module NewsCrawler::Storage::RawData

store raw data from website

Public Class Methods

add(url, body) click to toggle source

Add entry to raw data collection @param [ String ] url @param [ String ] body

# File lib/news_crawler/storage/raw_data.rb, line 52
def add(url, body)
  @engine.add(url, body)
end
clear() click to toggle source
# File lib/news_crawler/storage/raw_data.rb, line 67
def clear
  @engine.clear
end
count() click to toggle source
# File lib/news_crawler/storage/raw_data.rb, line 63
def count
  @engine.count
end
find_by_url(url) click to toggle source

Find document with correspond url @param [ String ] url @return [ String, nil ]

# File lib/news_crawler/storage/raw_data.rb, line 59
def find_by_url(url)
  @engine.find_by_url url
end
set_engine(engine, *opts) click to toggle source

Set RawData storage engine @param [ Symbol, Object ] engine specify database engine, pass an object for custom engine @param [ Hash ] opts options pass to engine

This can be
* `:mongo`, `:mongodb` for MongoDB backend
# File lib/news_crawler/storage/raw_data.rb, line 37
def set_engine(engine, *opts)
  if engine.respond_to? :intern
    engine = engine.intern
  end
  engine_class = RawDataEngine.get_engines[engine]
  if engine_class
    @engine = engine_class.new(*opts)
  else
    @engine = engine
  end
end