From 22be23224f2f25fdc602c58ddf7a3d95b478403b Mon Sep 17 00:00:00 2001
From: Patrice <ofjokg@gmail.com>
Date: Wed, 8 May 2019 16:48:42 +0200
Subject: [PATCH] golem + spiegel works

TODO: bewerten
---
 reader/__pycache__/siteobj.cpython-35.pyc | Bin 3530 -> 3505 bytes
 reader/main.py                            |  26 ++++++++----------
 reader/siteobj.py                         |  32 +++++++++++-----------
 reader/tests.py                           |  13 ++-------
 4 files changed, 31 insertions(+), 40 deletions(-)

diff --git a/reader/__pycache__/siteobj.cpython-35.pyc b/reader/__pycache__/siteobj.cpython-35.pyc
index a0b60343d3bf257ef65466fd33dbdacd9001fa26..6f1710410e1c4f407edcd90a271b0b46788376a7 100644
GIT binary patch
delta 330
zcmX>ly-}J|oR^o&@Y$spy^WmP*%=EbA7oebOl4zeW?+b7XGmdTNClFt3^pljU=}-&
z#Q|n<0$E&O7B`T^17`68S$tp?KaeHBkUH6%<Gif0zJ5w(S+qlPPGWJftx~!|x`|S(
zzJ5k(VoGY!WDU-RY}yPA3`LTY6WAr}b%0DOATAaI5<HA-V93eHg#?R0YLbB%4w!)~
e2Out{vhz33;!0p*)SmpCM@<r^dnQ}(P67aNe>d#_

delta 327
zcmdleeM*{BoR^pD+lh-Yp&L23voqFCKFF>Zn!>`6%Epkz&XB^&V3WcI<FErc954<i
zki!Mza059!Fb*$}!w2K=133a<&SY(l^GX`}`WdN-DXB%#4#_!*#l^Nt$vLIPC8<Ta
z5Mia*$>N*~8JQ<P;E`3(VPIge0^(v3Ai=}P27*kyjBq&l2d4}zUA(!TD}f2@7Bz8P
JPLSuF1ORulK5qa3

diff --git a/reader/main.py b/reader/main.py
index 3e88ad5..4a35a2c 100644
--- a/reader/main.py
+++ b/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"]
-
-    newLinks = []
-    for link in links:
-        if "http" not in link:
-            newLinks.append(obj.baseURL + link)
-    links = newLinks
+    if "http" not in str(links):
+        newLinks = []
+        for link in links:
+            if "http" not in link:
+                newLinks.append(obj.baseURL + link)
+        links = newLinks
 
     art = obj.read_headlines(links[int(number)-1])
     response = ""
     for element in art:
-        response +=  element + "   "
-    print(links)
+        response +=  element 
+
     session.attributes["lastCall"] = "search2"
     return statement(response)
 
diff --git a/reader/siteobj.py b/reader/siteobj.py
index c986a6b..8a15a86 100644
--- a/reader/siteobj.py
+++ b/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="
-
-    Site.xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
-    Site.xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
-    Site.xPath["newsArticle"] = '//li//h2/text()'
-    Site.xPath["newsLinks"] = '//header[@class="cluster-header"]//@href'
-    Site.xPath["readHeadlineTitle"] = '//header/h1/span[@class="dh1 head5"]/text()'
-    Site.xPath["readHeadlineText"] = '//header/p/text()'
-    Site.xPath["readArticleText"] = '//div[@class="formatted"]/p/text()'
+    xPath = dict()
+    xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
+    xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
+    xPath["newsArticle"] = '//li//h2/text()'
+    xPath["newsLinks"] = '//div[@class="g g4"]//header//@href'
+    xPath["readHeadlineTitle"] = '//header/h1/span[@class="dh1 head5"]/text()'
+    xPath["readHeadlineText"] = '//header/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="
-
-    Site.xPath["searchArticle"] = '//span[@class="dh2 head2"]/text()'
-    Site.xPath["searchLinks"] = '//ol[@class="list-articles"]/li/header//@href'
-    Site.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'
-    Site.xPath["readHeadlineTitle"] = '//div[@class="column-both"]//span[@class="headline"]//text()'
-    Site.xPath["readHeadlineText"] = '//div[@class="column-both"]/p/strong/text()'
-    Site.xPath["readArticleText"] = '//div[@class="formatted"]/p/text()'
+    xPath = dict()
+    xPath["searchArticle"] = '//div[@class="search-teaser"]/p/text()'
+    xPath["searchLinks"] = '//div[@class="search-teaser"]/p//@href'
+    xPath["newsArticle"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//span[@class="headline"]/text()'
+    xPath["newsLinks"] = '//div[@class="column-wide pano_xxl"]//div[@class="teaser"]//h2[@class="article-title"]//@href'
+    xPath["readHeadlineTitle"] = '//div[@class="column-both"]//span[@class="headline"]//text()'
+    xPath["readHeadlineText"] = '//div[@class="column-both"]/p/strong/text()'
+    xPath["readArticleText"] = '//div[@class="article-section clearfix"]/p/text()'
diff --git a/reader/tests.py b/reader/tests.py
index 8d310a6..261c094 100644
--- a/reader/tests.py
+++ b/reader/tests.py
@@ -1,12 +1,5 @@
-import urllib.request,urllib.parse,urllib.error
-from lxml import html
-import requests
-import re
+import siteobj as site2
 
-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()')
-links = tree.xpath('//ol[@class="list-articles"]/li/header//@href')
-print(len(articles), len(links))
\ No newline at end of file
+obj = site2.Golem()
+news = obj.get_news()