如何使用 google docx API 和 Python 在 google 文档中对齐 table

Question

我有添加 table 无边框的解决方案，但我在索引方面仍然遇到问题。我想按以下顺序在文档中插入数据 (function - insert_data(file_id)) -

在文档中插入图像（索引 = 1）
在文档中插入文本（索引 = 2）
在具有不可见边框（索引 = 3）的文档中插入 table
在文档中插入文本（索引 = 4）
再次在文档中插入 table 具有不可见边框（索引 = 5）
插入新行（索引 = 6）
在文档中插入图像（索引 = 7）

我正在尝试的代码是-

import io
from gdoctableapppy import gdoctableapp

SERVICE_FILENAME = 'C:/Users/XYZ/Testpython/service_account.json'  # set path to service account filename

from googleapiclient.discovery import build
from google.oauth2 import service_account
from googleapiclient.http import MediaIoBaseDownload, MediaFileUpload

credentials = service_account.Credentials.from_service_account_file(SERVICE_FILENAME,
                                                                    scopes=['https://www.googleapis.com/auth/drive',
                                                                            'https://www.googleapis.com/auth/documents']
                                                                    )
docs = build('docs', 'v1', credentials=credentials)
drive = build('drive', 'v3', credentials=credentials)


def create_file(file_name):
    file_metadata = {
        "title": file_name,
        "body": {}
    }

    file = docs.documents().create(body=file_metadata).execute()
    print('File ID: %s' % file.get('documentId'))
    file_id = file.get('documentId')
    try:
        permission = {
            "role": "writer",
            "type": "user",
            'emailAddress': 'xyz@gmail.com'
        }
        result = drive.permissions().create(fileId=file_id, body=permission).execute()
        print(result)
        return file_id
    except Exception as e:
        print('An error occurred:', e)
    return None


def insert_data(file_id):
    requests = []
    values = [['Name of the Client/Organization', 'XYZ'], ['Industry', 'Software']]
    requests.append(insert_table_data(file_id, values, index=3))
    values2 = [['Country', 'India'], ['State', 'UP']]
    requests.append(insert_table_data(file_id, values2, index=5))
    requests.append(insert_image(index=1))
    requests.append(insert_text(2, '\ntext\n'))
    requests.append(insert_text(4, '\nDemo text\n'))
    requests.append(insert_text(6, '\n'))
    requests.append(insert_image(index=7))


    result = docs.documents().batchUpdate(documentId=file_id, body={'requests': requests}).execute()


def insert_image(index):
    image_data = {
        'insertInlineImage': {
            'location': {
                'index': index
            },
            'uri':
                'https://www.oberlo.com/media/1603970279-pexels-photo-3.jpg?fit=max&fm=jpg&w=1824',
            'objectSize': {
                'height': {
                    'magnitude': 350,
                    'unit': 'PT'
                },
                'width': {
                    'magnitude': 350,
                    'unit': 'PT'
                }
            }

        }
    }
    return image_data


def insert_text(index, text):
    text_data = {
        "insertText":
            {
                "text": text,
                "location":
                    {
                        "index": index
                    }
            }
    }

    return text_data


def insert_table_data(file_id, values, index):
    documentId = file_id
    resource = {
        "oauth2": credentials,
        "documentId": documentId,
        "rows": len(values),
        "columns": len(values[0]),
        # "append": True,
        "createIndex": index,
        "values": values,
    }
    gdoctableapp.CreateTable(resource)
    resource = {
        "oauth2": credentials,
        "documentId": documentId,
    }
    res = gdoctableapp.GetTables(resource)
    obj = {"color": {"color": {}}, "dashStyle": "SOLID", "width": {"magnitude": 0, "unit": "PT"}}
    data = {
        "updateTableCellStyle": {
            "tableCellStyle": {
                "borderBottom": obj,
                "borderTop": obj,
                "borderLeft": obj,
                "borderRight": obj,
            },
            "tableStartLocation": {
                "index": res['tables'][-1]['tablePosition']['startIndex']
            },
            "fields": "borderBottom,borderTop,borderLeft,borderRight"
        }
    }
    # docs.documents().batchUpdate(documentId=documentId, body={'requests': requests}).execute()
    return data


def download_as_docx(file_id):
    results = drive.files().get(fileId=file_id, fields="id, name, mimeType, createdTime").execute()
    docMimeType = results['mimeType']
    mimeTypeMatchup = {
        "application/vnd.google-apps.document": {
            "exportType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "docExt": "docx"
        }
    }
    exportMimeType = mimeTypeMatchup[docMimeType]['exportType']
    # docExt = mimeTypeMatchup[docMimeType]['docExt']
    docName = results['name']
    request = drive.files().export_media(fileId=file_id,
                                         mimeType=exportMimeType)  # Export formats : https://developers.google.com/drive/api/v3/ref-export-formats
    # fh = io.FileIO(docName + "." + docExt, mode='w')
    fh = io.FileIO(docName, mode='w')
    downloader = MediaIoBaseDownload(fh, request)
    done = False
    while done is False:
        status, done = downloader.next_chunk()
        print("Download %d%%." % int(status.progress() * 100))


