape
+end#module

data/omni_scrape.gemspec

@@ -0,0 +1,22 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'omni_scrape/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "omni_scrape"
+  spec.version       = OmniScrape::VERSION
+  spec.authors       = ["Bradley Maynard"]
+  spec.email         = ["maynard_bradley@yahoo.com"]
+
+  spec.summary       = %q{This is an all-purpose web scraper}
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "nokogiri", "~>1.6.6.2"
+  spec.add_development_dependency "bundler", "~> 1.9"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

metadata

@@ -0,0 +1,95 @@
+--- !ruby/object:Gem::Specification
+name: omni_scrape
+version: !ruby/object:Gem::Version
+  version: 0.1.4.9
+platform: ruby
+authors:
+- Bradley Maynard
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-06-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.6.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.6.2
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !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: 
+email:
+- maynard_bradley@yahoo.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/omni_scrape.rb
+- lib/omni_scrape/version.rb
+- omni_scrape.gemspec
+homepage: 
+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: 2.4.7
+signing_key: 
+specification_version: 4
+summary: This is an all-purpose web scraper
+test_files: []