39 lines
1.1 KiB
Python
39 lines
1.1 KiB
Python
import pandas as pd
|
|
from pathlib import Path
|
|
from bs4 import BeautifulSoup
|
|
|
|
# 1. 读取本地HTML文件
|
|
file_path = Path(r'D:\WorkingProject\LightStackAdapter\Log\设备测试数据记录-铁塔主站\南和县牧村\Untitled-1.html')
|
|
html_content = file_path.read_text()
|
|
|
|
|
|
# 2. 解析HTML文件
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|
|
|
# 3. 找到表格元素
|
|
table = soup.find_all('table') # 假设页面中只有一个表格，如果有多个表格，可能需要进一步筛选
|
|
|
|
# 4. 提取表格数据
|
|
data = []
|
|
headers = []
|
|
|
|
# 提取表头
|
|
header_row = table.find('thead').find('tr')
|
|
for header in header_row.find_all('th'):
|
|
headers.append(header.text.strip())
|
|
|
|
# 提取数据行
|
|
for row in table.find('tbody').find_all('tr'):
|
|
row_data = []
|
|
for cell in row.find_all(['td', 'th']):
|
|
row_data.append(cell.text.strip())
|
|
data.append(row_data)
|
|
|
|
# 5. 将数据保存为DataFrame
|
|
df = pd.DataFrame(data, columns=headers)
|
|
|
|
# 6. 将DataFrame保存为CSV文件
|
|
output_file = 'extracted_table.csv'
|
|
df.to_csv(output_file, index=False, encoding='utf-8')
|
|
|
|
print(f'表格数据已成功提取并保存到 {output_file}') |