title_grabber 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 96fbc07b812b570e0827c2d6b7b2d18f7b9ad0b4a172b69606648bb21d7e41b6
+  data.tar.gz: 72c04ad3f1149e44bc0a16a8e7d6c0c5d13be794e026c3748415f96197c5d146
+SHA512:
+  metadata.gz: c88bdf88fe2dd0bce4bde4ad97d5432e7d5433a4a581372c938500fa7323d0020437c5326e19e3f7248cebe02123c93dfd00cb498669ae363a33d2267f28f90f
+  data.tar.gz: f9901cb587973ed762a2ad100e9410819a36dfe34e61c54daac78ad6ff72284faeddcd1f8f27594c25467622e3882670473931367d43efa68a026e7151f2bba8

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+bin/console
+bin/setup
+*.csv

data/.ruby-version

@@ -0,0 +1 @@
+2.6.2

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 title_grabber.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,49 @@
+PATH
+  remote: .
+  specs:
+    title_grabber (0.2.0)
+      http (~> 4.1)
+      oga (~> 2.15)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.6.0)
+      public_suffix (>= 2.0.2, < 4.0)
+    ansi (1.5.0)
+    ast (2.4.0)
+    domain_name (0.5.20180417)
+      unf (>= 0.0.5, < 1.0.0)
+    http (4.1.1)
+      addressable (~> 2.3)
+      http-cookie (~> 1.0)
+      http-form_data (~> 2.0)
+      http_parser.rb (~> 0.6.0)
+    http-cookie (1.0.3)
+      domain_name (~> 0.5)
+    http-form_data (2.1.1)
+    http_parser.rb (0.6.0)
+    minitest (5.11.3)
+    oga (2.15)
+      ast
+      ruby-ll (~> 2.1)
+    public_suffix (3.0.3)
+    rake (10.5.0)
+    ruby-ll (2.1.2)
+      ansi
+      ast
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.5)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.17)
+  minitest (~> 5.0)
+  rake (~> 10.0)
+  title_grabber!
+
+BUNDLED WITH
+   1.17.2

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 Cristian Rasch
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,48 @@
+# TitleGrabber
+
+Grab page & article titles from lists of URLs contained in files passed in as arguments
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'title_grabber'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install title_grabber
+
+## Usage
+
+Just pass it a list of files containing URLs (one per line)
+
+```
+title-grabber /abs/path/2/file1.txt rel/path/2/file2.txt
+```
+
+Data is either recorded to out.csv in the CWD or the file specified using the
+-o/--output argument, e.g.
+
+```
+title-grabber -o ~/output.csv /abs/path/2/file1.txt rel/path/2/file2.txt
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. 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/cristian-rasch/title_grabber.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task :default => :test

data/exe/title-grabber

@@ -0,0 +1,25 @@
+#!/usr/bin/env ruby
+
+require "optparse"
+require "pathname"
+
+require_relative '../lib/title_grabber'
+
+script_path = Pathname(__FILE__)
+def_out_path = Pathname('out.csv')
+
+arguments = { output: def_out_path }
+OptionParser.new do |args|
+  args.banner = "Usage: #{script_path.basename} [options]"
+
+  args.on("-o", "--output FILE", "Output file (defaults to #{def_out_path.basename})") do |out|
+    arguments[:output] = Pathname(out)
+  end
+end.parse!
+
+if ARGV.empty?
+  print "At least 1 input file is required!\n"
+  exit(1)
+else
+  TitleGrabber.call(ARGF, arguments)
+end

