From 0aa90f86d6974553d74bb4bde26acd1afcdee609 Mon Sep 17 00:00:00 2001
From: lub <git@lubiland.de>
Date: Tue, 2 Jul 2024 22:51:57 +0200
Subject: [PATCH] add some rudimentary webserver

---
 scrape.py | 72 +++++++++++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 29 deletions(-)

diff --git a/scrape.py b/scrape.py
index 815b06b..3f129a8 100644
--- a/scrape.py
+++ b/scrape.py
@@ -1,46 +1,60 @@
 import requests
 from bs4 import BeautifulSoup
+from http.server import BaseHTTPRequestHandler, HTTPServer
 
 overview_url = 'https://gruene-hohenlohe.de/kalender'
 overview_html = requests.get(overview_url, timeout=60).text
 overview_soup = BeautifulSoup(overview_html, 'html.parser')
 
 
-for href in overview_soup.select('.media-body h2 a'):
-    event_url = 'https://gruene-hohenlohe.de/' + href.attrs['href']
-    event_html = requests.get(event_url, timeout=60).text
-    event_soup = BeautifulSoup(event_html, 'html.parser')
+def scrape():
+    for href in overview_soup.select('.media-body h2 a'):
+        event_url = 'https://gruene-hohenlohe.de/' + href.attrs['href']
+        event_html = requests.get(event_url, timeout=60).text
+        event_soup = BeautifulSoup(event_html, 'html.parser')
 
-    data = event_soup.select('.calendarize dl dd')
+        data = event_soup.select('.calendarize dl dd')
 
-    output = ''
+        output = ''
 
-    # date
-    output += data[0].text.strip()
-    output += ' '
+        # date
+        output += data[0].text.strip()
+        output += ' '
 
-    # time
-    timespan = data[1].text.strip()
-    time = timespan.split(' ')[0]
+        # time
+        timespan = data[1].text.strip()
+        time = timespan.split(' ')[0]
 
-    output += time
-    output += ' Uhr'
-    output += ', '
+        output += time
+        output += ' Uhr'
+        output += ', '
 
-    # place
-    output += data[2].text.strip()
-    output += ', '
+        # place
+        #output += data[2].text.strip()
+        output += ', '
 
-    # title
-    #output += '<b>'
-    #output += event_soup.select('.calendarize h1')[0].text.strip()
-    #output += '</b>'
+        # title
+        output += '<b>'
+        output += event_soup.select('.calendarize h1')[0].text.strip()
+        output += '</b>'
 
-    #try:
-    description = event_soup.select('.calendarize .text p')[0].text.strip()
-    #output += ' '
-    output += description
-    #except IndexError:
-    #    pass
+        try:
+            description = event_soup.select('.calendarize .text p')[0].text.strip()
+            output += ' '
+            output += description
+        except IndexError:
+            pass
 
-    print(output)
+        return output
+
+
+
+
+class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
+    def do_GET(self):
+        self.send_response(200)
+        self.end_headers()
+        self.wfile.write(scrape().encode('utf-8'))
+
+httpd = HTTPServer(('', 8000), SimpleHTTPRequestHandler)
+httpd.serve_forever()