Python - Scrapear Eventos en meetup

Hola, estoy intentando scrappear los eventos de MeetUp para Madrid y exportarlos en un csv con las siguientes variables: .image_url, event_name, event_date, event_time, event_group, description_text, location_name, location_info, map_link, event_categories
Tengo el siguiente código pero no me funciona, si me pudierais ayudar por favor que no soy programadora y no sé muy bien cómo debo hacerlo. Gracias de antemano.


from selenium import webdriver
from bs4 import BeautifulSoup
import csv
import os
import time # Import the time module
import random

# URL of the page with meetup events in Madrid
base_url = "https://www.meetup.com/es-ES/find/?location=es--Madrid&source=EVENTS&eventType=inPerson"

# Limit of events you want to collect
event_limit = 100

# Directory to store the event images
image_dir = "event_images"
os.makedirs(image_dir, exist_ok=True)

# List to store event data
data = []

# Initialize a Selenium web driver
driver = webdriver.Chrome() # You need to have Chrome and chromedriver installed

# Function to get event details including the image
def get_event_details(event_url):
driver.get(event_url)
soup = BeautifulSoup(driver.page_source, 'html.parser')

# Introduce a 0.5-second delay before retrieving the map link
time.sleep(1 + random.uniform(0, 1))

# Find the HTML element containing the event image from within the event page
image_element = soup.find("img", {"alt": True, "data-nimg": True})

# Extract the image URL
image_url = image_element['src'] if image_element else "Image URL not available"

description_element = soup.find("div", {"class": "break-words"})
description = description_element.find_all("p")
description_text = "\n".join([p.text.strip() for p in description])

location_name_element = soup.select_one("a[data-testid='venue-name-link']").text if soup.select_one(
"a[data-testid='venue-name-link']") else "Information not available"

location_info_element = soup.find("div", {"class": "text-gray6", "data-testid": "location-info"})
location_info = location_info_element.text.strip() if location_info_element else "Information not available"



map_link_element = soup.find("a", {"data-testid": "map-link"})['href'] if soup.find("a", {
"data-testid": "map-link"}) else "Map link not available"

categories = get_event_categories(event_url)

return image_url, description_text, location_name_element, location_info, map_link_element, categories

# Function to get event categories
def get_event_categories(event_url):
driver.get(event_url)
soup = BeautifulSoup(driver.page_source, 'html.parser')

categories_element = soup.find("div", {"id": "topics"})

if categories_element:
categories = categories_element.find_all("a")
categories_list = [category.text for category in categories]
categories_text = ", ".join(categories_list)
else:
categories_text = "Categories not available"

return categories_text

# Counter for the number of collected events
event_count = 0
# Conjunto para almacenar URL de eventos ya recopiladas
collected_event_urls = set()
# Current page number
page_number = 1

while event_count < event_limit:
# Build the URL of the current page
url = f"{base_url}&page={page_number}"

# Send an HTTP request to get the page
driver.get(url)
soup = BeautifulSoup(driver.page_source, 'html.parser')

# Find all elements containing event details
event_elements = soup.find_all("div", {"data-element-name": "categoryResults-eventCard"})

if not event_elements:
break

for event_element in event_elements:
# Find the image URL, event name, and other details
event_url_element = event_element.find("a", {"data-event-label": "Event card"})
event_url = event_url_element["href"]

# Verifica si ya hemos recopilado este evento
if event_url in collected_event_urls:
continue

image_url, description_text, location_name, location_info, map_link, event_categories = get_event_details(event_url)

event_name = event_element.find('h2', class_="text-gray7 font-medium text-base pb-1 pt-0 line-clamp-3").text.strip()
event_date = event_element.find("span").text.strip()
event_time_element = event_element.find("time")
if event_time_element:
event_time = event_time_element.find_all("span")[1].text.strip()
else:
event_time = "Time not available"
event_group = event_element.find("p", class_="text-gray6").text.strip()
# Añade la URL del evento al conjunto de eventos recopilados
collected_event_urls.add(event_url)
data.append([image_url, event_name, event_date, event_time, event_group, description_text, location_name, location_info, map_link, event_categories])

event_count += 1

if event_count >= event_limit:
break

page_number += 1

# Save the data to a CSV file
with open('meetup_events_madrid.csv', 'w', newline='', encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["Image URL", "Name", "Date", "Time", "Group", "Description", "Location Name", "Location Info", "Map Link", "Categories"])
for event in data:
writer.writerow(event)