From 0ac2f2e9c169a45e89818871d363a7ba57e3a314 Mon Sep 17 00:00:00 2001
From: Rob <rw@boogiedev.net>
Date: Tue, 30 Jul 2019 11:35:46 +0200
Subject: [PATCH] my scraper

---
 src/Support/Stiftungssuche.de_rob.py | 43 ++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 src/Support/Stiftungssuche.de_rob.py

diff --git a/src/Support/Stiftungssuche.de_rob.py b/src/Support/Stiftungssuche.de_rob.py
new file mode 100644
index 0000000..e7ca14f
--- /dev/null
+++ b/src/Support/Stiftungssuche.de_rob.py
@@ -0,0 +1,43 @@
+import sys
+import requests
+import re
+from bs4 import BeautifulSoup
+
+suchwort = 'stift'
+
+if len(sys.argv) > 1:
+    if sys.argv[1] == 'download':
+        payload = {'searchtype': 1 , 'stichworte': suchwort, "ort":'', "bundesland":'', "action"  : "search"}
+        r = requests.post("https://stiftungssuche.de/", data=payload)
+        cookie = r.cookies
+        if r.status_code == 200:
+            f = open("data/website", "w")
+            f.write(r.text)
+            f.close()
+
+        count = 1
+
+        while True:
+            print("\nReload: "+str(count))
+            count = count + 1
+            r = requests.get('https://stiftungssuche.de/wp-content/plugins/stiftungssuche/ajax/more_content.php/', cookies=cookie)
+            if r.status_code == 200:
+                f = open("data/website", "a")
+                f.write(r.text)
+                f.close()
+            else:
+                break
+
+f = open("data/website", "r")
+document = BeautifulSoup(f.read(), 'html.parser')
+f.close()
+hitlist = document.find_all(id=re.compile("^portrait_"))
+
+for entry in hitlist:
+    portrait = str(entry['id'])
+    f = open("result/"+portrait+'.html', "w")
+    f.write(str(entry.div))
+    f.close()
+
+#page = 'https://stiftungssuche.de/wp-content/plugins/stiftungssuche/ajax/more_content.php/'
+