golem + spiegel works

TODO: bewerten

reader/main.py

@@ -14,7 +14,6 @@ logging.getLogger('flask_ask').setLevel(logging.DEBUG)
 @ask.intent('searchon', mapping={'site': 'Site'}, default={'site': 'golem'})
 def search_on(site):
     try:
-
         session.attributes["siteName"] = site
         print(session.attributes["siteName"])
     except: 
@@ -38,7 +37,7 @@ def search_for(searchTerm):
 
     if site == "golem":
         obj = site2.Golem()
-    elif site == "spiegel":
+    elif site.lower() == "spiegel":
         obj = site2.Spiegel()
     elif site is None:
         session.attributes["searchTerm"] = searchTerm
@@ -64,14 +63,13 @@ def search_for(searchTerm):
 @ask.intent('News', mapping={'site': 'Site'}, default={'site': ''})
 def news(site):
     try:
-        site = site.lower()
         session.attributes["siteName"] = site
     except: 
         print("error")
     print(site)
     if site == "golem":
         obj = site2.Golem()
-    elif site == "spiegel":
+    elif site.lower() == "spiegel":
         obj = site2.Spiegel()
     elif site == '':
         session.attributes["lastCall"] = "news"
@@ -96,25 +94,25 @@ def search_answer(number):
         site = session.attributes["siteName"]
     except:
         site = None
-
+    print(number)
     if site == "golem":
         obj = site2.Golem()
-    elif site == "spiegel":
+    elif site.lower() == "spiegel":
         obj = site2.Spiegel()
 
     links = session.attributes["lastSearch"]
-
+    if "http" not in str(links):
-    newLinks = []
+        newLinks = []
-    for link in links:
+        for link in links:
-        if "http" not in link:
+            if "http" not in link:
-            newLinks.append(obj.baseURL + link)
+                newLinks.append(obj.baseURL + link)
-    links = newLinks
+        links = newLinks
 
     art = obj.read_headlines(links[int(number)-1])
     response = ""
     for element in art:
-        response +=  element + "   "
+        response +=  element 
-    print(links)
+
     session.attributes["lastCall"] = "search2"
     return statement(response)
 

reader/siteobj.py

@@ -59,24 +59,24 @@ class Golem(Site):
     siteName = "golem"
     baseURL = "https://www.golem.de/"   
     searchURLString = "https://suche.golem.de/search.php?l=10&q="
-
+    xPath = dict()
-    Site.xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
+    xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
-    Site.xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
+    xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
-    Site.xPath["newsArticle"] = '//li//h2/text()'
+    xPath["newsArticle"] = '//li//h2/text()'
-    Site.xPath["newsLinks"] = '//header[@class="cluster-header"]//@href'
+    xPath["newsLinks"] = '//div[@class="g g4"]//header//@href'
-    Site.xPath["readHeadlineTitle"] = '//header/h1/span[@class="dh1 head5"]/text()'
+    xPath["readHeadlineTitle"] = '//header/h1/span[@class="dh1 head5"]/text()'
-    Site.xPath["readHeadlineText"] = '//header/p/text()'
+    xPath["readHeadlineText"] = '//header/p/text()'
-    Site.xPath["readArticleText"] = '//div[@class="formatted"]/p/text()'
+    xPath["readArticleText"] = '//div[@class="formatted"]/p/text()'
 
 class Spiegel(Site):
     siteName = "spiegel"
     baseURL = "https://www.spiegel.de/"   
     searchURLString = "https://www.spiegel.de/suche/?suchbegriff="
-
+    xPath = dict()
-    Site.xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
+    xPath["searchArticle"] = '//div[@class="search-teaser"]/p/text()'
-    Site.xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
+    xPath["searchLinks"] = '//div[@class="search-teaser"]/p//@href'
-    Site.xPath["newsArticle"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//span[@class="headline"]/text()'
+    xPath["newsArticle"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//span[@class="headline"]/text()'
-    Site.xPath["newsLinks"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//@href'
+    xPath["newsLinks"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//@href'
-    Site.xPath["readHeadlineTitle"] = '//div[@class="column-both"]//span[@class="headline"]//text()'
+    xPath["readHeadlineTitle"] = '//div[@class="column-both"]//span[@class="headline"]//text()'
-    Site.xPath["readHeadlineText"] = '//div[@class="column-both"]/p/strong/text()'
+    xPath["readHeadlineText"] = '//div[@class="column-both"]/p/strong/text()'
-    Site.xPath["readArticleText"] = '//div[@class="formatted"]/p/text()'
+    xPath["readArticleText"] = '//div[@class="article-section clearfix"]/p/text()'

reader/tests.py

@@ -1,12 +1,5 @@
-import urllib.request,urllib.parse,urllib.error
+import siteobj as site2
-from lxml import html
-import requests
-import re
 
-searchURL = "https://suche.golem.de/search.php?l=10&q=gaming" 
-site = requests.get(searchURL)
-tree = html.fromstring(site.content)
 
-articles = tree.xpath('//span[@class="dh2 head2"]/text()')
+obj = site2.Golem()
-links = tree.xpath('//ol[@class="list-articles"]/li/header//@href')
+news = obj.get_news()
-print(len(articles), len(links))