我正在尝试使用Python将几个PDF文件组合成一个PDF文件。我已经尝试了PyPDF和PyPDF2 -在一些文件上,它们都抛出了这个相同的错误:
PdfReadError:找不到EOF标记
以下是我的代码(page_files)是要组合的PDF文件路径列表:
# use pypdf to combine pdf pages
output = PdfFileWriter()
for pf in page_files:
filestream = file(pf, "rb")
pdf = PdfFileReader(filestream)
for num in range(pdf.getNumPages()):
output.addPage(pdf.getPage(num))
# write final file
outputStream = file(pdf_full_path, "wb")
output.write(outputStream)
outputStream.close()我已经阅读了一些关于这个主题的StackOverflow帖子,但没有一个包含有效的解决方案。如果你已经成功地使用Python组合了PDF文件,我很想听听你是怎么做的。谢谢!
发布于 2018-10-22 20:37:12
是否仍然有人在寻找合并pdf的“列表”:
注意:使用glob获取正确的文件列表。<-这将真正保护您的一天^^
from PyPDF2 import PdfFileMerger, PdfFileReader, PdfFileWriter
import os
import glob
class MergeAllPDF:
def __init__(self):
self.mergelist = []
def create(self, filepath, outpath, outfilename):
self.outfilname = outfilename
self.filepath = filepath
self.outpath = outpath
self.pdfs = glob.glob(self.filepath)
self.myrange = len(self.pdfs)
for _ in range(self.myrange):
if self.pdfs:
self.mergelist.append(self.pdfs.pop(0))
self.merge()
def merge(self):
if self.mergelist:
self.merger = PdfFileMerger()
for pdf in self.mergelist:
self.merger.append(open(pdf, 'rb'))
self.merger.write(self.outpath + "%s.pdf" % (self.outfilname))
self.merger.close()
self.mergelist = []
else:
print("mergelist is empty please check your input path")
# example how to use
#update your path here:
inpath = r"C:\Users\Fabian\Desktop\mergeallpdfs\scan\*.pdf" #here are your single page pdfs stored
outpath = r"C:\Users\Fabian\Desktop\mergeallpdfs\output\\" #here your merged pdf will be stored
b = MergeAllPDF()
b.create(inpath, outpath, "mergedpdf")https://stackoverflow.com/questions/16162478
复制相似问题