Method List
-
#add NewsCrawler::Storage::RawData::MongoStorage
-
#add NewsCrawler::Storage::RawData::RawDataEngine
-
add NewsCrawler::Storage::RawData
-
#add NewsCrawler::Storage::URLQueue::MongoEngine
-
add NewsCrawler::Storage::URLQueue
-
#add NewsCrawler::Storage::URLQueue::URLQueueEngine
-
all NewsCrawler::Storage::URLQueue
-
#all NewsCrawler::Storage::URLQueue::MongoEngine
-
#all NewsCrawler::Storage::URLQueue::URLQueueEngine
-
clear NewsCrawler::Storage::URLQueue
-
#clear NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#clear NewsCrawler::Storage::RawData::RawDataEngine
-
#clear NewsCrawler::Storage::URLQueue::MongoEngine
-
#clear NewsCrawler::Storage::RawData::MongoStorage
-
clear NewsCrawler::Storage::RawData
-
#count NewsCrawler::Storage::RawData::MongoStorage
-
#count NewsCrawler::Storage::RawData::RawDataEngine
-
count NewsCrawler::Storage::RawData
-
exclude? NewsCrawler::LinkSelector::SameDomainSelector
-
#extract_url NewsCrawler::LinkSelector::SameDomainSelector
-
#find_all NewsCrawler::CrawlerModule
-
#find_all NewsCrawler::Storage::URLQueue::MongoEngine
-
#find_all NewsCrawler::Storage::URLQueue::URLQueueEngine
-
find_all NewsCrawler::Storage::URLQueue
-
find_by_url NewsCrawler::Storage::RawData
-
#find_by_url NewsCrawler::Storage::RawData::RawDataEngine
-
#find_by_url NewsCrawler::Storage::RawData::MongoStorage
-
#find_one NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#find_one NewsCrawler::Storage::URLQueue::MongoEngine
-
#find_one NewsCrawler::CrawlerModule
-
find_one NewsCrawler::Storage::URLQueue
-
#find_unprocessed NewsCrawler::CrawlerModule
-
#find_unvisited NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#find_unvisited NewsCrawler::Storage::URLQueue::MongoEngine
-
find_unvisited NewsCrawler::Storage::URLQueue
-
get_engines NewsCrawler::Storage::URLQueue::URLQueueEngine
-
get_engines NewsCrawler::Storage::RawData::RawDataEngine
-
get_logger NewsCrawler::NCLogger
-
#get_url_depth NewsCrawler::Storage::URLQueue::MongoEngine
-
#get_url_path NewsCrawler::URLHelper
-
#graceful_terminate NewsCrawler::LinkSelector::SameDomainSelector
-
#graceful_terminate NewsCrawler::Downloader
-
inherited NewsCrawler::Storage::RawData::RawDataEngine
-
inherited NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#initialize Robots
-
#initialize NewsCrawler::Storage::RawData::MongoStorage
-
#initialize NewsCrawler::LinkSelector::SameDomainSelector
-
#initialize NewsCrawler::Downloader
-
#initialize NewsCrawler::Storage::URLQueue::MongoEngine
-
load_application_config NewsCrawler::CrawlerConfig
-
load_samedomainselector_config NewsCrawler::CrawlerConfig
-
#mark NewsCrawler::Storage::URLQueue::URLQueueEngine
-
mark NewsCrawler::Storage::URLQueue
-
#mark NewsCrawler::Storage::URLQueue::MongoEngine
-
mark_all NewsCrawler::Storage::URLQueue
-
#mark_all NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#mark_all NewsCrawler::Storage::URLQueue::MongoEngine
-
mark_all_unvisited NewsCrawler::Storage::URLQueue
-
#mark_all_unvisited NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#mark_all_unvisited NewsCrawler::Storage::URLQueue::MongoEngine
-
#mark_processed NewsCrawler::CrawlerModule
-
#mark_unprocessed NewsCrawler::CrawlerModule
-
mark_visited NewsCrawler::Storage::URLQueue
-
#mark_visited NewsCrawler::Storage::URLQueue::URLQueueEngine
-
#mark_visited NewsCrawler::Storage::URLQueue::MongoEngine
-
#next_unprocessed NewsCrawler::Storage::URLQueue::MongoEngine
-
next_unprocessed NewsCrawler::Storage::URLQueue
-
#next_unprocessed NewsCrawler::CrawlerModule
-
#next_unprocessed NewsCrawler::Storage::URLQueue::URLQueueEngine
-
normalize_url NewsCrawler::Storage::URLQueue
-
#run NewsCrawler::LinkSelector::SameDomainSelector
-
#run NewsCrawler::Downloader
-
#same_domain? NewsCrawler::URLHelper
-
set_engine NewsCrawler::Storage::URLQueue
-
set_engine NewsCrawler::Storage::RawData
-
set_level NewsCrawler::NCLogger
-
set_logdev NewsCrawler::NCLogger
-
#user_agent Robots