def bkpage(pdf_name):
f = open(pdf_name, 'rb')
pdf = PdfFileReader(f)
# map page ids to page numbers
pg_id_num_map = _setup_page_id_to_num(pdf)
outlines = pdf.getOutlines()
bookmarks_info = outlines_pg_zoom_info(outlines, pg_id_num_map)
#print bookmarks_info
page_title = {}
for key in bookmarks_info.keys():
a = bookmarks_info[key]
page_title[a['title'].encode('utf-8')] = int(a['page'])
#print page_title
a = sorted(page_title.items(), key=lambda (k, v): (v, k))
#print a
l = []
title_tokens = []
for x in a:
l.append(x[0])
title_tokens.append(x[0].split())
#print x[1], ":", x[0]
return (page_title, l, title_tokens)
def get_outlines(pdf_file_path):
"Get outlines"
if not pdf_file_path:
raise # TODO
with open(pdf_file_path) as f:
pdf_reader = PdfFileReader(f)
return pdf_reader.getOutlines()
intr = open(subheading[i],'w')
for k in xrange(len(part)-1):
intr.write(part[k])
c=0
part=[]
elif i+1==len(subheading):
intr = open(subheading[i],'w')
for k in xrange(len(part)-1):
intr.write(part[k])
path = "C:\Users\Wu/nordron-sciinfo\Code\Rainy\code\extraction" #please change path
article = textract.process('y.pdf', m='pdfminer') #please chang the file name
f = open('y.pdf', 'rb') #import PDF file
p = PdfFileReader(f)
o = p.getOutlines() #read outlines in pdf
list = []
dimension(o, list)
pdftotxt(article)
#build a list of subtitle
subheading = []
for j in range(0,len(list)):
sub = list[j]["/Title"]
subheading.append(sub)
#title=title_extractor(path, filename)
myfile = open("pdf_1.txt")
line = myfile.readlines() # read txt file line by line
split(line,subheading,path)