将HTML table转换为CSV

该脚本用于将html table脚本转换为csv文件。

from bs4 import BeautifulSoup
import csv

html = """
<YOUR HTML TABLE HERE>
"""

soup = BeautifulSoup(html, 'html.parser')

# Extract headers
headers = [th.get_text(strip=True) for th in soup.find_all('th')]

# Extract rows
rows = []
for tr in soup.find_all('tr')[1:]:  # skip the header row
    cells = tr.find_all('td')
    row = [cell.get_text(strip=True) for cell in cells]
    rows.append(row)

# Write to CSV
with open('output1.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerow(headers)
    writer.writerows(rows)

print("CSV file created successfully.")