href_scraper 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 8cceaad0196924b1a15e206e44d0dbe317e475ae3883e33cf1365a16d2aa7a6f
+  data.tar.gz: 0eb0a090760855586ec91029fe68e22cbfd0b292e9df233b1bf79770870fde7e
+SHA512:
+  metadata.gz: fd34dc317c92e5b4fdbbd550798f77ea2b733e54d00bf08ce1fe6480124601d343e1d879a3c67dcecb12fa95574aec4b50b8aa62608ce4740c02405f81060082
+  data.tar.gz: c0ccddf4643773ccec9a67f9b1e65fcbcd47233e1d8765665591aae246e38a88ffa8d93f58fe0d3efb444e9bdef5fa7342da21091616e43cd33f291808fac68e

data/bin/href_scraper

@@ -0,0 +1,2 @@
+#!/usr/bin/env ruby
+require 'href_scraper'

data/lib/href_scraper.rb

@@ -0,0 +1,25 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+require 'open-uri'
+require 'nokogiri'
+
+module HrefScraper
+  def self.fetch_html(url)
+    html = open(url)
+    Nokogiri::HTML(html)
+  end
+
+  OptionParser.new do |opt|
+    opt.on('-u', '--url URL', 'URL to scrape links from') do |url|
+      url !~ /^http/ && abort('Invalid URL passed')
+      anchors = fetch_html(url).xpath('//a')
+      hrefs = anchors.map { |tag| tag['href'] }
+      hrefs.each do |link|
+        if link =~ /^http/
+          puts link
+        end
+    end
+    end
+  end.parse!
+end

metadata

@@ -0,0 +1,81 @@
+--- !ruby/object:Gem::Specification
+name: href_scraper
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Caleb Lemoine
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-08-18 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: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.8.4
+description: Scrape hrefs from a single webpage
+email:
+- caleblemoine@gmail.com
+executables:
+- href_scraper
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/href_scraper
+- lib/href_scraper.rb
+homepage: https://github.com/circa10a/href-scraper.git
+licenses:
+- MIT
+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: 2.7.6
+signing_key: 
+specification_version: 4
+summary: CLI to scrape hrefs
+test_files: []