Method: Cobweb#start

Defined in:
lib/cobweb.rb

#start(base_url) ⇒ Object

This method starts the resque based crawl and enqueues the base_url



70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# File 'lib/cobweb.rb', line 70

def start(base_url)
  raise ":base_url is required" unless base_url
  request = {
    :crawl_id => Digest::SHA1.hexdigest("#{Time.now.to_i}.#{Time.now.usec}"),
    :url => base_url
  }

  if @options[:internal_urls].nil? || @options[:internal_urls].empty?
    uri = Addressable::URI.parse(base_url)
    @options[:internal_urls] = []

    if @options[:treat_https_as_http_to]
      @options[:internal_urls] << ["http://", uri.host, "/*"].join
      @options[:internal_urls] << ["http://", uri.host, ":", uri.inferred_port, "/*"].join
      @options[:internal_urls] << ["https://", uri.host, "/*"].join
      @options[:internal_urls] << ["https://", uri.host, ":", uri.inferred_port, "/*"].join
    else
      @options[:internal_urls] << [uri.scheme, "://", uri.host, "/*"].join
      @options[:internal_urls] << [uri.scheme, "://", uri.host, ":", uri.inferred_port, "/*"].join
    end

  end

  request.merge!(@options)
  @redis = Redis::Namespace.new("cobweb-#{Cobweb.version}-#{request[:crawl_id]}", :redis => RedisConnection.new(request[:redis_options]))
  @redis.set("original_base_url", base_url)
  @redis.hset "statistics", "queued_at", DateTime.now
  @redis.set("crawl-counter", 0)
  queue_counter = @options[:seed_urls].count + 1
  puts "queue_counter being init to #{queue_counter}"
  @redis.set("queue-counter", queue_counter)


  @options[:seed_urls].map{|link| @redis.sadd "queued", link }

  @stats = Stats.new(request)
  @stats.start_crawl(request)

  # add internal_urls into redis
  @options[:internal_urls].map{|url| @redis.sadd("internal_urls", url)}
  if @options[:queue_system] == :resque
    Resque.enqueue(CrawlJob, request)
  elsif @options[:queue_system] == :sidekiq
    CrawlWorker.perform_async(request)
    @options[:seed_urls].map{|url| 
      new_request = request.clone
      new_request[:url] = url
      CrawlWorker.perform_async(new_request)
    }

  else
    raise "Unknown queue system: #{content_request[:queue_system]}"
  end

  request
end