def download_as_pdf(file_id, file_name):
    request = drive.files().export_media(fileId=file_id,
                                         mimeType='application/pdf')
    fh = io.BytesIO()
    downloader = MediaIoBaseDownload(fh, request)
    done = False
    while done is False:
        status, done = downloader.next_chunk()
        print("Download %d%%." % int(status.progress() * 100))
    fh.seek(0)
    filename = file_name.split('.docx')[0] + '.pdf'
    with open(filename, 'wb') as fx:
        fx.write(fh.getvalue())


def delete_gdrive_file(file_id):
    """Deleted file on Google Drive
    :param file_id: ID of Google Drive file
    """
    response = drive.files().delete(fileId=file_id).execute()
    print(response)


if __name__ == '__main__':
    file_name = 'Data.docx'
    file_id = create_file(file_name)
    insert_data(file_id)
    download_as_docx(file_id)
    download_as_pdf(file_id, file_name)
    delete_gdrive_file(file_id)

错误：

returned "Invalid requests[0].insertTable: Index 4 must be less than the end index of the referenced segment, 2.". Details: "Invalid requests[0].insertTable: Index 4 
must be less than the end index of the referenced segment, 2.">

我猜 table 的结束索引变为 67，但即使我尝试在索引 68 处插入新数据，它要么追加到 table 的最后一个单元格中，要么抛出索引有时会出错。我应该在 google 文档中使整个数据插入流动态化。

Answer 1

修改点：

库 gdoctableapp 通过一次调用创建 table。这样，当您请求问题的流程时，索引会更改为 tables。我认为这就是您遇到问题的原因。

这样的话，下面的修改怎么样？

修改后的脚本：

请修改insert_table_data如下。

def insert_table_data(file_id, values, index):
    documentId = file_id
    resource = {
        "oauth2": credentials,
        "documentId": documentId,
        "rows": len(values),
        "columns": len(values[0]),
        # "append": True,
        "createIndex": index,
        "values": values,
    }
    gdoctableapp.CreateTable(resource)

另外，请修改insert_data如下。

def insert_data(file_id):
    # Insert texts and images.
    index = 1
    requests = []
    requests.append(insert_image(index))
    index += 1
    text1 = '\ntext\n'
    requests.append(insert_text(index, text1))
    index += len(text1)
    table1 = index
    text2 = '\nDemo text\n'
    requests.append(insert_text(index, text2))
    index += len(text2)
    table2 = index
    text3 = '\n'
    requests.append(insert_text(index, text3))
    index += len(text3)
    requests.append(insert_image(index))
    docs.documents().batchUpdate(documentId=file_id, body={'requests': requests}).execute()

    # Create tables.
    values2 = [['Country', 'India'], ['State', 'UP']]
    insert_table_data(file_id, values2, table2)
    values1 = [['Name of the Client/Organization', 'XYZ'], ['Industry', 'Software']]
    insert_table_data(file_id, values1, table1)

    # Remove borders of tables.
    resource = {"oauth2": credentials, "documentId": file_id}
    res = gdoctableapp.GetTables(resource)
    obj = {"color": {"color": {}}, "dashStyle": "SOLID", "width": {"magnitude": 0, "unit": "PT"}}
    reqs = []
    for e in res['tables']:
        data = {
            "updateTableCellStyle": {
                "tableCellStyle": {
                    "borderBottom": obj,
                    "borderTop": obj,
                    "borderLeft": obj,
                    "borderRight": obj,
                },
                "tableStartLocation": {
                    "index": e['tablePosition']['startIndex']
                },
                "fields": "borderBottom,borderTop,borderLeft,borderRight"
            }
        }
        reqs.append(data)
    docs.documents().batchUpdate(documentId=file_id, body={'requests': reqs}).execute()

在此修改中，我将文本和图像以及 table 分开。这样就可以正确的检索出tables的索引。

注：

此修改后的脚本是针对您的问题。所以当你的实际情况与你的问题不同时，这个修改后的脚本可能无法直接使用。所以请注意这一点。

如何使用 google docx API 和 Python 在 google 文档中对齐 table

How to align table in a google document using google docx API and Python

python

google-docs-api

google-drive-api

google-api-python-client

google-developers-console

修改点：

修改后的脚本：

注：