cd /data  && tar -xvf  PyPDF2-1.26.0.tar.gz

cd PyPDF2-1.26.0

python setup.py install

pip install pypdf2

#coding:utf-8

import importlib

import sys

import time

importlib.reload(sys)

time1 = time.time()

from pdfminer.pdfparser import PDFParser, PDFDocument

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

from pdfminer.converter import PDFPageAggregator

from pdfminer.layout import LTTextBoxHorizontal, LAParams

from pdfminer.pdfinterp import PDFTextExtractionNotAllowed

text_path = r'5b931164edc09a226b3a12c4.pdf'

def parse():

    '''解析PDF文本，并保存到TXT文件中'''

    fp = open(text_path, 'rb')

    # 用文件对象创建一个PDF文档分析器

    parser = PDFParser(fp)

    # 创建一个PDF文档

    doc = PDFDocument()

    # 连接分析器，与文档对象

    parser.set_document(doc)

    doc.set_parser(parser)

    # 提供初始化密码，如果没有密码，就创建一个空的字符串

    doc.initialize()

    # 检测文档是否提供txt转换，不提供就忽略

    if not doc.is_extractable:

        raise PDFTextExtractionNotAllowed

    else:

        # 创建PDF，资源管理器，来共享资源

        rsrcmgr = PDFResourceManager()

        # 创建一个PDF设备对象

        laparams = LAParams()

        device = PDFPageAggregator(rsrcmgr, laparams=laparams)

        # 创建一个PDF解释其对象

        interpreter = PDFPageInterpreter(rsrcmgr, device)

        # 循环遍历列表，每次处理一个page内容

        # doc.get_pages() 获取page列表

        for page in doc.get_pages():

            interpreter.process_page(page)

            # 接受该页面的LTPage对象

            layout = device.get_result()

            # 这里layout是一个LTPage对象 里面存放着 这个page解析出的各种对象

            # 一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等等

            # 想要获取文本就获得对象的text属性，

            for x in layout:

                if (isinstance(x, LTTextBoxHorizontal)):

                    with open(r'2.txt', 'a') as f:

                        results = x.get_text()

                        print(results)

                        f.write(results + "\n")

if __name__ == '__main__':

    parse()

    time2 = time.time()

    print("总共消耗时间为:", time2 - time1)

# coding:utf-8

import os

from PyPDF2 import PdfFileReader

from PyPDF2 import PdfFileWriter

def get_reader(filename, password):

    try:

        old_file = open(filename, 'rb')

        print('run  jiemi1')

    except Exception as err:

        print('文件打开失败！' + str(err))

        return None

    # 创建读实例

    pdf_reader = PdfFileReader(old_file, strict=False)

    # 解密操作

    if pdf_reader.isEncrypted:

        if password is None:

            print('%s文件被加密，需要密码！' % filename)

            return None

        else:

            if pdf_reader.decrypt(password) != 1:

                print('%s密码不正确！' % filename)

                return None

    if old_file in locals():

        old_file.close()

    return pdf_reader

def decrypt_pdf(filename, password, decrypted_filename=None):

    """

    将加密的文件及逆行解密，并生成一个无需密码pdf文件

    :param filename: 原先加密的pdf文件

    :param password: 对应的密码

    :param decrypted_filename: 解密之后的文件名

    :return:

    """

    # 生成一个Reader和Writer

    print('run  jiemi')

    pdf_reader = get_reader(filename, password)

    if pdf_reader is None:

        return

    if not pdf_reader.isEncrypted:

        print('文件没有被加密，无需操作！')

        return

    pdf_writer = PdfFileWriter()

    pdf_writer.appendPagesFromReader(pdf_reader)

    if decrypted_filename is None:

        decrypted_filename = "".join(filename.split('.')[:-1]) + '_' + 'decrypted' + '.pdf'

    # 写入新文件

    pdf_writer.write(open(decrypted_filename, 'wb'))

decrypt_pdf(r'5b931164edc09a226b3a12c4.pdf', '')

# coding:utf-8

import os

from PyPDF2 import PdfFileReader

from PyPDF2 import PdfFileWriter

def get_reader(filename, password):

    try:

        old_file = open(filename, 'rb')

        print('run  jiemi1')

    except Exception as err:

        print('文件打开失败！' + str(err))

        return None

    # 创建读实例

    pdf_reader = PdfFileReader(old_file, strict=False)

    # 解密操作

    if pdf_reader.isEncrypted:

        if password is None:

            print('%s文件被加密，需要密码！' % filename)

            return None

        else:

            if pdf_reader.decrypt(password) != 1:

                print('%s密码不正确！' % filename)

                return None

    if old_file in locals():

        old_file.close()

    return pdf_reader

def decrypt_pdf(filename, password, decrypted_filename=None):

    """

    将加密的文件及逆行解密，并生成一个无需密码pdf文件

    :param filename: 原先加密的pdf文件

    :param password: 对应的密码

    :param decrypted_filename: 解密之后的文件名

    :return:

    """

    # 生成一个Reader和Writer

    print('run  jiemi')

    pdf_reader = get_reader(filename, password)

    if pdf_reader is None:

        return

    if not pdf_reader.isEncrypted:

        print('文件没有被加密，无需操作！')

        return

    pdf_writer = PdfFileWriter()

    pdf_writer.appendPagesFromReader(pdf_reader)

    if decrypted_filename is None:

        decrypted_filename = "".join(filename.split('.')[:-1]) + '_' + 'decrypted' + '.pdf'

    # 写入新文件

    pdf_writer.write(open(decrypted_filename, 'wb'))

decrypt_pdf(r'5b931164edc09a226b3a12c4.pdf', 'abc')

from PyPDF2 import PdfFileWriter, PdfFileReader

writer = PdfFileWriter()

reader = PdfFileReader(open("document1.pdf", "rb"))

from PyPDF2 import PdfFileWriter, PdfFileReader

output = PdfFileWriter()

input1 = PdfFileReader(open("document1.pdf", "rb"))

# print how many pages input1 has:

print "document1.pdf has %d pages." % input1.getNumPages()

# add page 1 from input1 to output document, unchanged

output.addPage(input1.getPage(0))

# add page 2 from input1, but rotated clockwise 90 degrees

output.addPage(input1.getPage(1).rotateClockwise(90))

# add page 3 from input1, rotated the other way:

output.addPage(input1.getPage(2).rotateCounterClockwise(90))

# alt: output.addPage(input1.getPage(2).rotateClockwise(270))

# add page 4 from input1, but first add a watermark from another PDF:

page4 = input1.getPage(3)

watermark = PdfFileReader(open("watermark.pdf", "rb"))

page4.mergePage(watermark.getPage(0))

output.addPage(page4)

# add page 5 from input1, but crop it to half size:

page5 = input1.getPage(4)

page5.mediaBox.upperRight = (

    page5.mediaBox.getUpperRight_x() / 2,

    page5.mediaBox.getUpperRight_y() / 2

)

output.addPage(page5)

# add some Javascript to launch the print window on opening this PDF.

# the password dialog may prevent the print dialog from being shown,

# comment the the encription lines, if that's the case, to try this out

output.addJS("this.print({bUI:true,bSilent:false,bShrinkToFit:true});")

# encrypt your new PDF and add a password

password = "secret"

output.encrypt(password)

# finally, write "output" to document-output.pdf

outputStream = file("PyPDF2-output.pdf", "wb")

output.write(outputStream)

class PyPDF2.PdfFileReader（stream，strict = True，warndest = None，

overwriteWarnings = True ）