hmo
04db423416
- 70 skills with code and documentation - Add .gitignore (ignore __pycache__, output/, temp/, venv/) - Clean up test intermediates and caches
266 lines
9.4 KiB
Python
266 lines
9.4 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""
|
|
文件读取工具 - 支持docx、xlsx、xls等二进制文件读取
|
|
解决中文编码问题
|
|
"""
|
|
|
|
import sys
|
|
import os
|
|
import zipfile
|
|
import re
|
|
import pandas as pd
|
|
|
|
|
|
def read_docx_and_save(file_path):
|
|
"""读取docx并保存为UTF-8文本文件"""
|
|
try:
|
|
import zipfile
|
|
import re
|
|
import os
|
|
|
|
with zipfile.ZipFile(file_path, "r") as z:
|
|
with z.open("word/document.xml") as f:
|
|
content = f.read()
|
|
|
|
# 尝试UTF-8，然后尝试GBK
|
|
try:
|
|
text = content.decode("utf-8", errors="strict")
|
|
except:
|
|
try:
|
|
text = content.decode("gbk", errors="ignore")
|
|
except:
|
|
text = content.decode("utf-8", errors="replace")
|
|
|
|
# 提取段落
|
|
paragraphs = re.findall(r"<w:t[^>]*>([^<]*)</w:t>", text)
|
|
|
|
content_lines = []
|
|
for p in paragraphs:
|
|
if p.strip():
|
|
content_lines.append(p)
|
|
|
|
# 读取表格
|
|
tables = re.findall(r"<w:tbl>(.*?)</w:tbl>", text, re.DOTALL)
|
|
for table in tables:
|
|
rows = re.findall(r"<w:tr>(.*?)</w:tr>", table, re.DOTALL)
|
|
for row in rows:
|
|
cells = re.findall(r"<w:tc>(.*?)</w:tc>", row, re.DOTALL)
|
|
row_data = []
|
|
for cell in cells:
|
|
cell_text = re.findall(r"<w:t[^>]*>([^<]*)</w:t>", cell)
|
|
if cell_text:
|
|
row_data.append("".join(cell_text).strip())
|
|
if row_data:
|
|
content_lines.append(" | ".join(row_data))
|
|
|
|
output = "\n".join(content_lines)
|
|
|
|
# 保存到文件
|
|
output_file = "temp/docx_output.txt"
|
|
os.makedirs("temp", exist_ok=True)
|
|
with open(output_file, "w", encoding="utf-8") as f:
|
|
f.write(output)
|
|
|
|
return f"[内容已保存到 temp/docx_output.txt]\n\n{output}"
|
|
|
|
except Exception as e:
|
|
return f"Error: {e}"
|
|
|
|
|
|
def read_xlsx(file_path, sheet_index=0, max_rows=20):
|
|
"""读取xlsx文件，中文正确显示（保存到文件）"""
|
|
try:
|
|
with zipfile.ZipFile(file_path, "r") as z:
|
|
# 读取sharedStrings - UTF-8编码
|
|
string_map = {}
|
|
if "xl/sharedStrings.xml" in z.namelist():
|
|
with z.open("xl/sharedStrings.xml") as f:
|
|
ss_content = f.read()
|
|
text = ss_content.decode("utf-8", errors="ignore")
|
|
strings = re.findall(r"<t>([^<]*)</t>", text)
|
|
for i, s in enumerate(strings):
|
|
string_map[i] = s
|
|
|
|
# 读取sheet
|
|
sheet_files = [
|
|
f
|
|
for f in z.namelist()
|
|
if f.startswith("xl/worksheets/sheet") and f.endswith(".xml")
|
|
]
|
|
if sheet_index >= len(sheet_files):
|
|
return f"Sheet index {sheet_index} out of range"
|
|
|
|
sheet_file = sheet_files[sheet_index]
|
|
with z.open(sheet_file) as f:
|
|
sheet_content = f.read().decode("utf-8", errors="ignore")
|
|
|
|
# 解析数据
|
|
rows = re.findall(
|
|
r'<row r="(\d+)"[^>]*>(.*?)</row>', sheet_content, re.DOTALL
|
|
)
|
|
|
|
result = [f"=== Sheet {sheet_index} ==="]
|
|
for row_num, row_content in rows[:max_rows]:
|
|
cells = re.findall(
|
|
r'<c r="([A-Z]+\d+)"[^>]*>(.*?)</c>', row_content, re.DOTALL
|
|
)
|
|
row_data = []
|
|
for cell_ref, cell_content in cells:
|
|
v_match = re.search(r"<v>([^<]*)</v>", cell_content)
|
|
t_match = re.search(r"<is><t[^>]*>([^<]*)</t></is>", cell_content)
|
|
|
|
if t_match:
|
|
val = t_match.group(1)
|
|
elif v_match:
|
|
v = v_match.group(1)
|
|
if 't="s"' in cell_content and v.isdigit():
|
|
idx = int(v)
|
|
val = string_map.get(idx, f"[str:{v}]")
|
|
else:
|
|
try:
|
|
val = str(int(v)) if "." not in v else str(float(v))
|
|
except:
|
|
val = v
|
|
else:
|
|
val = ""
|
|
|
|
if val:
|
|
row_data.append(val)
|
|
|
|
if row_data:
|
|
result.append(" | ".join(row_data))
|
|
|
|
output = "\n".join(result)
|
|
|
|
# 写入文件确保中文正确显示
|
|
output_file = f"temp/xlsx_output.txt"
|
|
os.makedirs("temp", exist_ok=True)
