Question

我有一些代码可以读取Word文档中的表格并从中生成数据框。

import numpy as np
import pandas as pd
from docx import Document

####    Time for some old fashioned user functions    ####
def make_dataframe(f_name, table_loc):
    document = Document(f_name)
    tables = document.tables[table_loc]

    for i, row in enumerate(tables.rows):
        text = (cell.text for cell in row.cells)
        if i == 0:
            keys = tuple(text)
            continue

        row_data = dict(zip(keys, text))
        data.append(row_data)
    df = pd.DataFrame.from_dict(data)
    return df


SHRD_filename = "SHRD - 12485.docx"
SHDD_filename = "SHDD - 12485.docx"

df_SHRD = make_dataframe(SHRD_filename,30)
df_SHDD = make_dataframe(SHDD_filename,-60)

因为文件不同（例如SHRD有32个表，我要找的是倒数第二个，但是SHDD文件有280个表，我要找的那个是结尾的第60个。但情况可能并非总是如此。

如何搜索文档中的表格并开始处理cell[0,0] = 'Tag Numbers'的表格。

Answer 1

您可以遍历表并检查第一个单元格中的文本。我修改了输出以返回数据帧列表，以防万一找到多个表。如果没有表符合标准，它将返回一个空列表。

def make_dataframe(f_name, first_cell_string='tag number'):
    document = Document(f_name)

    # create a list of all of the table object with text of the
    # first cell equal to `first_cell_string`
    tables = [t for t in document.tables 
              if t.cell(0,0).text.lower().strip()==first_cell_string]

    # in the case that more than one table is found 
    out = []
    for table in tables:
        for i, row in enumerate(table.rows):
            text = (cell.text for cell in row.cells)
            if i == 0:
                keys = tuple(text)
                continue

            row_data = dict(zip(keys, text))
            data.append(row_data)
        out.append(pd.DataFrame.from_dict(data))
    return out

在Word表格中搜索某些文本Python docx

1 个答案: