Module: Elasticrawl

Defined in:

lib/elasticrawl.rb,
lib/elasticrawl/job.rb,
lib/elasticrawl/crawl.rb,
lib/elasticrawl/error.rb,
lib/elasticrawl/config.rb,
lib/elasticrawl/cluster.rb,
lib/elasticrawl/version.rb,
lib/elasticrawl/job_step.rb,
lib/elasticrawl/parse_job.rb,
lib/elasticrawl/combine_job.rb,
lib/elasticrawl/crawl_segment.rb

Defined Under Namespace

Classes: AWSCredentialsInvalidError, Cluster, CombineJob, Config, ConfigDirMissingError, Crawl, CrawlSegment, DatabaseAccessError, ElasticMapReduceAccessError, Error, FileAccessError, Job, JobStep, ParseJob, S3AccessError

Constant Summary

COMMON_CRAWL_BUCKET =

S3 locations

'commoncrawl'

COMMON_CRAWL_PATH =

'crawl-data'

SEGMENTS_PATH =

'segments'

WARC_PATHS =

'warc.paths.gz'

MAX_SEGMENTS =

256

VERSION =

'1.1.7'