|
|
with open(output_file, "w", encoding="utf-8") as f:
|
|
f.write(output)
|
|
|
|
return f"[内容已保存到 temp/xlsx_output.txt]\n\n{output}"
|
|
|
|
except Exception as e:
|
|
return f"Error: {e}"
|
|
|
|
|
|
def read_xls(file_path, sheet_index=0, max_rows=20):
|
|
"""读取xls文件，处理中文编码"""
|
|
try:
|
|
# 首先尝试用pandas直接读取
|
|
df = pd.read_excel(file_path, sheet_name=sheet_index, nrows=max_rows)
|
|
|
|
# 转换为文本格式
|
|
result = [f"=== Sheet {sheet_index} ==="]
|
|
# 添加列名
|
|
result.append(" | ".join(str(col) for col in df.columns))
|
|
|
|
# 添加数据行
|
|
for idx, row in df.iterrows():
|
|
row_data = []
|
|
for val in row:
|
|
if pd.isna(val):
|
|
row_data.append("")
|
|
else:
|
|
row_data.append(str(val))
|
|
result.append(" | ".join(row_data))
|
|
|
|
output = "\n".join(result)
|
|
|
|
# 保存到文件
|
|
output_file = "temp/xls_output.txt"
|
|
os.makedirs("temp", exist_ok=True)
|
|
with open(output_file, "w", encoding="utf-8") as f:
|
|
f.write(output)
|
|
|
|
return f"[内容已保存到 temp/xls_output.txt]\n\n{output}"
|
|
|
|
except Exception as e:
|
|
# 如果pandas失败，尝试手动解析（可能是制表符分隔的csv）
|
|
try:
|
|
encodings = ["gbk", "utf-8", "latin1"]
|
|
for encoding in encodings:
|
|
try:
|
|
df = pd.read_csv(
|
|
file_path, encoding=encoding, sep="\t", nrows=max_rows
|
|
)
|
|
result = [f"=== Sheet {sheet_index} (CSV format) ==="]
|
|
result.append(" | ".join(str(col) for col in df.columns))
|
|
for idx, row in df.iterrows():
|
|
row_data = []
|
|
for val in row:
|
|
if pd.isna(val):
|
|
row_data.append("")
|
|
else:
|
|
row_data.append(str(val))
|
|
result.append(" | ".join(row_data))
|
|
output = "\n".join(result)
|
|
|
|
output_file = "temp/xls_output.txt"
|
|
os.makedirs("temp", exist_ok=True)
|
|
with open(output_file, "w", encoding="utf-8") as f:
|
|
f.write(output)
|
|
|
|
return f"[内容已保存到 temp/xls_output.txt]\n\n{output}"
|
|
except:
|
|
continue
|
|
return f"Error reading xls file: {e}"
|
|
except Exception as e2:
|
|
return f"Error: {e} | {e2}"
|
|
|
|
|
|
def list_sheets(file_path):
|
|
"""列出Excel所有sheet"""
|
|
try:
|
|
import pandas as pd
|
|
|
|
excel_file = pd.ExcelFile(file_path)
|
|
sheets = excel_file.sheet_names
|
|
return "可用Sheets:\n" + "\n".join(f"{i}: {s}" for i, s in enumerate(sheets))
|
|
except Exception as e:
|
|
return f"Error: {e}"
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print("用法:")
|
|
print(" python file_reader.py <file.docx>")
|
|
print(" python file_reader.py <file.xlsx> # 列出所有sheets")
|
|
print(" python file_reader.py <file.xlsx> <sheet_index> # 读取指定sheet")
|
|
print(" python file_reader.py <file.xlsx> <sheet_index> <max_rows>")
|
|
print(" python file_reader.py <file.xls> # 列出所有sheets")
|
|
print(" python file_reader.py <file.xls> <sheet_index> # 读取指定sheet")
|
|
print("\n示例:")
|
|
print(" python file_reader.py test.xlsx # 列出sheets")
|
|
print(" python file_reader.py test.xlsx 1 # 读取第2个sheet")
|
|
print(" python file_reader.py test.xlsx 1 30 # 读取前30行")
|
|
print(" python file_reader.py test.xls # 读取xls文件")
|
|
sys.exit(1)
|
|
|
|
file_path = sys.argv[1]
|
|
|
|
if not os.path.exists(file_path):
|
|
print(f"文件不存在: {file_path}")
|
|
sys.exit(1)
|
|
|
|
ext = os.path.splitext(file_path)[1].lower()
|
|
|
|
if ext == ".docx":
|
|
print(read_docx_and_save(file_path))
|
|
elif ext == ".xlsx":
|
|
if len(sys.argv) == 2:
|
|
print(list_sheets(file_path))
|
|
else:
|
|
sheet_index = int(sys.argv[2])
|
|
max_rows = int(sys.argv[3]) if len(sys.argv) > 3 else 20
|
|
print(read_xlsx(file_path, sheet_index, max_rows))
|
|
elif ext == ".xls":
|
|
if len(sys.argv) == 2:
|
|
print(list_sheets(file_path))
|
|
else:
|
|
sheet_index = int(sys.argv[2])
|
|
max_rows = int(sys.argv[3]) if len(sys.argv) > 3 else 20
|
|
print(read_xls(file_path, sheet_index, max_rows))
|
|
else:
|
|
print(f"不支持的文件类型: {ext}")
|