Table of Contents - apollo-crawler-0.1.31 Documentation
Classes and Modules
- Apollo
- Apollo::Agent
- Apollo::Agent::BaseAgent
- Apollo::Agent::CrawlerAgent
- Apollo::Agent::DomainerAgent
- Apollo::Agent::FetcherAgent
- Apollo::BaseProgram
- Apollo::Cache
- Apollo::Cache::BaseCache
- Apollo::Cache::CACHE_CLASS
- Apollo::Cache::Factory
- Apollo::Cache::MemcachedCache
- Apollo::Cache::MemoryCache
- Apollo::Cache::MongoCache
- Apollo::Cache::NullCache
- Apollo::Cache::SqliteCache
- Apollo::ConsoleProgram
- Apollo::Crawler
- Apollo::Crawler::BaseCrawler
- Apollo::Crawler::GoogleCrawler
- Apollo::Crawler::HackerNewsCrawler
- Apollo::Crawler::SlashdotCrawler
- Apollo::Crawler::SpiderCrawler
- Apollo::Crawler::StackoverflowCrawler
- Apollo::Crawler::XkcdCrawler
- Apollo::Crawler::YoujizzCrawler
- Apollo::CrawlerProgram
- Apollo::Fetcher
- Apollo::Fetcher::BaseFetcher
- Apollo::Fetcher::SimpleFetcher
- Apollo::Fetcher::SmartFetcher
- Apollo::Formatter
- Apollo::Formatter::BaseFormatter
- Apollo::Formatter::JsonFormatter
- Apollo::Formatter::PlainFormatter
- Apollo::Formatter::TableFormatter
- Apollo::Helper
- Apollo::Helper::Amqp
- Apollo::Helper::Core
- Apollo::Helper::Mongo
- Apollo::Logger
- Apollo::Logger::BaseLogger
- Apollo::Logger::ConsoleLogger
- Apollo::Model
- Apollo::Model::BaseModel
- Apollo::Model::Crawler
- Apollo::Model::DataChunk
- Apollo::Model::DataSource
- Apollo::Model::Domain
- Apollo::Model::QueuedUrl
- Apollo::Model::RawDocument
- Apollo::Model::User
- Apollo::Planner
- Apollo::Planner::BasePlanner
- Apollo::Planner::SmartPlanner
- Apollo::PlatformProgram
- Apollo::RbConfig
- Apollo::Scheduler
- Apollo::Scheduler::BaseScheduler
- Apollo::Store
- Apollo::Store::BaseStore
- Class
- String
Methods
- ::connect — Apollo::Helper::Amqp
- ::connect — Apollo::Helper::Mongo
- ::console_table — Apollo::CrawlerProgram
- ::construct — Apollo::Cache::Factory
- ::create_metadoc — Apollo::Crawler::BaseCrawler
- ::csv_bulk_insert — Apollo::Helper::Mongo
- ::declare_entities — Apollo::Agent
- ::declare_exchanges — Apollo::Agent
- ::declare_queues — Apollo::Agent
- ::fetch — Apollo::Crawler::BaseCrawler
- ::fetch — Apollo::Fetcher::BaseFetcher
- ::fetch — Apollo::Fetcher::SimpleFetcher
- ::fetch — Apollo::Fetcher::SmartFetcher
- ::fetch_old — Apollo::Fetcher::BaseFetcher
- ::format — Apollo::Formatter::JsonFormatter
- ::format — Apollo::Formatter::PlainFormatter
- ::format — Apollo::Formatter::TableFormatter
- ::get_classes — Apollo::Helper::Core
- ::get_config_path — Apollo::BaseProgram
- ::get_fake_headers — Apollo::Fetcher::BaseFetcher
- ::get_modules_paths — Apollo::CrawlerProgram
- ::log — Apollo::Logger::ConsoleLogger
- ::name_re — Apollo::Crawler::BaseCrawler
- ::name_re — Apollo::Formatter::BaseFormatter
- ::new — Apollo::Agent::CrawlerAgent
- ::new — Apollo::Agent::DomainerAgent
- ::new — Apollo::Agent::FetcherAgent
- ::new — Apollo::Cache::BaseCache
- ::new — Apollo::Cache::Factory
- ::new — Apollo::Cache::MemcachedCache
- ::new — Apollo::Cache::MemoryCache
