YueHuihui
/
RAGflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #157 from xinsenyan/main 

refactor: 更新解析excel的函数，适配更复杂的表格结构
This commit is contained in:
zstar 2025-06-09 19:07:56 +08:00 committed by GitHub
parent cd2f479bb4 d5fbd8d620
commit 0640f973aa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
management/server/services/knowledgebases/excel_parser.py
View File

@ -2,18 +2,19 @@ import pandas as pd
def parse_excel(file_path):
# 读取Excel文件
df = pd.read_excel(file_path)
# 获取表头
headers = df.columns.tolist()
# 读取所有工作表
all_sheets = pd.read_excel(file_path, sheet_name=None) # 读取所有sheet
blocks = []
for _, row in df.iterrows():
# 构建HTML表格
html_table = "<html><body><table><tr>{}</tr><tr>{}</tr></table></body></html>".format("".join(f"<td>{col}</td>" for col in headers), "".join(f"<td>{row[col]}</td>" for col in headers))
block = {"type": "table", "img_path": "", "table_caption": [], "table_footnote": [], "table_body": f"{html_table}", "page_idx": 0}
for sheet_name, df in all_sheets.items():
df = df.fillna(method="ffill") # 填充合并的单元格
headers = df.columns.tolist()
blocks.append(block)
for _, row in df.iterrows():
html_table = "<html><body><table><tr>{}</tr><tr>{}</tr></table></body></html>".format("".join(f"<td>{col}</td>" for col in headers), "".join(f"<td>{row[col]}</td>" for col in headers))
block = {"type": "table", "img_path": "", "table_caption": [f"Sheet: {sheet_name}"], "table_footnote": [], "table_body": f"{html_table}", "page_idx": 0}
blocks.append(block)
return blocks