python—pdf模块

相关模块

 

提取pdf文字

pdfplumber.open(PDF路径)

pdf.pages[页数]

pdf.extract_text()

#读取第一页

import pdfplumber

with pdfplumber.open('Netease Q2 2019 Earnings Release-Final.pdf') as pdf:
	first_page = pdf.pages[0]
	print(first_page.extract_text())

sublime可能会出现

        UnicodeEncodeError: 'gbk' codec can't encode character '\u2022' in position 590: illegal multibyte sequence

用vscode就好了

 

#读取全部页

import pdfplumber

with pdfplumber.open('Netease Q2 2019 Earnings Release-Final.pdf') as pdf:
	for page in pdf.pages:
		print(page.extract_text())

 

分割pdf

PdfFileReader() , PdfFileWriter()

from PyPDF2 import PdfFileReader,PdfFileWriter
import os

os.mkdir('分割后的pdf文件')
pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
for page in range(pdf_reader.getNumPages()):
	pdf_writer = PdfFileWriter()
	pdf_writer.addPage(pdf_reader.getPage(page))  #getpage函数获得具体的某一页的内容
	with open(f'./分割后的pdf文件/Netease Q2 2019 Earnings {page}.pdf','wb')as out:
		pdf_writer.write(out)

 

合并pdf文件

from PyPDF2 import PdfFileReader,PdfFileWriter

pdf_writer = PdfFileWriter()
for page in range(16):
	pdf_reader = PdfFileReader(f'./分割后的pdf文件/Netease Q2 2019 Earnings {page}.pdf')
	for page in range(pdf_reader.getNumPages()):
		pdf_writer.addPage(pdf_reader.getPage(page))

with open('merged.pdf','wb')as out:
	pdf_writer.write(out)

 

旋转pdf

.rotateClockwise(90的倍数)     顺时针旋转

.rotateCounterClockwise(90的倍数)    逆时针旋转

from PyPDF2 import PdfFileReader,PdfFileWriter

pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()
page = pdf_reader.getPage(0).rotateClockwise(90)
pdf_writer.addPage(page)
page = pdf_reader.getPage(1).rotateCounterClockwise(90)
pdf_writer.addPage(page)
with open('rotated.pdf','wb') as out:
	pdf_writer.write(out)

 

排序pdf

直接按照期望的顺序添加页面即可，此处例子为倒序排列

from PyPDF2 import PdfFileReader,PdfFileWriter

pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()-1, -1 ,-1):
	pdf_writer.addPage(pdf_reader.getPage(page))

with open('ordered.pdf','wb') as out:
	pdf_writer.write(out)

 

pdf添加水印

首先制作水印文件

先拿word制作一个只有水印的页面，放在你想放水印的位置，保存为pdf

然后合并pdf

打开水印pdf文件和要加水印的pdf文件，再创建一个pdf写入器

然后合并pdf水印

对每一页都进行合并水印的操作，注意.mergePage()方法合成的页面顺序

下面的内容.mergePage(出现在上面的内容)

from PyPDF2 import PdfFileReader,PdfFileWriter
from copy import copy

watermark_pdf = PdfFileReader('mark.pdf')
watermark_page = watermark_pdf.getPage(0)

pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()

for page in range(pdf_reader.getNumPages()):
	original_page = pdf_reader.getPage(page)
	new_page = copy(watermark_page)
	new_page.mergePage(original_page)
	pdf_writer.addPage(new_page)

with open('watermark.pdf','wb') as out:
	pdf_writer.write(out)

 

pdf加密

pdf_writer.encrypt(密码)

from PyPDF2 import PdfFileReader,PdfFileWriter


pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()

for page in range(pdf_reader.getNumPages()):
	pdf_writer.addPage(pdf_reader.getPage(page))

pdf_writer.encrypt('hxx')
with open('encrypted.pdf','wb') as out:
	pdf_writer.write(out)

 

解密pdf

pdf_reader.decrypt(密码)

from PyPDF2 import PdfFileReader,PdfFileWriter


pdf_reader = PdfFileReader('encrypted.pdf')
pdf_reader.decrypt('hxx')
pdf_writer = PdfFileWriter()

for page in range(pdf_reader.getNumPages()):
	pdf_writer.addPage(pdf_reader.getPage(page))


with open('decrypted.pdf','wb') as out:
	pdf_writer.write(out)