1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
|
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
import feedparser, datetime, xml.etree.ElementTree, re
def getNewAlerts(rssaddress, lastchecktimestamp):
print "RSSCheckerImpl.getNewAlerts() called", rssaddress, lastchecktimestamp
#Get and parse the RSS/Atom data
d = feedparser.parse(rssaddress)
newalertsxml = "<alerts xmlns=\"http://tuscany.apache.org/samples/alerter\">\n"
lastcheckdate = datetime.datetime.min
if lastchecktimestamp:
lastcheckdate = datetime.datetime.strptime(lastchecktimestamp, "%Y-%m-%dT%H:%M:%S")
defaultTitle = d.feed.get('title', 'RSS feed article')
defaultLink = d.feed.get('link', 'http://incubator.apache.org/tuscany')
defaultSummary = 'No information provided'
for entry in d.entries:
if entry.has_key('date'):
(year, month, day, hour, minute, second, millisecond, microsecond, tzinfo) = entry.date_parsed
entrydate = datetime.datetime(year, month, day, hour, minute, second)
else:
entrydate = datetime.datetime.now()
if (entrydate > lastcheckdate) :
newalertsxml += "<alert><title>" + stripXML(entry.get('title', defaultTitle)) + "</title>\n"
newalertsxml += "<address>" + entry.get('link', defaultLink) + "</address>\n"
newalertsxml += "<date>" + entrydate.isoformat() + "</date>\n"
newalertsxml += "<summary>" + stripXML(entry.get('description', defaultSummary)) + "</summary></alert>\n"
newalertsxml += "</alerts>"
return xml.etree.ElementTree.XML(newalertsxml)
def stripXML(data):
elementsRemoved = re.sub("<.*?>","", data)
entitiesRemoved = re.sub("&.*?;", " ", elementsRemoved)
asciiEncoded = entitiesRemoved.encode('ASCII', 'replace')
returnData = asciiEncoded.replace('&', 'and')
return returnData
# Testing
# print xml.etree.ElementTree.tostring(getNewAlerts("http://www.engadget.com/rss.xml", "2007-02-07T17:11:14"))
#
#
# today = datetime.datetime.now().replace(hour=0, minute=0, second=0, microsecond=0)
# data2 = getNewAlerts("http://newsrss.bbc.co.uk/rss/newsonline_uk_edition/front_page/rss.xml", today.isoformat())
# print xml.etree.ElementTree.tostring(data2)
#
# print "1st call returned", len(data.findall("./{http://tuscany.apache.org/samples/alerter}alert")), "elements"
# print "2nd call returned", len(data2.findall("./{http://tuscany.apache.org/samples/alerter}alert")), "elements"
|
