Linux上使用python处理docx转pdf教程
今天在使用flask将生成好的docx文档转化为pdf的过程中，遇到了一些问题，本来在windows上转化的好好的，但是到了Linux上却是直接报错显示ModuleNotFoundError: No module named 'win32com'。
很明显他说的是在Linux系统下并没有win32com这个模块，所以通过百度发现python使用pdf2docx这个包将docx转化为pdf的使用环境必须为windows，那么在Linux上我们应该使用什么来进行文档的转化呢？百度后发现了一个解决方法：传送门。
但是上述代码的时间应该是有段时间了，pywpsrpc的代码已经更新了，目前的最新使用代码可以去github上访问官方文档。
需要注意的是需要安装好qt5-default, 我使用的Linux版本是Ubuntu23.04，在安装的时候会报错，所以百度后提供了别人的解决方案粘在下面。
以下是代码解决方案，代码来自于官方，我仅仅调用了其中的函数：
#!/usr/bin/python3
#**
# * Copyright (c) 2020 Weitian Leung
# *
# * This file is part of pywpsrpc.
# *
# * This file is distributed under the MIT License.
# * See the LICENSE file for details.
# *
#*
import os
import sys
import argparse
from pywpsrpc.rpcwpsapi import (createWpsRpcInstance, wpsapi)
from pywpsrpc.common import (S_OK, QtApp)
formats = {
"doc": wpsapi.wdFormatDocument,
"docx": wpsapi.wdFormatXMLDocument,
"rtf": wpsapi.wdFormatRTF,
"html": wpsapi.wdFormatHTML,
"pdf": wpsapi.wdFormatPDF,
"xml": wpsapi.wdFormatXML,
}
class ConvertException(Exception):
def __init__(self, text, hr):
self.text = text
self.hr = hr
def __str__(self):
return """Convert failed:
Details: {}
ErrCode: {}
""".format(self.text, hex(self.hr & 0xFFFFFFFF))
def convert_to(paths, format, abort_on_fails=False):
hr, rpc = createWpsRpcInstance()
if hr != S_OK:
raise ConvertException("Can't create the rpc instance", hr)
hr, app = rpc.getWpsApplication()
if hr != S_OK:
raise ConvertException("Can't get the application", hr)
# we don't need the gui
app.Visible = False
docs = app.Documents
def _handle_result(hr):
if abort_on_fails and hr != S_OK:
raise ConvertException("convert_file failed", hr)
for path in paths:
abs_path = os.path.realpath(path)
if os.path.isdir(abs_path):
files = [(os.path.join(abs_path, f)) for f in os.listdir(abs_path)]
for file in files:
hr = convert_file(file, docs, format)
_handle_result(hr)
else:
hr = convert_file(abs_path, docs, format)
_handle_result(hr)
app.Quit()
def convert_file(file, docs, format):
hr, doc = docs.Open(file, ReadOnly=True)
if hr != S_OK:
return hr
out_dir = os.path.dirname(os.path.realpath(file)) + "/out"
os.makedirs(out_dir, exist_ok=True)
# you have to handle if the new_file already exists
new_file = out_dir + "/" + os.path.splitext(os.path.basename(file))[0] + "." + format
ret = doc.SaveAs2(new_file, FileFormat=formats[format])
# always close the doc
doc.Close(wpsapi.wdDoNotSaveChanges)
return ret
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--format", "-f",
required=True,
metavar="<DOC_TYPE>",
choices=["doc", "docx", "rtf", "html", "pdf", "xml"],
help="convert to <DOC_TYPE>,")
parser.add_argument("--abort", "-a",
action="store_true",
help="abort if one convert fails")
parser.add_argument("path",
metavar="<path>",
nargs='+',
help="the <path> can be one or more file or folder")
args = parser.parse_args()
qApp = QtApp(sys.argv)
try:
convert_to(args.path, args.format, args.abort)
except ConvertException as e:
print(e)
if __name__ == "__main__":
main()
上面是官方代码，下面是我的flask调用函数：
from .convertto import convert_to
@medical.route('/insertMoadlDocx', methods=['POST', 'GET'])
@login_required
def insertModalDocx():
try:
image_id = request.form.get('image_id')
# 查询相关信息
medical_picture_info = MedicalPicture.query.filter_by(id=image_id).first()
user_info = User.query.filter_by(id=medical_picture_info.user_id).first()
user_message_info = UserMessage.query.filter_by(user_id=user_info.id).first()
modal_list_info = ModalList.query.filter_by(image_id=image_id).all()
# 读取docx模板
template_path = os.path.join(current_app.root_path, 'static', 'word', 'template.docx')
doc = Document(template_path)
# 替换表格占位符
placeholders = {
'{{username}}': user_info.username,
'{{name}}': user_message_info.name,
'{{sex}}': '男' if user_message_info.sex == 1 else '女',
'{{age}}': str(user_message_info.age),
'{{imageType}}': medical_picture_info.imageType,
'{{uploadTime}}': str(medical_picture_info.uploadTime),
'{{phone}}': user_message_info.phone,
'{{idCard}}': str(user_message_info.idCard),
'{{asset}}': user_message_info.asset
}
for table in doc.tables:
for row in table.rows:
for cell in row.cells:
for key, value in placeholders.items():
if key in cell.text:
# 保留原始字体格式
for paragraph in cell.paragraphs:
for run in paragraph.runs:
if key in run.text:
run.text = run.text.replace(key, value)
# 循环插入ModalList信息
for index, item in enumerate(modal_list_info):
if index == 0:
# 如果是第一条记录，直接替换原有的占位符
for paragraph in doc.paragraphs:
if '{{description}}' in paragraph.text:
paragraph.text = paragraph.text.replace('{{description}}','\t' + item.description)
if '{{image}}' in paragraph.text:
# 删除原有的占位符
paragraph.text = paragraph.text.replace('{{image}}', '')
# 添加图片
run = paragraph.add_run()
image_path = os.path.join(current_app.root_path, item.image.lstrip('/'))
run.add_picture(image_path, width=docx.shared.Cm(14.5), height=docx.shared.Cm(5.2))
else:
# 如果不是第一条记录，在报告医师信息的上一行插入新段落并插入数据
paragraphs_copy, paragraphs_iter = tee(doc.paragraphs)
for i, paragraph in enumerate(paragraphs_iter):
if '报告医师：' in paragraph.text:
# 在报告医师信息的上一行插入空白行
doc.paragraphs[i - 1].insert_paragraph_before()
# 在空白行之后插入新段落
new_paragraph = doc.paragraphs[i].insert_paragraph_before()
# 插入诊断描述和图片信息
new_run1 = new_paragraph.add_run(f"诊断描述：\n")
new_run1.font.name = '宋体' # 设置字体为宋体
new_run1.font.size = Pt(12) # 设置字号为12磅
new_paragraph.add_run('\t') # 添加制表符实现缩进
new_paragraph.add_run(item.description)
new_run2 = new_paragraph.add_run(f"\n诊断图片：\n") # 设置字体为宋体
new_run2.font.name = '宋体' # 设置字体为宋体
new_run2.font.size = Pt(12) # 设置字号为12磅
image_path = os.path.join(current_app.root_path, item.image.lstrip('/'))
new_paragraph.add_run().add_picture(image_path, width=docx.shared.Cm(14.5),
height=docx.shared.Cm(5.2))
break
# 添加一个空行，用于分隔不同的记录
doc.add_paragraph()
docx_filename = f"{image_id}_{user_message_info.name}_{medical_picture_info.imageType}.docx"
folder_name = os.path.splitext(docx_filename)[0] # 去掉文件尾缀
docx_folder = os.path.join(current_app.root_path, 'static', 'word', folder_name) # 使用去掉尾缀后的文件名作为文件夹名
# 确保文件夹存在，如果不存在则创建
if not os.path.exists(docx_folder):
os.makedirs(docx_folder)
# 保存 DOCX 文件
docx_path = os.path.join(docx_folder, docx_filename)
doc.save(docx_path)
# from win32com.client import pythoncom # 导入 pythoncom
# pythoncom.CoInitialize() # 初始化 COM 线程
# # 构建 PDF 文件路径
# pdf_filename = docx_filename.replace('.docx', '.pdf')
# pdf_folder = docx_folder # 与 DOCX 文件相同的目录
# pdf_path = os.path.join(pdf_folder, pdf_filename)
#
# # 将 DOCX 文件转换为 PDF
# convert(docx_path, pdf_path)
# 创建 PDF 文件
pdf_filename = docx_filename.replace('.docx', '.pdf')
convert_to([docx_path], "pdf")
# 构建目标文件的路径
docx_save_path = os.path.join('/static', 'word', folder_name, docx_filename)
pdf_save_path = os.path.join('/static', 'word', folder_name, 'out', pdf_filename)
# 替换所有路径中的反斜杠为正斜杠
docx_save_path = docx_save_path.replace('\\', '/')
pdf_save_path = pdf_save_path.replace('\\', '/')
# 将路径保存到数据库中
medical_picture_info.pdf_path = pdf_save_path
medical_picture_info.docx_path = docx_save_path
db.session.commit()
# 返回 JSON 响应
return jsonify({'message': '报告生成成功!'}), 200
except Exception as e:
# 返回 JSON 响应，表示修改失败
return jsonify({'error': str(e)}), 500
