added senti

reader/GermanPolarityClues-2012/SentiWS_v2.0/SentiWS.txt

@@ -0,0 +1,76 @@
+SentiWS
+~~~~~~~
+
+SentimentWortschatz, or SentiWS for short, is a publicly available German-language resource for sentiment analysis, opinion mining etc. It lists positive and negative polarity bearing words weighted within the interval of [-1; 1] plus their part of speech tag, and if applicable, their inflections. The current version of SentiWS (v2.0) contains around 1,650 positive and 1,800 negative words, which sum up to around 16,000 positive and around 18,000 negative word forms incl. their inflections, respectively. It not only contains adjectives and adverbs explicitly expressing a sentiment, but also nouns and verbs implicitly containing one.
+
+
+License
+~~~~~~~
+
+SentiWS is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported License (http://creativecommons.org/licenses/by-nc-sa/3.0/).
+
+
+Obtain a Copy
+~~~~~~~~~~~~~
+The latest version of SentiWS can be found at https://wortschatz.uni-leipzig.de/download/.
+
+
+Data Format
+~~~~~~~~~~~
+SentiWS is organised in two utf8-encoded text files structured the following way:
+
+<Word>|<POS tag> \t <Polarity weight> \t <Infl_1>,...,<Infl_k> \n
+
+where \t denotes a tab, and \n denotes a new line.
+
+
+Citation
+~~~~~~~~
+
+If you use SentiWS in your work we kindly ask you to cite
+
+R. Remus, U. Quasthoff & G. Heyer: SentiWS - a Publicly Available German-language Resource for Sentiment Analysis.
+In: Proceedings of the 7th International Language Ressources and Evaluation (LREC'10), 2010
+
+or use the following BibTeX-code snippet:
+
+@INPROCEEDINGS{remquahey2010,
+title = {SentiWS -- a Publicly Available German-language Resource for Sentiment Analysis},
+booktitle = {Proceedings of the 7th International Language Resources and Evaluation (LREC'10)},
+author = {Remus, R. and Quasthoff, U. and Heyer, G.},
+year = {2010}
+}
+
+
+Version History
+~~~~~~~~~~~~~~~
+
+SentiWS is "work in progress" and hence far from being fully-fledged and error-free. It will be continuously refined by adding missing words and word forms and removing ambiguous ones.
+
+v1.8b, 2010-05-19: First publicly available version as described in Remus et al. (2010).
+v1.8c, 2012-03-21: Second publicly available version in which some POS tags were corrected.
+v2.0, 2018-10-19: Third publicly available version in which the inflected forms were extended.
+
+
+Statistics
+~~~~~~~~~~
+
+				Positive	Negative
+Adjectives	Baseforms	792		712
+		Inflections	10,922		10,461
+Adverbs		Baseforms	7		4
+		Inflections	5		0
+Nouns		Baseforms	548		688
+		Inflections	731		1154
+Verbs		Baseforms	297		423
+		Inflections	3,235		4,568
+All		Baseforms	1,644		1,827
+		Inflections	14,893		16,183
+
+		Total		16,537		18,010
+
+Table: Overview of the dictionary's content
+
+
+
+SentiWS.txt was last updated on 2018-12-19.

reader/app.py

@@ -3,6 +3,8 @@ import os
 from flask import Flask
 from flask_ask import Ask, request, session, question, statement
 import yaml
+from nltk.corpus import treebank
+from textblob_de import TextBlobDE as TextBlob
 import siteobj as site2
 import util
 
@@ -126,6 +128,40 @@ def search_answer(number):
     session.attributes["lastCall"] = "search2"
     return statement(response)
 
+
+@ask.intent('Senti', mapping={'number': 'Nummer'}, default={'number': 1})
+def get_sentiment(number):
+    site = util.get_session_value(session.attributes, "siteName")
+
+    if site is not None:
+        obj = get_site_obj(site) 
+    else:
+        session.attributes["lastCall"] = "senti"
+        return question("Wonach wollen Sie suchen?")
+
+    if obj is None: # should never be called
+        return question("Error. Wonach wollen Sie suchen?")
+
+
+    links = util.get_session_value(session.attributes, "lastSearch")
+
+    url = links[int(number)-1]
+    NewsText = obj.read_article(url)
+
+    newText = ""
+    for text in NewsText:
+            newText += text
+
+    newText = TextBlob(newText)
+    sent = newText.sentiment[0] 
+
+    if sent < 0:
+            good = "shit"
+    else:
+            good = "nice" 
+
+    return statement(good)
+
 @ask.intent('AMAZON.HelpIntent')
 def help():
     speech_text = 'Dieser Skill erlaubt es Ihnen einige Nachrichten Websites zu nutzen'
@@ -150,10 +186,4 @@ if __name__ == '__main__':
         if verify == 'false':
             app.config['ASK_VERIFY_REQUESTS'] = False
     
