Created
September 1, 2013 14:02
-
-
Save aloncarmel/6404647 to your computer and use it in GitHub Desktop.
Small experiement to start writing my own related content engine on app engine using search api and some basic levenshtein. * Grabs keywords per url from textwise.com * Writes full text search in app engine, creates a hash.
* Grab url and keywords, compare hashes after keyword search. Its a start. never been tested.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# | |
# Copyright 2007 Google Inc. | |
# | |
# Licensed 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 webapp2 | |
from datetime import datetime | |
from google.appengine.api import search | |
from google.appengine.api import urlfetch | |
import simplejson as json | |
import urllib | |
from urlparse import urlparse | |
def levenshtein(a,b): | |
"Calculates the Levenshtein distance between a and b." | |
n, m = len(a), len(b) | |
if n > m: | |
# Make sure n <= m, to use O(min(n,m)) space | |
a,b = b,a | |
n,m = m,n | |
current = range(n+1) | |
for i in range(1,m+1): | |
previous, current = current, [i]+[0]*n | |
for j in range(1,n+1): | |
add, delete = previous[j]+1, current[j-1]+1 | |
change = previous[j-1] | |
if a[j-1] != b[i-1]: | |
change = change + 1 | |
current[j] = min(add, delete, change) | |
return current[n] | |
# Grab keywords from textwise and return them | |
def getKeywords(url): | |
apiurl = 'http://api.semantichacker.com/KEY/concept?format=json&uri='+url | |
result = urlfetch.fetch(apiurl) | |
json_decoder = json.decoder.JSONDecoder() | |
decoded_json = json_decoder.decode(result.content) | |
keywords = [] | |
for concept in decoded_json['conceptExtractor']['conceptExtractorResponse']['concepts']: | |
keywords.append(concept['label']) | |
return keywords | |
# Grab url and save keywords and hash for future search | |
class WriteDocHandler(webapp2.RequestHandler): | |
def get(self): | |
url = self.request.get("url") | |
parsed_uri = urlparse(url) | |
domain = '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri) | |
keywords = getKeywords(url) | |
keywordss = ','.join(map(str, keywords)) | |
document = search.Document(fields=[ | |
search.TextField(name='keywords', value=keywordss), | |
search.TextField(name='url', value=url), | |
search.TextField(name='hash',value=str(hash(frozenset(keywords)))) | |
]) | |
index = search.Index(name=domain) | |
results = index.put(document) | |
doc_id = results[0].id | |
self.response.write(doc_id) | |
# Search the database for url and compare results scoring with hash using levenshtein basic method and return scores. | |
class SearchHandler(webapp2.RequestHandler): | |
def get(self): | |
url = self.request.get("url") | |
parsed_uri = urlparse(url) | |
domain = '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri) | |
keywords = getKeywords(url) | |
keywordss = ' OR '.join(map(str, keywords)) | |
query = search.Query("keywords = "+keywordss) | |
index = search.Index(name=domain) | |
results = index.search(query) | |
json_encoder = json.encoder.JSONEncoder() | |
jsonobj = [] | |
currenthashurl = str(hash(frozenset(keywords))) | |
currenturlarr = {} | |
currenturlarr['requested_url'] = url | |
currenturlarr['hash'] = currenthashurl | |
jsonobj.append(currenturlarr) | |
for ScoredDocument in results: | |
if(ScoredDocument.fields[1].value != url): | |
arr = {} | |
arr['url'] = ScoredDocument.fields[1].value | |
arr['keywords'] = str(ScoredDocument.fields[0].value) | |
arr['hash'] = str(ScoredDocument.fields[2].value) | |
arr['score'] = float(levenshtein(currenthashurl,str(ScoredDocument.fields[2].value)))/100 | |
jsonobj.append(arr) | |
self.response.write(json_encoder.encode(jsonobj)) | |
app = webapp2.WSGIApplication([ | |
('/writedoc', WriteDocHandler), | |
('/search',SearchHandler) | |
], debug=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment