added alexa zeug

reader/main.py

@@ -0,0 +1,66 @@
+import logging
+import os
+from flask import Flask
+from flask_ask import Ask, request, session, question, statement
+import random
+import yaml
+import site as s
+
+app = Flask(__name__)
+ask = Ask(app, "/")
+logging.getLogger('flask_ask').setLevel(logging.DEBUG)
+
+
+@ask.intent('Search',
+    mapping={'site': 'Site',  'searchTerm':'SearchTerm'},
+    default={'site': 'golem', 'searchTerm':''})
+def search(site, searchTerm):
+    print(site, searchTerm)
+
+    if site == "golem":
+        obj = s.Golem()
+    elif site == "zeit":
+        obj = s.Zeit()
+    elif site == "welt":
+        obj = s.Welt()
+    else:
+        return statement("Es gab einen Fehler")
+    session.attributes["site"] = obj.url
+
+    articles, links = obj.search_article(searchTerm)
+    session.attributes["lastSearch"] = links
+    antwort = "Für welchen der folgenden Artikel interessieren Sie sich?"
+    for i in range(0, len(articles)):
+        antwort += articles[i] + "..."
+
+    return question(antwort)
+
+@ask.intent('Read',
+    mapping={'site': 'Site',  'activity':'Activity'},
+    default={'site': 'golem', 'activity':'read_headlines'})
+def read(site, activity):
+    print(site, activity)
+
+    response = ""
+    return statement(response)
+
+@ask.intent('AMAZON.HelpIntent')
+def help():
+    speech_text = 'Dieser Skill erlaubt es Ihnen einige Nachrichten Websites zu nutzen'
+    return statement(speech_text)
+
+@ask.launch
+def launch():
+    return read("golem", "read_headlines")
+
+@ask.session_ended
+def session_ended():
+    return "{}", 200
+
+
+if __name__ == '__main__':
+    if 'ASK_VERIFY_REQUESTS' in os.environ:
+        verify = str(os.environ.get('ASK_VERIFY_REQUESTS', '')).lower()
+        if verify == 'false':
+            app.config['ASK_VERIFY_REQUESTS'] = False
+    app.run()

reader/site.py

@@ -28,6 +28,76 @@ class site:
     
 
 class Golem(site):
+    url = "golem"   
+    def search_article(self, topic):
+        searchURL = "https://suche.golem.de/search.php?l=10&q=" + topic.replace(" ", "+")
+        site = requests.get(searchURL, headers=self.header_values)
+        tree = html.fromstring(site.content)
+        
+        articles = tree.xpath('//span[@class="dh2 head2"]/text()')
+        links = tree.xpath('//ol[@class="list-articles"]/li/header//@href')
+        return articles, links
+    
+    def get_news(self):
+        searchURL = "https://www.golem.de/"
+        site = requests.get(searchURL, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        articles = tree.xpath('//h2[@class="head2"]/text()')
+        return articles
+
+    def read_headlines(self, url):
+        site = requests.get(url, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        title = tree.xpath('//header/h1/span[@class="dh1 head5"]/text()')
+        title += tree.xpath('//header/p/text()')
+        return title
+
+    def read_article(self, url):
+        site = requests.get(url, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        title = self.read_headlines(url)
+        title += tree.xpath('//div[@class="formatted"]/p/text()')
+        return title
+
+class Zeit(site):
+    url = "zeit"   
+    def search_article(self, topic):
+        searchURL = "https://suche.golem.de/search.php?l=10&q=" + topic.replace(" ", "+")
+        site = requests.get(searchURL, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        articles = tree.xpath('//span[@class="dh2 head2"]/text()')
+        return articles
+    
+    def get_news(self):
+        searchURL = "https://www.golem.de/"
+        site = requests.get(searchURL, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        articles = tree.xpath('//h2[@class="head2"]/text()')
+        return articles
+
+    def read_headlines(self, url):
+        site = requests.get(url, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        title = tree.xpath('//header/h1/span[@class="dh1 head5"]/text()')
+        title += tree.xpath('//header/p/text()')
+        return title
+
+    def read_article(self, url):
+        site = requests.get(url, headers=self.header_values)
+        tree = html.fromstring(site.content)
+
+        title = self.read_headlines(url)
+        title += tree.xpath('//div[@class="formatted"]/p/text()')
+        return title
+
+class Welt(site):
+    url = "welt"   
     def search_article(self, topic):
         searchURL = "https://suche.golem.de/search.php?l=10&q=" + topic.replace(" ", "+")
         site = requests.get(searchURL, headers=self.header_values)

reader/tests.py

@@ -3,8 +3,10 @@ from lxml import html
 import requests
 import re
 
-url="https://www.golem.de/news/tchap-forscher-gelingt-anmeldung-im-regierungschat-frankreichs-1904-140799.html"
+searchURL = "https://suche.golem.de/search.php?l=10&q=gaming" 
-site = requests.get(url)
+site = requests.get(searchURL)
 tree = html.fromstring(site.content)
-title = tree.xpath('//div[@class="formatted"]/p/text()')
+
-print(title)
+articles = tree.xpath('//span[@class="dh2 head2"]/text()')
+links = tree.xpath('//ol[@class="list-articles"]/li/header//@href')
+print(len(articles), len(links))