data/lib/http_helper.rb

@@ -0,0 +1,66 @@
+require "logger"
+
+require "http"
+
+require_relative "text_helper"
+
+module HTTPHelper
+  WRITE_TO = Integer(ENV.fetch("WRITE_TIMEOUT", 5))
+  CONN_TO = Integer(ENV.fetch("CONNECT_TIMEOUT", 10))
+  READ_TO = Integer(ENV.fetch("READ_TIMEOUT", 15))
+  MAX_HOPS = 5
+  MAX_RETRIES = 3
+  INVALID_BYTE_SEQ = "invalid byte sequence".freeze
+  CONNECTION_ERRORS = ["SSL_connect", "Connection reset"].freeze
+
+  include TextHelper
+
+  def open_w_timeout(url, write_to: WRITE_TO, connect_to: CONN_TO,
+                          read_to: READ_TO)
+    logger.info "GET #{url}"
+    retries = 0
+
+    begin
+      body = Timeout.timeout(read_to) {
+               HTTP.timeout(write: write_to, connect: connect_to, read: read_to).
+                    follow(max_hops: MAX_HOPS).
+                    get(url, ssl_context: ssl_ctx).
+                    to_s
+             }
+    rescue HTTP::Error, Timeout::Error => err
+      msg = err.message
+
+      if err.kind_of?(HTTP::Error) || err.kind_of?(Timeout::Error) ||
+           CONNECTION_ERRORS.any? { |e| msg.start_with?(e) }
+        retries += 1
+
+        if retries <= MAX_RETRIES
+          logger.warn "URL: #{url} [#{msg}] - Retry ##{retries}"
+          retry
+        else
+          logger.error "URL: #{url} [#{msg}]"
+          nil
+        end
+      end
+    rescue => err
+      logger.error "URL: #{url} [#{err.message}]"
+      nil
+    else
+      utf8_encode(body)
+    end
+  end
+
+  private
+
+  def logger
+    @logger ||= Logger.new(STDOUT)
+  end
+
+  def ssl_ctx
+    @ssl_ctx ||= begin
+                  ctx = OpenSSL::SSL::SSLContext.new
+                  ctx.verify_mode = OpenSSL::SSL::VERIFY_NONE
+                  ctx
+                  end
+  end
+end

data/lib/text_helper.rb

@@ -0,0 +1,18 @@
+module TextHelper
+  def utf8_encode(text = nil)
+    begin
+      String(text).encode(-"UTF-8", invalid: :replace, undef: :replace,
+                                    replace: -"")
+    rescue EncodingError
+      -""
+    end
+  end
+
+  # document.querySelector('title').textContent.trim().replace(/\n/g, ' ').replace(/\s{2,}/g, ' ')
+  def clean_up_whitespace(text)
+    text.strip!
+    text.gsub!("\n", " ")
+    text.gsub(/\s{2,}/, ' ')
+    text
+  end
+end

