Skip to content

Commit

Permalink
Update scraper.rb
Browse files Browse the repository at this point in the history
  • Loading branch information
BfB-Schenefeld committed Apr 21, 2024
1 parent e1d30ab commit 00e93bc
Showing 1 changed file with 11 additions and 3 deletions.
14 changes: 11 additions & 3 deletions scraper.rb
Original file line number Diff line number Diff line change
Expand Up @@ -43,11 +43,16 @@ def scrape_event_details(event_url)
end
vorlage_link = row.at_css('td.tovonr a')
vorlage_text = vorlage_link ? vorlage_link.text.strip : "-"
vorlage_url = vorlage_link ? "https://www.sitzungsdienst-schenefeld.de/bi/#{vorlage_link['href']}" : nil

# Speichere Daten nur, wenn 'index_number' und 'betreff_text' nicht leer sind
if !index_number.empty? && !betreff_text.empty?
event_data << [index_number, betreff_text, vorlage_text]
puts "Found: #{index_number}, Betreff: #{betreff_text}, Vorlage: #{vorlage_text}"
data_entry = [index_number, betreff_text, vorlage_text]
data_entry << vorlage_url if vorlage_url # Füge die Vorlagen-URL nur hinzu, wenn sie vorhanden ist
event_data << data_entry
output_text = "Found: #{index_number}, Betreff: #{betreff_text}, Vorlage: #{vorlage_text}"
output_text += ", Vorlage URL: #{vorlage_url}" if vorlage_url
puts output_text
end
end
return event_data
Expand All @@ -70,10 +75,13 @@ def scrape_calendar_data(year, month)
# Function to save data to CSV
def save_to_csv(data)
CSV.open("event_details.csv", "wb") do |csv|
csv << ["Index Number", "Betreff", "Vorlage"]
headers = ["Index Number", "Betreff", "Vorlage Text"]
headers << "Vorlage URL" if data.any? { |row| row.length > 3 } # Füge die URL-Spalte hinzu, wenn URLs vorhanden sind
csv << headers
data.each { |row| csv << row }
end
end

# Start scraping
scrape_calendar_data(2024, 3)

0 comments on commit 00e93bc

Please sign in to comment.