"""
$Id: observer.py,v 1.3 2002/07/17 08:15:51 niko_schmuck Exp $
test the observer while new items pop up over a period
"""
from java.lang import Thread
from java.net import URL
from de.nava.informa.impl.basic import ChannelBuilder
from de.nava.informa.utils import ChannelRegistry
from de.nava.informa.utils import SimpleChannelObserver
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# register channels (which should be updated every 15-35 minutes)
c = {}
c[1] = reg.addChannel(URL("http://www.newsforge.com/newsforge.rss"), 15 * 60,
1)
c[2] = reg.addChannel(URL("http://slashdot.org/slashdot.rdf"), 20 * 60, 1)
c[3] = reg.addChannel(URL("http://www.heise.de/newsticker/heise.rdf"), 25 * 60,
1)
c[4] = reg.addChannel(URL("http://xmlhack.com/rss10.php"), 30 * 60, 1)
c[5] = reg.addChannel(URL("http://freshmeat.net/backend/fm.rdf"), 35 * 60, 1)
# create a simple observer which watches out for new items
o = SimpleChannelObserver()
for idx in c.keys():
c[idx].addObserver(o)
# sleep 4 hours (let the updating threads work)
chl_urls = [["http://www.newsforge.com/newsforge.rss", 15*60],
["http://slashdot.org/slashdot.rdf", 20*60],
["http://www.heise.de/newsticker/heise.rdf", 25*60],
["http://xmlhack.com/rss10.php", 30*60],
["http://freshmeat.net/backend/fm.rdf", 35*60]]
else:
data_dir = "file://" + System.getProperty("user.dir") + "/data/"
chl_urls = [[data_dir + "linuxjournal.rss", 1*60],
[data_dir + "salon_use.rdf", 2*60],
[data_dir + "heise.rdf", 3*60],
[data_dir + "slashdot.rdf", 4*60],
[data_dir + "xmlhack-1.0.xml", 5*60]]
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# add channels to registry and populate news items
observer = SimpleChannelObserver()
for chl_url in chl_urls:
c = reg.addChannel(URL(chl_url[0]), chl_url[1], 1)
c.addObserver(observer)
# finally show the whole thing
main_frame = MainFrame(reg.getChannels())
main_frame.pack()
main_frame.setVisible(1)
# autosave task
t = AutosaveThread(reg)
t.start()
from java.lang import Thread
from java.net import URL
from java.util import Date
from de.nava.informa.impl.basic import ChannelBuilder
from de.nava.informa.utils import ChannelRegistry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# url_xmlhack = "http://xmlhack.com/rss10.php"
# url_xmlhack = URL("http://localhost/rss/xmlhack-1.0.xml")
url_xmlhack = URL("http://localhost/rss/xmlhack-0.91.xml")
# update channel which should be updated every 30 seconds
reg.addChannel(url_xmlhack, 30, 1)
print "first time parsed in at ", Date()
for channel in reg.getChannels():
print "channel:", channel
for item in channel.getItems():
print " -", item
# sleep 100 seconds
Thread.currentThread().sleep(100 * 1000)
print "--- after updating"
for channel in reg.getChannels():
print "channel:", channel
for item in channel.getItems():
print " -", item
# offically deregister
# reg.removeChannel(channel)
chl_urls = [["http://www.newsforge.com/newsforge.rss", 15 * 60],
["http://slashdot.org/slashdot.rdf", 20 * 60],
["http://www.heise.de/newsticker/heise.rdf", 25 * 60],
["http://xmlhack.com/rss10.php", 30 * 60],
["http://freshmeat.net/backend/fm.rdf", 35 * 60]]
else:
data_dir = "file://" + System.getProperty("user.dir") + "/data/"
chl_urls = [[data_dir + "linuxjournal.rss", 1 * 60],
[data_dir + "salon_use.rdf", 2 * 60],
[data_dir + "heise.rdf", 3 * 60],
[data_dir + "slashdot.rdf", 4 * 60],
[data_dir + "xmlhack-1.0.xml", 5 * 60]]
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# add channels to registry and populate news items
observer = SimpleChannelObserver()
for chl_url in chl_urls:
c = reg.addChannel(URL(chl_url[0]), chl_url[1], 1)
c.addObserver(observer)
# finally show the whole thing
main_frame = MainFrame(reg.getChannels())
main_frame.pack()
main_frame.setVisible(1)
# autosave task
t = AutosaveThread(reg)
t.start()
"""
$Id: observer.py,v 1.3 2002/07/17 08:15:51 niko_schmuck Exp $
test the observer while new items pop up over a period
"""
from java.lang import Thread
from java.net import URL
from de.nava.informa.impl.basic import ChannelBuilder
from de.nava.informa.utils import ChannelRegistry
from de.nava.informa.utils import SimpleChannelObserver
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# register channels (which should be updated every 15-35 minutes)
c = {}
c[1]=reg.addChannel(URL("http://www.newsforge.com/newsforge.rss"), 15*60, 1);
c[2]=reg.addChannel(URL("http://slashdot.org/slashdot.rdf"), 20*60, 1);
c[3]=reg.addChannel(URL("http://www.heise.de/newsticker/heise.rdf"), 25*60, 1);
c[4]=reg.addChannel(URL("http://xmlhack.com/rss10.php"), 30*60, 1)
c[5]=reg.addChannel(URL("http://freshmeat.net/backend/fm.rdf"), 35*60, 1);
# create a simple observer which watches out for new items
o = SimpleChannelObserver()
for idx in c.keys():
c[idx].addObserver(o)
# sleep 4 hours (let the updating threads work)
Thread.currentThread().sleep(4 * 60 * 60 * 1000)
# create an index for the lucene engine to perform search queries with.
from java.io import File
from java.util import Date
from de.nava.informa.impl.basic import ChannelBuilder
from de.nava.informa.utils import ChannelRegistry
from de.nava.informa.search import ItemDocument
from org.apache.lucene.analysis.standard import StandardAnalyzer
from org.apache.lucene.index import IndexWriter
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# register some channels
chfiles = ('data/heise.rdf',
'data/slashdot.rdf',
'data/xmlhack-0.91.xml',
'data/xmlhack-1.0.xml')
for filename in chfiles:
reg.addChannel(File(filename).toURL(), 60, 0)
# create (3rd arg) index writer in directory (first arg)
start_time = Date()
writer = IndexWriter("index", StandardAnalyzer(), 1)
# loop over all channels and their items
for channel in reg.getChannels():
# create an index for the lucene engine to perform search queries with.
from java.io import File
from java.util import Date
from de.nava.informa.impl.basic import ChannelBuilder
from de.nava.informa.utils import ChannelRegistry
from de.nava.informa.search import ItemDocument
from org.apache.lucene.analysis.standard import StandardAnalyzer
from org.apache.lucene.index import IndexWriter
# create channel registry
builder = ChannelBuilder()
reg = ChannelRegistry(builder)
# register some channels
chfiles = ('data/heise.rdf',
'data/slashdot.rdf',
'data/xmlhack-0.91.xml',
'data/xmlhack-1.0.xml')
for filename in chfiles:
reg.addChannel(File(filename).toURL(), 60, 0)
# create (3rd arg) index writer in directory (first arg)
start_time = Date()
writer = IndexWriter("index", StandardAnalyzer(), 1)
# loop over all channels and their items
for channel in reg.getChannels():