data/lib/title_grabber/version.rb

@@ -0,0 +1,3 @@
+module TitleGrabber
+  VERSION = "0.2.0"
+end

data/lib/title_grabber.rb

@@ -0,0 +1,95 @@
+require "csv"
+require "etc"
+require "fileutils"
+
+require "bundler/setup"
+require "oga"
+
+require_relative "title_grabber/version"
+require_relative "http_helper"
+require_relative "text_helper"
+
+module TitleGrabber
+  class Error < StandardError; end
+
+  URL_RE = %r(https?://\S+)i
+  URL_HEADER = -"url"
+  PAGE_TIT_HEAD = -"page_title"
+  ART_TIT_HEAD = -"article_title"
+  HEADERS = [URL_HEADER, PAGE_TIT_HEAD, ART_TIT_HEAD].freeze
+
+  class << self
+    include HTTPHelper
+    include TextHelper
+
+    def call(lines, options)
+      tmp_path = nil
+      processed_urls = if (out_path = options[:output]).exist?
+                         tmp_path = out_path.sub_ext(".tmp#{out_path.extname}")
+                         FileUtils.cp(out_path, tmp_path)
+                         arr_of_h = CSV.read(tmp_path, headers: true)
+                         arr_of_h.each_with_object({}) { |r, h|
+                           page_tit = r[PAGE_TIT_HEAD]
+                           art_tit = r[ART_TIT_HEAD]
+
+                           unless page_tit.empty? && art_tit.empty?
+                             h[r[URL_HEADER]] = { PAGE_TIT_HEAD => page_tit,
+                                                  ART_TIT_HEAD => art_tit }
+                           end
+                         }.tap do
+                           arr_of_h = nil
+                         end
+                       else
+                         {}
+                       end
+
+      queue = Queue.new
+
+      CSV.open(options[:output], "w", force_quotes: true) do |csv|
+        csv << HEADERS
+
+        lines.each do |line|
+          md = line.match(URL_RE)
+          next unless md
+
+          url = md.to_s
+          if h = processed_urls[url]
+            csv << [url, h[PAGE_TIT_HEAD], h[ART_TIT_HEAD]]
+            next
+          end
+
+          queue << url
+        end
+        lines = nil
+
+        thr_cnt = [Etc.nprocessors * 2, queue.size].min
+        threads = 1.upto(thr_cnt).map {
+          Thread.new do
+            url = begin
+                    queue.pop(true)
+                  rescue ThreadError; end
+
+            while url
+              if html = open_w_timeout(url)
+                doc = Oga.parse_html(html)
+                page_title = doc.at_css('title')&.text || -""
+                clean_up_whitespace(page_title) unless page_title.empty?
+                article_title = doc.at_css('article h1')&.text
+                article_title ||= doc.at_css('h1')&.text || -""
+                clean_up_whitespace(article_title) unless article_title.empty?
+
+                csv << [url, page_title, article_title]
+              end
+
+              url = begin
+                      queue.pop(true)
+                    rescue ThreadError; end
+            end
+          end
+        }.each(&:join)
+      end
+
+      tmp_path&.unlink
+    end
+  end
+end

data/title_grabber.gemspec

@@ -0,0 +1,45 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "title_grabber/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "title_grabber"
+  spec.version       = TitleGrabber::VERSION
+  spec.authors       = ["Cristian Rasch"]
+  spec.email         = ["cristianrasch@fastmail.fm"]
+
+  spec.summary       = %q{Grabs page & article titles from lists of URLs contained in files passed in as arguments}
+  # spec.description   = %q{TODO: Write a longer description or delete this line.}
+  spec.homepage      = "https://bitbucket.org/cristian-rasch/title_grabber"
+  spec.license       = "MIT"
+
+  # 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'"
+
+    spec.metadata["homepage_uri"] = spec.homepage
+    spec.metadata["source_code_uri"] = "https://bitbucket.org/cristian-rasch/title_grabber/src/master/"
+    # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
+  else
+    raise "RubyGems 2.0 or newer is required to protect against " \
+      "public gem pushes."
+  end
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |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_runtime_dependency "http", "~> 4.1"
+  spec.add_runtime_dependency "oga", "~> 2.15"
+
+  spec.add_development_dependency "bundler", "~> 1.17"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "minitest", "~> 5.0"
+end

metadata

@@ -0,0 +1,130 @@
+--- !ruby/object:Gem::Specification
+name: title_grabber
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Cristian Rasch
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-04-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: http
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.1'
+- !ruby/object:Gem::Dependency
+  name: oga
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.15'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.15'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+description: 
+email:
+- cristianrasch@fastmail.fm
+executables:
+- title-grabber
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".ruby-version"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- exe/title-grabber
+- lib/http_helper.rb
+- lib/text_helper.rb
+- lib/title_grabber.rb
+- lib/title_grabber/version.rb
+- title_grabber.gemspec
+homepage: https://bitbucket.org/cristian-rasch/title_grabber
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://bitbucket.org/cristian-rasch/title_grabber
+  source_code_uri: https://bitbucket.org/cristian-rasch/title_grabber/src/master/
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Grabs page & article titles from lists of URLs contained in files passed
+  in as arguments
+test_files: []