PyPDF2.PdfFileReader(stream,strict = True,warndest = None,overwriteWarnings = True)

# encoding:utf-8
from PyPDF2 import PdfFileReader, PdfFileWriter

readFile = 'C:/Users/Administrator/Desktop/RxJava 完全解析.pdf'
# 獲取 PdfFileReader 對(duì)象
pdfFileReader = PdfFileReader(readFile) # 或者這個(gè)方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
# 獲取 PDF 文件的文檔信息
documentInfo = pdfFileReader.getDocumentInfo()
print('documentInfo = %s' % documentInfo)
# 獲取頁(yè)面布局
pageLayout = pdfFileReader.getPageLayout()
print('pageLayout = %s ' % pageLayout)

# 獲取頁(yè)模式
pageMode = pdfFileReader.getPageMode()
print('pageMode = %s' % pageMode)

xmpMetadata = pdfFileReader.getXmpMetadata()
print('xmpMetadata = %s ' % xmpMetadata)

# 獲取 pdf 文件頁(yè)數(shù)
pageCount = pdfFileReader.getNumPages()

print('pageCount = %s' % pageCount)
for index in range(0, pageCount):
  # 返回指定頁(yè)編號(hào)的 pageObject
  pageObj = pdfFileReader.getPage(index)
  print('index = %d , pageObj = %s' % (index, type(pageObj))) # <class 'PyPDF2.pdf.PageObject'>
  # 獲取 pageObject 在 PDF 文檔中處于的頁(yè)碼
  pageNumber = pdfFileReader.getPageNumber(pageObj)
  print('pageNumber = %s ' % pageNumber)

def addBlankpage():
  readFile = 'C:/Users/Administrator/Desktop/RxJava 完全解析.pdf'
  outFile = 'C:/Users/Administrator/Desktop/copy.pdf'
  pdfFileWriter = PdfFileWriter()

  # 獲取 PdfFileReader 對(duì)象
  pdfFileReader = PdfFileReader(readFile) # 或者這個(gè)方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
  numPages = pdfFileReader.getNumPages()

  for index in range(0, numPages):
    pageObj = pdfFileReader.getPage(index)
    pdfFileWriter.addPage(pageObj) # 根據(jù)每頁(yè)返回的 PageObject,寫入到文件
    pdfFileWriter.write(open(outFile, 'wb'))

  pdfFileWriter.addBlankPage()  # 在文件的最后一頁(yè)寫入一個(gè)空白頁(yè),保存至文件中
  pdfFileWriter.write(open(outFile,'wb'))

def splitPdf():
  readFile = 'C:/Users/Administrator/Desktop/RxJava 完全解析.pdf'
  outFile = 'C:/Users/Administrator/Desktop/copy.pdf'
  pdfFileWriter = PdfFileWriter()

  # 獲取 PdfFileReader 對(duì)象
  pdfFileReader = PdfFileReader(readFile) # 或者這個(gè)方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
  # 文檔總頁(yè)數(shù)
  numPages = pdfFileReader.getNumPages()

  if numPages > 5:
    # 從第五頁(yè)之后的頁(yè)面，輸出到一個(gè)新的文件中，即分割文檔
    for index in range(5, numPages):
      pageObj = pdfFileReader.getPage(index)
      pdfFileWriter.addPage(pageObj)
    # 添加完每頁(yè)，再一起保存至文件中
    pdfFileWriter.write(open(outFile, 'wb'))

def mergePdf(inFileList, outFile):
  '''
  合并文檔
  :param inFileList: 要合并的文檔的 list
  :param outFile:  合并后的輸出文件
  :return:
  '''
  pdfFileWriter = PdfFileWriter()
  for inFile in inFileList:
    # 依次循環(huán)打開要合并文件
    pdfReader = PdfFileReader(open(inFile, 'rb'))
    numPages = pdfReader.getNumPages()
    for index in range(0, numPages):
      pageObj = pdfReader.getPage(index)
      pdfFileWriter.addPage(pageObj)

    # 最后,統(tǒng)一寫入到輸出文件中
    pdfFileWriter.write(open(outFile, 'wb'))

PageObject(pdf=None,indirectRef=None)

def getPdfContent(filename):
  pdf = PdfFileReader(open(filename, "rb"))
  content = ""
  for i in range(0, pdf.getNumPages()):
    pageObj = pdf.getPage(i)

    extractedText = pageObj.extractText()
    content += extractedText + "\n"
    # return content.encode("ascii", "ignore")
  return content