def getPdffileBookmark(filename, bookmark_file_savepath):
pdf = PdfFileReader(open(filename, "rb"))
pagecount = pdf.getNumPages()
print('pagecount:', pagecount)
pageLabels = {
} #真实页码的索引 indirectRef “{'/Type': '/Fit', '/Page': IndirectObject(7871, 0), '/Title': '封面'}”
for i in range(pagecount):
page = pdf.getPage(i)
pageLabels[page.indirectRef.idnum] = i + 1
# print(page.indirectRef.idnum,i+1)
bookmark_file = codecs.open(bookmark_file_savepath, 'w', encoding='utf-8')
title = []
pagedir = []
bookmark_jibie = []
outlines = pdf.getOutlines()
print(outlines)
index = 0
jibie = 0
for outline in outlines:
index += 1
jibie = 0
print(len(outline), outline)
if type(outline) == PyPDF2.generic.Destination:
# print('dict--------')
# print(list(outline.keys()))
# for x,j in enumerate(list(outline.keys())):
# print(str(outline[j]))
# print(outline['/Title'])
# print(outline['/Type'])
# print(outline.page.idnum)
bookmark_file.write(outline['/Title'] + '\t' +
str(pageLabels[outline.page.idnum]) + '\r\n')
if type(outline) == list:
# print('list')
jibie = 1
for i, outline in enumerate(outline):
if type(outline) == PyPDF2.generic.Destination:
bookmark_file.write('\t' * jibie + outline['/Title'] +
'\t' +
str(pageLabels[outline.page.idnum]) +
'\r\n')
elif type(outline) == list:
jibie = 2
for i, o in enumerate(outline):
if type(outline) == PyPDF2.generic.Destination:
bookmark_file.write(
'\t' * jibie + outline['/Title'] + '\t' +
str(pageLabels[outline.page.idnum]) + '\r\n')
# print('\n')
# if index>=3:
# break
bookmark_file.close()
