pyDoc/main.py

import json
import sys

from docx import Document
from docx.shared import Inches
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT

def get_command_argv_by_sys():
    # 默认值-用于测试
    template_path = "template.docx"
    #template_path = "test.docx"
    filename_path = "demo.docx"
    datafile_path = "data.json"
    #datafile_path = "data_1.json"
    cycle = 0
    # 读取参数
    number = len(sys.argv)
    if 2 == number:
        template_path = sys.argv[1]
    if 3 == number:
        template_path = sys.argv[1]
        filename_path = sys.argv[2]
    if 4 == number:
        template_path = sys.argv[1]
        filename_path = sys.argv[2]
        datafile_path = sys.argv[3]
    if 5 == number:
        template_path = sys.argv[1]
        filename_path = sys.argv[2]
        datafile_path = sys.argv[3]
        cycle = sys.argv[4]
    return template_path, filename_path, datafile_path,cycle


def read_data(filepath):
    content = []
    if filepath != "":
        try:
            with open(filepath, "r", encoding="utf-8") as file:
                content = json.load(file)
        finally:
            return content


def replace(template_path, filename_path, data_json):
    try:
        document_file = Document(template_path)
    except:
        return 2
    # 段落替换
    for paragraph in document_file.paragraphs:
        for datum in data_json:
            if datum["key"] in paragraph.text:
                if "text" == datum["type"]:
                    paragraph.text = paragraph.text.replace(datum["key"], datum["value"])
                elif "picture" == datum["type"]:
                    paragraph.clear()
                    paragraph.add_run().add_picture(datum["value"], width=Inches(datum["width"]))
                elif "number" == datum["type"]:
                    paragraph.text = paragraph.text.replace(datum["key"], str(datum["value"]))

    # 表格替换
    for table in document_file.tables:
        # 字段
        row = table.rows[0]
        group = None
        fields = []
        for cell in row.cells:
            split = cell.text.replace("}","").split(".")
            group = split[0] + "}"
            field = split[1]
            fields.append(field.strip())

        # 替换
        for datum in data_json:
            if datum["key"] in group:
                rows = len(table.rows)
                values = datum["value"]
                for z in range(0, len(values)):
                    if z < rows:
                       row = table.rows[z]
                    else:
                        row = table.add_row()

                    item = values[z]
                    for i in range(0, len(fields)):
                        field = fields[i]
                        if item.get(field) is not None:
                            row.cells[i].text = str(item.get(field))

    document_file.save(filename_path)
    return 0

def foreach(template_path, filename_path, data_json):
    try:
        document_file = Document(template_path)
    except:
        return 2

    placeholder = []
    loop = False
    i = 0
    for paragraph in document_file.paragraphs:
        text = paragraph.text
        if "$[" == text:
            loop = True
            paragraph.clear()
            p = paragraph._element
            p.getparent().remove(p)
            p._p = p._element = None
            continue
        elif "]$" == text:
            loop = False
            paragraph.clear()
            p = paragraph._element
            p.getparent().remove(p)
            p._p = p._element = None
            z = 0
            for datum in data_json:
                for item in placeholder:
                    key = item["paragraph"].text.replace("{", "").replace("}", "")
                    style = item["paragraph"].style
                    if key == datum["key"]:
                        if "text" == datum["type"]:
                            paragraph = document_file.add_paragraph(datum["value"], style=style)
                            paragraph._element.getparent().insert(z, paragraph._element)
                        elif "picture" == datum["type"]:
                            paragraph = document_file.add_paragraph(style=style)
                            paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
                            paragraph.add_run().add_picture(datum["value"], width=Inches(datum["width"]))
                            paragraph._element.getparent().insert(z, paragraph._element)
                        elif "number" == datum["type"]:
                            paragraph = document_file.add_paragraph(str(datum["value"]), style=style)
                            paragraph._element.getparent().insert(z, paragraph._element)
                    # else:
                    #     paragraph = document_file.add_paragraph(item["text"], style=style)
                    #     paragraph._element.getparent().insert(z, paragraph._element)
                z += 1

            placeholder = []



        if loop:
            placeholder.append({"paragraph": paragraph, "key": text.replace("{", "").replace("}", ""), "style": paragraph.style,"text":text, "index": i})
            p = paragraph._element
            p.getparent().remove(p)
            p._p = p._element = None
        else:
            if text.startswith("{") and text.endswith("}"):
                for datum in data_json:
                    if datum["key"] in text:
                        key = "{" + datum["key"] + "}"
                        if "text" == datum["type"]:
                            paragraph.text = paragraph.text.replace(key, datum["value"])
                        elif "picture" == datum["type"]:
                            paragraph.clear()
                            paragraph.add_run().add_picture(datum["value"], width=Inches(datum["width"]))
                        elif "number" == datum["type"]:
                            paragraph.text = paragraph.text.replace(key, str(datum["value"]))
        i += 1

    document_file.save(filename_path)
    return 0


def main():
    params = get_command_argv_by_sys()
    [template, filename, datafile, cycle] = params
    data = read_data(datafile)
    if len(data) == 0:
        return 1
    else:
        if cycle == 0:
            return replace(template, filename, data)
        else:
            return foreach(template, filename, data)

if __name__ == '__main__':
    print(main())