[120] | 1 | #Licensed to the Apache Software Foundation (ASF) under one |
---|
| 2 | #or more contributor license agreements. See the NOTICE file |
---|
| 3 | #distributed with this work for additional information |
---|
| 4 | #regarding copyright ownership. The ASF licenses this file |
---|
| 5 | #to you under the Apache License, Version 2.0 (the |
---|
| 6 | #"License"); you may not use this file except in compliance |
---|
| 7 | #with the License. You may obtain a copy of the License at |
---|
| 8 | |
---|
| 9 | # http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 10 | |
---|
| 11 | #Unless required by applicable law or agreed to in writing, software |
---|
| 12 | #distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 13 | #WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 14 | #See the License for the specific language governing permissions and |
---|
| 15 | #limitations under the License. |
---|
| 16 | import urllib, urlparse, re |
---|
| 17 | |
---|
| 18 | from HTMLParser import HTMLParser |
---|
| 19 | |
---|
| 20 | class miniHTMLParser( HTMLParser ): |
---|
| 21 | |
---|
| 22 | viewedQueue = [] |
---|
| 23 | instQueue = [] |
---|
| 24 | |
---|
| 25 | def setBaseUrl(self, url): |
---|
| 26 | self.baseUrl = url |
---|
| 27 | |
---|
| 28 | def getNextLink( self ): |
---|
| 29 | if self.instQueue == []: |
---|
| 30 | return None |
---|
| 31 | else: |
---|
| 32 | return self.instQueue.pop(0) |
---|
| 33 | |
---|
| 34 | def handle_starttag( self, tag, attrs ): |
---|
| 35 | if tag == 'a': |
---|
| 36 | newstr = urlparse.urljoin(self.baseUrl, str(attrs[0][1])) |
---|
| 37 | if re.search('mailto', newstr) != None: |
---|
| 38 | return |
---|
| 39 | |
---|
| 40 | if (newstr in self.viewedQueue) == False: |
---|
| 41 | self.instQueue.append( newstr ) |
---|
| 42 | self.viewedQueue.append( newstr ) |
---|
| 43 | |
---|
| 44 | |
---|
| 45 | |
---|