-
-    context = SSL.Context(SSL.TLSv1_2_METHOD)
-    cer = os.path.join(os.path.dirname(__file__), 'certificate.pem')
-    key = os.path.join(os.path.dirname(__file__), 'privkey.pem')
-    context = (cer, key)
-    
     app.run(host='127.0.0.1',port=443)

reader/sentiment.py

@@ -1,6 +1,7 @@
 # http://www.ulliwaltinger.de/sentiment/
 # https://github.com/solariz/german_stopwords
 #!/usr/bin/env python
+# https://github.com/markuskiller/textblob-de
 # -*- coding: utf-8 -*-
 import nltk
 import copy
@@ -8,80 +9,28 @@ import encodings
 import csv
 from siteobj import *
 from nltk.corpus import treebank
-
+from textblob_de import TextBlobDE as TextBlob
-negatives = dict()
-positives = dict()
-neutrals = dict()
-
-with open("./reader/GermanPolarityClues-2012/GermanPolarityClues-Negative.tsv", "r", encoding="utf-8") as tsvfile:
-  reader = csv.reader(tsvfile, delimiter='\t')
-  for row in reader:
-        
-        if "-" not in row[4].split("/"):
-                negatives[row[0]] = [float(row[4].split("/")[0]), float(row[4].split("/")[1]), float(row[4].split("/")[2])]
-
-with open("./reader/GermanPolarityClues-2012/GermanPolarityClues-Neutral.tsv", "r", encoding="utf-8") as tsvfile:
-  reader = csv.reader(tsvfile, delimiter='\t')
-  for row  in reader:
-        if "-" not in row[4].split("/"):
-                neutrals[row[0]] = [float(row[4].split("/")[0]), float(row[4].split("/")[1]), float(row[4].split("/")[2])]
-
-with open("./reader/GermanPolarityClues-2012/GermanPolarityClues-Positive.tsv", "r", encoding="utf-8") as tsvfile:
-  reader = csv.reader(tsvfile, delimiter='\t')
-  for row  in reader:
-        if "-" not in row[4].split("/"):
-                positives[row[0]] = [float(row[4].split("/")[0]), float(row[4].split("/")[1]), float(row[4].split("/")[2])]
-
-# get stopwords
-stopwords = []
-with  open("./reader/stopwords.txt", 'r', encoding='utf-8') as f:
-        for line in f:
-                stopwords.append(line)
-
-extraSW = [".", ",", "´´", "``", "'", '"', ]
-stopwords += extraSW
-
-obj = Spiegel()
-
-NewsText = obj.read_article("https://www.spiegel.de/netzwelt/games/labo-vr-set-von-nintendo-im-test-erst-basteln-dann-staunen-a-1265633.html")
-
-newText = ""
-for text in NewsText:
-        newText += text
-
-tokens = nltk.word_tokenize(newText)
-
-toDelete = []
-for token in tokens:
-        if token in stopwords:
-                toDelete.append(token)
-
-for token in toDelete:
-        while token in tokens:
-                tokens.remove(token)
-
-p = 0
-ne = 0
-nu = 0
-for token in tokens:
-        if token in negatives:
-                p += negatives[token][0]
-                ne += negatives[token][1]
-                nu += negatives[token][2]
-        elif token in positives:
-                p += positives[token][0]
-                ne += positives[token][1]
-                nu += positives[token][2]
-        elif token in neutrals:
-                p += neutrals[token][0]
-                ne += neutrals[token][1]
-                nu += neutrals[token][2]
 
 
-total = p + ne + nu
+def get_sentiment(url):
+        NewsText = obj.read_article(url)
 
-p /= total
+        newText = ""
-nu /= total
+        for text in NewsText:
-ne /= total
+                newText += text
 
-print(p, nu, ne)
+        newText = TextBlob(newText)
+
+        sent = newText.sentiment[0] 
+        if sent < 0:
+                good = "shit"
+        else:
+                good = "nice" 
+        print(good, newText.sentiment,"\n", link.split("/")[-1], "\n")
+        return good
+
+obj = Golem()
+news, links = obj.get_news()
+
+for link in links:
+        get_sentiment(link)

requirements

@@ -5,3 +5,5 @@ nltk
 lxml
 urllib
 yaml
+pip install -U textblob-de
+python -m textblob.download_corpora