- ::new — Apollo::Cache::MongoCache
- ::new — Apollo::Cache::MemcachedCache
- ::new — Apollo::Crawler::BaseCrawler
- ::new — Apollo::Planner::SmartPlanner
- ::new — Apollo::BaseProgram
- ::new — Apollo::ConsoleProgram
- ::new — Apollo::CrawlerProgram
- ::new — Apollo::PlatformProgram
- ::register_modules — Apollo::CrawlerProgram
- ::require_files — Apollo::BaseProgram
- ::schedule — Apollo::Scheduler::BaseScheduler
- ::try_get_doc — Apollo::Crawler::BaseCrawler
- ::try_get_url — Apollo::Crawler::BaseCrawler
- #at_exit_handler — Apollo::CrawlerProgram
- #construct — Apollo::Cache::Factory
- #enqueue_crawlers_urls — Apollo::PlatformProgram
- #enqueue_url — Apollo::Crawler::BaseCrawler
- #etl — Apollo::Crawler::BaseCrawler
- #extract_data — Apollo::Crawler::BaseCrawler
- #extract_data — Apollo::Crawler::GoogleCrawler
- #extract_data — Apollo::Crawler::HackerNewsCrawler
- #extract_data — Apollo::Crawler::SlashdotCrawler
- #extract_data — Apollo::Crawler::SpiderCrawler
- #extract_data — Apollo::Crawler::StackoverflowCrawler
- #extract_data — Apollo::Crawler::XkcdCrawler
- #extract_data — Apollo::Crawler::YoujizzCrawler
- #extract_links — Apollo::Crawler::BaseCrawler
- #extract_links — Apollo::Crawler::GoogleCrawler
- #extract_links — Apollo::Crawler::HackerNewsCrawler
- #extract_links — Apollo::Crawler::SlashdotCrawler
- #extract_links — Apollo::Crawler::SpiderCrawler
- #extract_links — Apollo::Crawler::StackoverflowCrawler
- #extract_links — Apollo::Crawler::XkcdCrawler
- #extract_links — Apollo::Crawler::YoujizzCrawler
- #fetch_document — Apollo::Crawler::BaseCrawler
- #fetch_queued_urls — Apollo::Planner::SmartPlanner
- #fetch_url — Apollo::Planner::SmartPlanner
- #format — Apollo::Formatter::JsonFormatter
- #format — Apollo::Formatter::PlainFormatter
- #format — Apollo::Formatter::TableFormatter
- #format_response_msg — Apollo::Agent::FetcherAgent
- #generate_crawler — Apollo::CrawlerProgram
- #get — Apollo::Cache::MemcachedCache
- #get — Apollo::Cache::MemoryCache
- #get — Apollo::Cache::MongoCache
- #get — Apollo::Cache::NullCache
- #get — Apollo::Cache::SqliteCache
- #get — Apollo::Cache::MemcachedCache
- #get_crawlers — Apollo::CrawlerProgram
- #get_crawlers_by_name — Apollo::CrawlerProgram
- #get_next_url — Apollo::Planner::SmartPlanner
- #get_url_count — Apollo::Planner::SmartPlanner
- #init_additional_crawlers — Apollo::CrawlerProgram
- #init_agents — Apollo::PlatformProgram
- #init_amqp — Apollo::BaseProgram
- #init_crawlers — Apollo::PlatformProgram
- #init_domainers — Apollo::PlatformProgram
- #init_domains — Apollo::PlatformProgram
- #init_fetchers — Apollo::PlatformProgram
- #init_mongo — Apollo::BaseProgram
- #init_options — Apollo::BaseProgram
- #init_options — Apollo::ConsoleProgram
- #init_options — Apollo::CrawlerProgram
- #init_options — Apollo::PlatformProgram
- #init_options_parser — Apollo::ConsoleProgram
- #init_options_parser — Apollo::CrawlerProgram
- #init_program — Apollo::BaseProgram
- #init_program — Apollo::ConsoleProgram
- #init_program — Apollo::CrawlerProgram
- #init_program — Apollo::PlatformProgram
- #init_program_directory — Apollo::CrawlerProgram
- #init_seeds — Apollo::BaseProgram
- #init_seeds_crawlers — Apollo::BaseProgram
- #init_user_config_file — Apollo::CrawlerProgram
- #initilize — Apollo::Cache::NullCache
- #initilize — Apollo::Cache::SqliteCache
- #load_config — Apollo::BaseProgram
- #load_config_file — Apollo::BaseProgram
- #load_config_file — Apollo::CrawlerProgram
- #load_configs — Apollo::BaseProgram
- #log — Apollo::Logger::ConsoleLogger
- #name — Apollo::Crawler::BaseCrawler
- #name — Apollo::Crawler::GoogleCrawler
- #name — Apollo::Crawler::HackerNewsCrawler
- #name — Apollo::Crawler::SlashdotCrawler
- #name — Apollo::Crawler::SpiderCrawler
- #name — Apollo::Crawler::StackoverflowCrawler
- #name — Apollo::Crawler::XkcdCrawler
- #name — Apollo::Crawler::YoujizzCrawler
- #name — Apollo::Formatter::JsonFormatter
- #name — Apollo::Formatter::PlainFormatter
- #name — Apollo::Formatter::TableFormatter
- #parse_options — Apollo::BaseProgram
- #parse_options — Apollo::ConsoleProgram
- #parse_options — Apollo::CrawlerProgram
- #process_docs_handler — Apollo::CrawlerProgram
- #process_fetched_doc — Apollo::Agent::FetcherAgent
- #process_options — Apollo::BaseProgram
- #process_options — Apollo::ConsoleProgram
- #process_options — Apollo::CrawlerProgram
- #process_options — Apollo::PlatformProgram
- #process_url — Apollo::Crawler::BaseCrawler
- #remove — Apollo::Cache::BaseCache
- #request_exit — Apollo::BaseProgram
- #request_exit — Apollo::ConsoleProgram
- #request_exit — Apollo::CrawlerProgram
- #requeue_fetching_urls — Apollo::PlatformProgram
- #run — Apollo::Agent::BaseAgent
- #run — Apollo::Planner::BasePlanner
- #run — Apollo::Planner::SmartPlanner
- #run — Apollo::BaseProgram
- #run — Apollo::ConsoleProgram
- #run — Apollo::CrawlerProgram
- #run — Apollo::PlatformProgram
- #run_crawlers — Apollo::CrawlerProgram
- #run_query — Apollo::CrawlerProgram
- #send_response_msg — Apollo::Agent::FetcherAgent
- #set — Apollo::Cache::BaseCache
- #set — Apollo::Cache::MemcachedCache
- #set — Apollo::Cache::MemoryCache
- #set — Apollo::Cache::MongoCache
- #set — Apollo::Cache::NullCache
- #set — Apollo::Cache::SqliteCache
- #set — Apollo::Cache::MemcachedCache
- #subclasses — Class
- #to_class — String
- #try_get — Apollo::Cache::BaseCache
- #try_get — Apollo::Cache::MemcachedCache
- #try_get — Apollo::Cache::MemoryCache
- #try_get — Apollo::Cache::MongoCache
- #try_get — Apollo::Cache::NullCache
- #try_get — Apollo::Cache::SqliteCache
- #try_get — Apollo::Cache::MemcachedCache
- #url — Apollo::Crawler::BaseCrawler
- #url — Apollo::Crawler::GoogleCrawler
- #url — Apollo::Crawler::HackerNewsCrawler
- #url — Apollo::Crawler::SlashdotCrawler
- #url — Apollo::Crawler::SpiderCrawler
- #url — Apollo::Crawler::StackoverflowCrawler
- #url — Apollo::Crawler::XkcdCrawler
- #url — Apollo::Crawler::YoujizzCrawler
- #url_processed? — Apollo::Crawler::BaseCrawler