Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import requests
- from bs4 import BeautifulSoup
- def fetch_data_rows(url):
- response = requests.get(url)
- if response.status_code == 200:
- soup = BeautifulSoup(response.text, 'html.parser')
- table = soup.find('table', {'class': 'wikitable'})
- if table:
- rows = table.find_all('tr')
- data_rows = []
- for row in rows:
- cells = row.find_all('td')
- data = [cell.get_text(strip=True) for cell in cells]
- if data:
- data_rows.append(data)
- return data_rows
- else:
- print("Table 'wikitable' was not found.")
- else:
- print("Failed to retrieve the page. Status code:", response.status_code)
- return []
- url = 'https://en.wikipedia.org/wiki/List_of_European_Union_member_states_by_population'
- data_rows = fetch_data_rows(url)
- countries_dictionary = {}
- for row in data_rows:
- country = row[0]
- population = row[1]
- percent = row[2]
- percent = percent.strip('%')
- percent = float(percent) if percent else None
- population = ''.join(filter(str.isdigit, population))
- if population:
- population = int(population)
- countries_dictionary[country] = {
- 'population': population,
- 'percent': percent,
- }
- print(countries_dictionary)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement