# the fetcher is ignored, but since we must instantiate something, an HTMLFetcher is used
fetcher.class = edu.uiuc.ncsa.datastream.util.fetch.fetcher.HTMLFetcher
# non-realtime, because we're performing a Twitter search
fetcher.realtime = false
# wait 5 minutes between fetches (Twitter is rate-limited)
fetcher.delay = 300000
parser.class = edu.uiuc.ncsa.datastream.util.fetch.dataparser.TwitterParser
# the following four parameters are OAuth authentication parameters
# the example values are not valid; do not attempt to authenticate with them
parser.twitter.key = qeS5HHN1s69Xrz2SqtJISQ
parser.twitter.secret = sXcEHIlzMqDSsfRrUNe8D4bGOObxsqidmknpmBn8I
parser.twitter.token = 61353510-9TUfOSHMdQWSklTzpV23kCqrnK23ev2WdFzlvNP1F
parser.twitter.tokenSecret = nHyQR6Mi5zZvgptZOPDr0JjqGnoASbvyW5wAa5bKBE
# the next few parameters specify a query against Twitter's query API
# for documentation on query syntax see http://search.twitter.com/api/
# this is the query itself. "car" means search for tweets containing the word "car"
parser.twitter.query = car
# here we specify a geographic centroid
parser.twitter.lat = 40.116349
parser.twitter.lon = -88.239183
# and a radius
parser.twitter.radius = 30
# in miles. this is the geographic region in which to search
parser.twitter.distanceUnits = miles
# the date extractor is ignored; the twitter4j API performs date extraction for us
date.extractor.class = edu.uiuc.ncsa.datastream.util.fetch.dateparser.SimpleDateExtractor
# here we're putting all search results into a single stream
stream.assigner.class = edu.uiuc.ncsa.datastream.util.fetch.ConstantStreamAssigner
# the URI of the stream. this can be any valid URI
stream.assigner.constant.stream = urn:streams/snorb7/twitter
# TypeRegisterFilter allows us to associate a content type with token data
onetimefilter.class = edu.uiuc.ncsa.datastream.util.fetch.filter.TypeRegisterFilter
# in this case tweets are of type text/plain
filter.typeregister.mime = text/plain |