将Python Pandas DataFrame写入Word文档

Question

我正在创建一个Python生成的使用Pandas DataFrames的报告。目前我使用的是DataFrame.to_string()方法。但是，这将以字符串的形式写入文件。有没有办法让我在保持表格的同时实现这一点，这样我就可以使用表格格式化了。

代码：

SEMorgkeys = client.domain_organic(url, database = "us", display_limit = 10, export_columns=["Ph,Pp,Pd,Nq,Cp,Ur,Tr"])
org_df = pd.DataFrame(SEMorgkeys)

f = open(name, 'w')
f.write("\nOrganic:\n")
f.write(org_df.to_string(index=False,justify="left"))
f.close()

当前打印输出(字符串形式)：

CPC    Keyword                        Position Difference Previous Position Search Volume Traffic (%) Url                                               
75.92       small business factoring   0                   1                 210          11.69       https://www..com/small-business-f...
80.19              factoring company   0                   8                1600           5.72       https://www..com/factoring-vs-ban...

Answer 1

您可以使用python-docx库将该表直接写入.docx文件。

如果您使用的是Conda或使用Anaconda安装的Python，则可以从命令行运行该命令：

conda install python-docx --channel conda-forge

或者从命令行执行pip install：

pip install python-docx

安装后，我们可以使用它打开文件，添加表，然后用数据框数据填充表的单元格文本。

import docx
import pandas as pd

# i am not sure how you are getting your data, but you said it is a
# pandas data frame
df = pd.DataFrame(data)

# open an existing document
doc = docx.Document('./test.docx')

# add a table to the end and create a reference variable
# extra row is so we can add the header row
t = doc.add_table(df.shape[0]+1, df.shape[1])

# add the header rows.
for j in range(df.shape[-1]):
    t.cell(0,j).text = df.columns[j]

# add the rest of the data frame
for i in range(df.shape[0]):
    for j in range(df.shape[-1]):
        t.cell(i+1,j).text = str(df.values[i,j])

# save the doc
doc.save('./test.docx')

Answer 2

def doctable(data, tabletitle, pathfile):
    from docx import Document
    from docx.shared import Pt, Mm
    import pandas as pd
    document = Document()
    section = document.sections[0]
    section.page_height = Mm(297)
    section.page_width = Mm(210)
    section.left_margin = Mm(20)
    section.right_margin = Mm(20)
    section.top_margin = Mm(20)
    section.bottom_margin = Mm(20)
    section.header_distance = Mm(12.7)
    section.footer_distance = Mm(12.7)
    data = pd.DataFrame(data) # My input data is in the 2D list form
    document.add_heading(tabletitle)
    table = document.add_table(rows=(data.shape[0]), cols=data.shape[1]) # First row are table headers!
    table.allow_autofit = True
    table.autofit = True
    for i, column in enumerate(data) :
        for row in range(data.shape[0]) :
            table.cell(row, i).text = str(data[column][row])
    document.save(pathfile)
    return 0

Answer 3

如果你愿意，可以用这个来证明它：

from docx import Document
import pandas as pd

def df_to_word(data: dict, report_name:str) -> docx.Document:
    assert type(data) == dict, 'data has to be dict'
    assert '.docx' in report_name, 'report_name has to be a .docx file'
    df = pd.DataFrame(data)
    doc = docx.Document()

    table = doc.add_table(df.shape[0]+1, df.shape[1])

    for j in range(df.shape[-1]):
        table.cell(0,j).text = df.columns[j]

    for i in range(df.shape[0]):
        for j in range(df.shape[-1]):
            table.cell(i+1,j).text = str(df.values[i,j])

    doc.save(f'./{report_name}')


data = {
  "calorierbes": [420, 380, 390],
  "duratierbn": [50, 40, 45],
  "durationverg": [50, 40, 45],
  "duratiorgern": [50, 40, 45],
  "calorieers": [420, 380, 390],
  "calorierbers": [420, 380, 390],
  "calorierbes": [420, 380, 390]
}
df_to_word(data, 'report_4.docx')