这应该正确地找到并整理所有要合并的文件;它仍然需要实际的 .pdf 合并代码。
编辑:我添加了基于pyPdf 示例代码的 pdf 编写代码。它没有经过测试,但应该(据我所知)可以正常工作。
Edit2:意识到我有地图编号十字路口;重新调整它以合并正确的地图集。
import collections
import glob
import re
# probably need to install this module -
# pip install pyPdf
from pyPdf import PdfFileWriter, PdfFileReader
def group_matched_files(filespec, reg, keyFn, dataFn):
res = collections.defaultdict(list)
reg = re.compile(reg)
for fname in glob.glob(filespec):
data = reg.match(fname)
if data is not None:
res[keyFn(data)].append(dataFn(data))
return res
def merge_pdfs(fnames, newname):
print("Merging {} to {}".format(",".join(fnames), newname))
# create new output pdf
newpdf = PdfFileWriter()
# for each file to merge
for fname in fnames:
with open(fname, "rb") as inf:
oldpdf = PdfFileReader(inf)
# for each page in the file
for pg in range(oldpdf.getNumPages()):
# copy it to the output file
newpdf.addPage(oldpdf.getPage(pg))
# write finished output
with open(newname, "wb") as outf:
newpdf.write(outf)
def main():
matches = group_matched_files(
"map*.pdf",
"map(\d+)_(\d+).pdf$",
lambda d: "{}".format(d.group(2)),
lambda d: "map{}_".format(d.group(1))
)
for map,pages in matches.iteritems():
merge_pdfs((page+map+'.pdf' for page in sorted(pages)), "merged{}.pdf".format(map))
if __name__=="__main__":
main()