added all files to project

speiseplan-skript/speiseplan.html

@@ -0,0 +1,12 @@
+<html>
+<div style="background:black; color:white">
+
+
+
+
+
+Speiseplan <br/><h4>Mittwoch 23.02.2022</h4>Essen 1<br/>Pfefferrahmgeschnetzeltes vom Schwein  mit Spätzle <br/>2,52 € (Stud.)   3,57 €  (Bed.)       5,04 €  (Gäste)<br/><br/> <br/>Essen 2<br/>Currywurst mit Soße <br/>2,40 € (Stud.)   3,40 €  (Bed.)       4,40 €  (Gäste)<br/><br/> <br/>Essen 3<br/>Sesamkartoffeln auf Kokosspinat <br/>2,79 € (Stud.)   3,79 €  (Bed.)       5,58 €  (Gäste)<br/><br/> <br/>
+
+
+</div>
+</html>

speiseplan-skript/speiseplan.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+import re
+from string import Template
+import urllib
+try:
+    from BeautifulSoup import BeautifulSoup
+except ImportError:
+    from bs4 import BeautifulSoup
+
+
+def excludeAllergens(html_soup):
+    exclude_allergens = html_soup.find_all("sup")
+    for element in exclude_allergens:
+        element.extract()
+
+
+def excludeForm(html_soup):
+    excludeForm = html_soup.find('form')
+    excludeForm.extract()
+
+
+def excludeImages(html_soup):
+    exclude_img = html_soup.find_all("img")
+    for element in exclude_img:
+        element.extract()
+
+
+if __name__ == '__main__':
+    url = 'https://www.werkswelt.de/?id=mohm'
+    page = urllib.request.urlopen(url).read().decode()
+    correctedPage = re.sub('/br', 'br', page)
+    html_soup = BeautifulSoup(correctedPage, features='html.parser')
+    parsed_html = html_soup.findAll('body')
+    #parsed_html = html_soup.body.html.body
+    excludeForm(parsed_html[1])
+    excludeAllergens(parsed_html[1])
+    excludeImages(parsed_html[1])
+    template = Template('<html>\n<div style="background:black; color:white">\n$parsed_html\n</div>\n</html>')
+
+    # write html-file
+    with open("speiseplan.html", "w") as file:
+        file.write(template.substitute(parsed_html=parsed_html[1].div.decode_contents()))