first order

src/Kalender/scrape_EFA_online.py

@@ -0,0 +1,34 @@
+from bs4 import BeautifulSoup
+import requests
+import csv
+
+source = requests.get('https://efa-net.eu/events/events-calendar').text
+soup = BeautifulSoup(source, 'lxml')
+
+csv_file = open('EFA_scrape_csv', 'w')
+csv_writer = csv.writer(csv_file)
+csv_writer.writerow(['titel', 'datum', 'event_url', 'ort'])
+
+
+for event in soup.find_all("div", class_="column mcb-column one column_list"):
+    titel = event.h4.text
+    print(titel)
+
+    datum =event.find("div", class_="desc").p.b.text
+    print(datum)
+    
+    ort =event.find("div", class_="desc").p.i.text
+    print(ort)
+
+    try:
+        event_url = event.find("a")['href']
+    except Exception as e:
+        event_url = None
+
+    print(event_url)
+
+    print()
+
+    csv_writer.writerow([titel, datum, event_url, ort])
+
+csv_file.close()

src/Kalender/scrape_FR_online_final.py

@@ -0,0 +1,54 @@
+from bs4 import BeautifulSoup
+import requests
+import csv
+
+source = requests.get('https://fundraiser-magazin.de/fundraising-kalender.html').text
+soup = BeautifulSoup(source, 'lxml')
+
+csv_file = open("frkalender_scrape_csv", "w")
+
+csv_writer = csv.writer(csv_file)
+csv_writer.writerow(["titel", "datum", "veranstalter", "event_url", "ort"])
+
+
+for event in soup.find_all("div", class_="kalender-veranstaltung"):
+    titel = event.find("div", class_="kalender-titel").text
+    print(titel)
+
+    datum = event.find("div", class_="kalender-termin").text
+    print(datum)
+
+    veranstalter = event.find("div", class_="kalender-veranstalter").text
+    veranstalter = veranstalter.split(": ")[1]
+    print(veranstalter)
+
+    event_url = event.find("a")['href']
+    #print(event_url)
+    event_link = f"Weitere Informationen: {event_url}"
+    print(event_link)
+
+    try:
+        ort = event.find("div", class_="kalender-ort").text
+        ort = ort.split(": ")[1]
+
+    except Exception as e:
+        ort = None
+    print(ort)
+
+
+    print()
+
+    csv_writer.writerow([titel, datum, veranstalter, event_url, ort])
+csv_file.close()
+'''
+for event in soup.find_all("div", class_="kalender-veranstaltung"):
+    
+    titel = event.find_all('div', class_='kalender-titel')
+    print(titel)
+    
+    veranstalter = event.find_all('div', class_='kalender-veranstalter')
+    print(veranstalter)
+    
+    ort = event.find_all('div', class_='kalender-ort')
+    print(ort)
+'''

src/Stiftungssuche_190621_scrape.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/'
+