Python Crawler爬虫实战公式-表格数据

import requests
from bs4 import BeautifulSoup
import pandas as pd

# 定义一个函数来获取表格数据
def get_table_data(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    table = soup.find('table', {'class': 'wikitable'})
    data = []
    for row in table.find_all('tr')[1:]:  # 跳过表头
        cols = row.find_all('td')
        data.append([col.text.strip() for col in cols])
    return data

# 定义URL
url = 'https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)_and_GDP_per_capita'

# 获取表格数据
table_data = get_table_data(url)

# 将数据转换为pandas DataFrame并进行简单的处理
df = pd.DataFrame(table_data, columns=['Country', 'GDP (nominal)', 'GDP per capita'])
df['GDP (nominal)'] = df['GDP (nominal)'].str.replace(',', '').astype('int64')
df['GDP per capita'] = df['GDP per capita'].str.replace(',', '').str.rstrip('USD').astype('float')

# 打印前几行结果
print(df.head())