ubuntu server系统文本转pdf

下面是通过软件实现方法：

使用soffice软件的转换功能实现需求

环境安装：

sudo apt install libreoffice-writer

如果出现没安装java的warning那么执行下面的命令：
sudo apt install default-jre
sudo apt install libreoffice-java-common

转换命令：

soffice --convert-to pdf 输入文件.txt --outdir 输出目录    #会生成输出目录下同名的.pdf文件
soffice --convert-to pdf 输入文件.txt   #会生成当前目录下同名的.pdf文件

python实现方法：

之前使用python的库来实现此需求，但是比较繁琐，效果不好，要调整每一页的大小和坐标，所以转向使用现成的软件通过命令行转换，效果能满足需要。

python库的安装：

pip install pdfminer PyPDF2 reportlab -i https://pypi.tuna.tsinghua.edu.cn/simple

pdf转换代码：

# -*- coding: UTF-8 -*-
import sys
import string
import fitz

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.lib.colors import HexColor
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

def create_pdf(input_text, output_file):
    pdfmetrics.registerFont(TTFont('msyh', 'msyh.ttf'))  # 注册字体
    c = canvas.Canvas(output_file, pagesize=letter)
    width, height = letter
    c.setFont('msyh', 10)
    c.setFillColor(HexColor(0x666666))
    text = c.beginText(50, height-50)
    text.setFont('msyh', 12)
    text.setFillColor(HexColor(0x333333))
    lines = input_text.split('\n')
    for line in lines:
        text.textLine(line)
    c.drawText(text)
    c.save()


if __name__ == "__main__":
    text = "这是一段测试文本。" * 1000
    create_pdf(text, "output.pdf")
    

PDF增加文字水印代码：

# -*- coding: UTF-8 -*-
import sys
import string
import fitz

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.lib.colors import HexColor
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont


def add_watermark(input_file, output_file, watermark):
    from PyPDF2 import PdfFileWriter, PdfFileReader,PdfReader,PdfWriter
    from reportlab.pdfgen import canvas
    from reportlab.lib.pagesizes import letter
    from io import BytesIO

    packet = BytesIO()
    can = canvas.Canvas(packet, pagesize=letter)
    width, height = letter
    can.rotate(15)
    can.setFont('msyh', 30)
    can.setFillColor(HexColor(0xFF00FF))
    
    can.drawString(width/2, height/2, watermark)
    can.drawString(width/3, height/4, watermark)
    can.drawString(width/3, (height/4)*3, watermark)
    can.save()

    packet.seek(0)
   
    new_pdf = PdfReader(packet)
    existing_pdf = PdfReader(open(input_file, "rb"))

    output = PdfWriter()
    for i in range(len(existing_pdf.pages)):
        page = existing_pdf.pages[i]
        watermark = new_pdf.pages[0]
        page.merge_page(watermark)
        output.add_page(page)

    with open(output_file, "wb") as outputStream:
        output.write(outputStream)

if __name__ == "__main__":
    pdfmetrics.registerFont(TTFont('msyh', 'msyh.ttf'))  # 注册字体
    add_watermark("input.pdf", "input_watermark.pdf", "版权所有")
    

PDF增加图像水印代码：

# -*- coding: UTF-8 -*-
import sys
import fitz
import string

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.lib.colors import HexColor
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

def add_watermark(input_file, output_file, watermark):
    from PyPDF2 import PdfFileWriter, PdfFileReader,PdfReader,PdfWriter
    from reportlab.pdfgen import canvas
    from reportlab.lib.pagesizes import letter
    from io import BytesIO

    packet = BytesIO()
    can = canvas.Canvas(packet, pagesize=letter)
    width, height = letter
    can.setFillColor(HexColor(0xFF00FF))
    can.setFillAlpha(0.5)
    can.drawImage(watermark, 0, 0, width, height)
    can.save()

    packet.seek(0)
    
    new_pdf = PdfReader(packet)
    existing_pdf = PdfReader(open(input_file, "rb"))

    output = PdfWriter()

    for i in range(len(existing_pdf.pages)):
        page = existing_pdf.pages[i]
        watermark = new_pdf.pages[0]
        page.merge_page(watermark)
        output.add_page(page)

    with open(output_file, "wb") as outputStream:
        output.write(outputStream)

if __name__ == "__main__":
    pdfmetrics.registerFont(TTFont('msyh', 'msyh.ttf'))  # 注册字体
    #pdfwatermark.png 为自定义背景图片
    add_watermark("input.pdf", "input_watermark.pdf", "pdfwatermark.png")