def basic_Op():
# readFile = 'C:/Users/Administrator/Desktop/RxJava 完全解析.pdf'
# 获取 PdfFileReader 对象
pdfFileReader = PdfFileReader(
"1.pdf") # 或者这个方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
# 获取 PDF 文件的文档信息
documentInfo = pdfFileReader.getDocumentInfo()
print('documentInfo = %s' % documentInfo)
# 获取页面布局
pageLayout = pdfFileReader.getPageLayout()
print('pageLayout = %s ' % pageLayout)
# 获取页模式
pageMode = pdfFileReader.getPageMode()
print('pageMode = %s' % pageMode)
xmpMetadata = pdfFileReader.getXmpMetadata()
print('xmpMetadata = %s ' % xmpMetadata)
# 获取 pdf 文件页数
pageCount = pdfFileReader.getNumPages()
print('pageCount = %s' % pageCount)
for index in range(0, pageCount):
# 返回指定页编号的 pageObject
pageObj = pdfFileReader.getPage(index)
print('index = %d , pageObj = %s' %
(index, type(pageObj))) # <class 'PyPDF2.pdf.PageObject'>
# 获取 pageObject 在 PDF 文档中处于的页码
pageNumber = pdfFileReader.getPageNumber(pageObj)
print('pageNumber = %s ' % pageNumber)
def info_page(readFile):
pdfFileReader = PdfFileReader(
readFile) # 或者这个方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
# 获取 PDF 文件的文档信息
documentInfo = pdfFileReader.getDocumentInfo()
print('documentInfo = %s' % documentInfo)
# 获取页面布局
pageLayout = pdfFileReader.getPageLayout()
print('pageLayout = %s ' % pageLayout)
# 获取页模式
pageMode = pdfFileReader.getPageMode()
print('pageMode = %s' % pageMode)
xmpMetadata = pdfFileReader.getXmpMetadata()
print('xmpMetadata = %s ' % xmpMetadata)
# 获取 pdf 文件页数
pageCount = pdfFileReader.getNumPages()
print('pageCount = %s' % pageCount)
for index in range(0, pageCount):
# 返回指定页编号的 pageObject
pageObj = pdfFileReader.getPage(index)
print('index = %d , pageObj = %s' %
(index, pageObj)) # <class 'PyPDF2.pdf.PageObject'>
# 获取 pageObject 在 PDF 文档中处于的页码
pageNumber = pdfFileReader.getPageNumber(pageObj)
print('pageNumber = %s ' % pageNumber)
def get_metadata():
for dirpath, dirnames, files in os.walk("pdf"):
for data in files:
ext = data.lower().rsplit('.', 1)[-1]
if ext in ['pdf']:
print("[--- Metadata : " + "%s ",
(dirpath + os.path.sep + data))
print(
"------------------------------------------------------------------------------------"
)
pdfReader = PdfFileReader(
open(dirpath + os.path.sep + data, 'rb'))
info = pdfReader.getDocumentInfo()
for metaItem in info:
print('[+] ' + metaItem.strip('/') + ': ' + info[metaItem])
pages = pdfReader.getNumPages()
print('[+] Pages:', pages)
layout = pdfReader.getPageLayout()
print('[+] Layout: ' + str(layout))
xmpinfo = pdfReader.getXmpMetadata()
if hasattr(xmpinfo, 'dc_contributor'):
print('[+] Contributor:', xmpinfo.dc_contributor)
if hasattr(xmpinfo, 'dc_identifier'):
print('[+] Identifier:', xmpinfo.dc_identifier)
if hasattr(xmpinfo, 'dc_date'):
print('[+] Date:', xmpinfo.dc_date)
if hasattr(xmpinfo, 'dc_source'):
print('[+] Source:', xmpinfo.dc_source)
if hasattr(xmpinfo, 'dc_subject'):
print('[+] Subject:', xmpinfo.dc_subject)
if hasattr(xmpinfo, 'xmp_modifyDate'):
print('[+] ModifyDate:', xmpinfo.xmp_modifyDate)
if hasattr(xmpinfo, 'xmp_metadataDate'):
print('[+] MetadataDate:', xmpinfo.xmp_metadataDate)
if hasattr(xmpinfo, 'xmpmm_documentId'):
print('[+] DocumentId:', xmpinfo.xmpmm_documentId)
if hasattr(xmpinfo, 'xmpmm_instanceId'):
print('[+] InstanceId:', xmpinfo.xmpmm_instanceId)
if hasattr(xmpinfo, 'pdf_keywords'):
print('[+] PDF-Keywords:', xmpinfo.pdf_keywords)
if hasattr(xmpinfo, 'pdf_pdfversion'):
print('[+] PDF-Version:', xmpinfo.pdf_pdfversion)
if hasattr(xmpinfo, 'dc_publisher'):
for published in xmpinfo.dc_publisher:
if publisher:
print("[+] Publisher:\t" + publisher)
fsize = os.stat((dirpath + os.path.sep + data))
print('[+] Size:', fsize[6], 'bytes \n\n')
def get_info_pdf(filename):
# 打开文件
file_stream = open(filename, 'rb')
# 创建一个实例用来读取pdf文件
pdf_reader = PdfFileReader(file_stream)
# 获取pdf文件的信息
document_info = pdf_reader.getDocumentInfo()
# 获取pdf文件的总页数
pdf_page_nums = pdf_reader.getNumPages()
# 获取单页pdf文件数据，得到一个PageObject对象
single_page = pdf_reader.getPage(1)
# 获取页面布局
pdf_layout = pdf_reader.getPageLayout()
# 检索指定PageObject的页码
page_num = pdf_reader.getPageNumber(single_page)
# encoding:utf-8
from PyPDF2 import PdfFileReader, PdfFileWriter
readFile = 'ks.pdf'
# 获取 PdfFileReader 对象
pdfFileReader = PdfFileReader(readFile) # 或者这个方式：pdfFileReader = PdfFileReader(open(readFile, 'rb'))
# 获取 PDF 文件的文档信息
documentInfo = pdfFileReader.getDocumentInfo()
print('documentInfo = %s' % documentInfo)
# 获取页面布局
pageLayout = pdfFileReader.getPageLayout()
print('pageLayout = %s ' % pageLayout)
# 获取页模式
pageMode = pdfFileReader.getPageMode()
print('pageMode = %s' % pageMode)
xmpMetadata = pdfFileReader.getXmpMetadata()
print('xmpMetadata = %s ' % xmpMetadata)
# 获取 pdf 文件页数
pageCount = pdfFileReader.getNumPages()
print('pageCount = %s' % pageCount)
for index in range(0, pageCount):
# 返回指定页编号的 pageObject
pageObj = pdfFileReader.getPage(index)
print('index = %d , pageObj = %s' % (index, type(pageObj))) # <class 'PyPDF2.pdf.PageObject'>
# 获取 pageObject 在 PDF 文档中处于的页码
pageNumber = pdfFileReader.getPageNumber(pageObj)
print('pageNumber = %s ' % pageNumber)
def add_page_numbers(self, input_path, output_path, mask, total_pages_flag, bottom_margin):
page_rotations_dict = PdfTask.get_page_rotations(input_path)
logger.info('Page rotations: {}'.format(page_rotations_dict))
output = PdfFileWriter()
input_pdf = open(input_path, "rb")
reader = PdfFileReader(input_pdf)
page_ct = reader.getNumPages()
logger.info('doc info: ' + str(reader.documentInfo))
logger.info('page layout:' + str(reader.getPageLayout()))
logger.info('page mode:' + str(reader.getPageMode()))
logger.info('xmp metadata:' + str(reader.getXmpMetadata()))
for page_num in range(page_ct):
# inspect the current input PDF page
page = reader.getPage(page_num)
page_rect = page.mediaBox
logger.info('page media box: Page {num}: {dim}'.format(num=page_num, dim=page_rect))
# dimensions for a letter sized sheet of paper are [0, 0, 612, 792]
# 72 pt = 1 inch
page_dimensions = {
'lower_left': page_rect.getUpperLeft()
, 'lower_right': page_rect.getLowerRight()
, 'upper_left': page_rect.getUpperLeft()
, 'upper_right': page_rect.getUpperRight()
}
logger.info('Page dimensions: {}'.format(page_dimensions))
# create a new PDF containing the page number as a watermark with Reportlab
txt = str(page_num + 1)
if mask:
txt = mask + " " + txt
if total_pages_flag == 'Y':
txt = txt + " of " + str(page_ct)
packet = io.BytesIO()
page_width = page_rect.getWidth()
page_height = page_rect.getHeight()
c = canvas.Canvas(packet, pagesize=(0, 0))
c.drawString(page_width / 2, bottom_margin, txt)
c.save()
packet.seek(0)
new_pdf = PdfFileReader(packet)
# merge new watermark pdf with the original
wm = new_pdf.getPage(0)
page_rotation = page_rotations_dict.get(page_num) or 0
page.mergeRotatedTranslatedPage(
wm
, rotation=page_rotation
, tx=page_width / 2
, ty=page_height / 2
, expand=True
)
page.scaleTo(page_width, page_height)
page.compressContentStreams()
output.addPage(page)
with open(output_path, "wb") as outputStream:
output.write(outputStream)
input_pdf.close()
logger.debug('Successfully added page numbers to {}'.format(input_path))
def test_get_page_layout(src, expected):
src = os.path.join(RESOURCE_ROOT, src)
reader = PdfFileReader(src)
assert reader.getPageLayout() == expected
# Exercise================================================================
1. 取得PDF 檔案資訊
from PyPDF2 import PdfFileReader , PdfFileWriter #import PyPDF2
pdffile = r'/Users/martychen/Documents/Python/water.pdf'
pfr = PdfFileReader(pdffile)
documentInfo = pfr.getDocumentInfo()
print('documentInfo = %s' % documentInfo)
pageLayout = pfr.getPageLayout()
print('pagelayout = %s' % pageLayout)
pagemode = pfr.getPageMode()
print('pagemode = %s' % pagemode)
xmpmetadata = pfr.getXmpMetadata()
print('xmpmetadata = %s' % xmpmetadata)
pagecount = pfr.getNumPages()
print('pagecount = %s' % pagecount)
