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 7970f1e commit 771ead3
Showing 1 changed file with 5 additions and 6 deletions.
11 changes: 5 additions & 6 deletions scraper.rb
Original file line number Diff line number Diff line change
Expand Up @@ -29,28 +29,26 @@

# Function to scrape details from each event page
def scrape_event_details(event_url)
puts "Accessing event page: #{event_url}"
document = Nokogiri::HTML(open(event_url))

event_data = []
document.css('tr').each do |row|
index_number = row.css('td.tonr a').text.strip
betreff = row.css('td.tobetreff div a').text.strip
vorlage_link = row.at_css('td.tovonr a')
vorlage_url = vorlage_link ? "https://www.sitzungsdienst-schenefeld.de/bi/#{vorlage_link['href']}" : "No Vorlage"
vorlage_text = vorlage_link ? vorlage_link.text.strip : "No Vorlage"
vorlage_url = vorlage_link ? "https://www.sitzungsdienst-schenefeld.de/bi/#{vorlage_link['href']}" : "Keine Vorlage"
vorlage_text = vorlage_link ? vorlage_link.text.strip : "Keine Vorlage"

# Save data to an array
event_data << [index_number, betreff, vorlage_text, vorlage_url]
puts "Found: #{index_number}, Betreff: #{betreff}, Vorlage: #{vorlage_text}, Vorlage URL: #{vorlage_url}"
# Debug-Ausgaben können hier auskommentiert werden:
# puts "Found: #{index_number}, Betreff: #{betreff}, Vorlage: #{vorlage_text}, Vorlage URL: #{vorlage_url}"
end
return event_data
end

# Function to iterate over calendar data and fetch event details
def scrape_calendar_data(year, month)
url = "https://www.sitzungsdienst-schenefeld.de/bi/si010_r.asp?MM=#{month}&YY=#{year}"
puts "Attempting to access URL: #{url}"
document = Nokogiri::HTML(open(url))
event_links = document.css('a[href*="to010_r.asp?SILFDNR="]').map { |link| "https://www.sitzungsdienst-schenefeld.de/bi/#{link['href']}" }

Expand All @@ -71,3 +69,4 @@ def save_to_csv(data)

# Start scraping
scrape_calendar_data(2024, 3)

0 comments on commit 771ead3

Please sign in to comment.