Python从Confluence提取结构化数据：API优先策略

pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup
import base64
import json

# Confluence 配置
CONFLUENCE_BASE_URL = "https://your-confluence-domain.atlassian.net" # 或 "http://your-self-hosted-confluence.com"
API_USERNAME = "your_email@example.com" # 或您的Confluence用户名
API_TOKEN = "YOUR_API_TOKEN" # 或您的Confluence密码，如果是自托管

# 要提取数据的Confluence页面ID
PAGE_ID = "123456789" # 替换为实际的页面ID

def get_confluence_page_content(page_id):
    """
    通过Confluence REST API获取指定页面的内容（存储格式）。
    """
    url = f"{CONFLUENCE_BASE_URL}/wiki/rest/api/content/{page_id}?expand=body.storage"

    # 构建认证头
    # 对于云端Confluence，使用API令牌
    # 对于自托管Confluence，使用用户名和密码
    headers = {
        "Accept": "application/json",
        "Authorization": f"Basic {base64.b64encode(f'{API_USERNAME}:{API_TOKEN}'.encode()).decode()}"
    }

    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status() # 检查HTTP请求是否成功
        data = response.json()

        # 提取页面的存储格式内容
        storage_content = data.get('body', {}).get('storage', {}).get('value')
        if storage_content:
            return storage_content
        else:
            print(f"Page {page_id} has no storage content or content is empty.")
            return None
    except requests.exceptions.RequestException as e:
        print(f"Error fetching Confluence page {page_id}: {e}")
        return None

def extract_table_data(html_content):
    """
    从HTML内容中解析并提取所有表格数据。
    """
    if not html_content:
        return []

    soup = BeautifulSoup(html_content, 'html.parser')
    tables = soup.find_all('table')

    all_extracted_tables = []

    for i, table in enumerate(tables):
        table_data = []
        rows = table.find_all('tr')

        # 提取表头
        header_row = rows[0] if rows else None
        headers = [th.get_text(strip=True) for th in header_row.find_all(['th', 'td'])] if header_row else []
        if headers:
            table_data.append(headers)

        # 提取数据行
        for row in rows[1:]: # 跳过表头行
            cols = row.find_all(['td', 'th']) # td for data, th for potential row headers
            cols = [ele.get_text(strip=True) for ele in cols]
            table_data.append(cols)

        if table_data:
            print(f"\n--- Extracted Table {i+1} ---")
            for row in table_data:
                print(row)
            all_extracted_tables.append(table_data)

    return all_extracted_tables

if __name__ == "__main__":
    page_html = get_confluence_page_content(PAGE_ID)
    if page_html:
        extracted_tables = extract_table_data(page_html)
        if extracted_tables:
            print(f"\nSuccessfully extracted {len(extracted_tables)} table(s) from Confluence page {PAGE_ID}.")
        else:
            print(f"No tables found on Confluence page {PAGE_ID}.")
    else:
        print(f"Could not retrieve content for Confluence page {PAGE_ID}.")