def dumpoutline(outfp,
fname,
objids,
pagenos,
password='',
dumpall=False,
codec=None,
extractdir=None):
fp = open(fname, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser, password)
pages = dict((page.pageid, pageno)
for (pageno, page) in enumerate(PDFPage.create_pages(doc), 1))
def resolve_dest(dest):
if isinstance(dest, str):
dest = resolve1(doc.get_dest(dest))
elif isinstance(dest, PSLiteral):
dest = resolve1(doc.get_dest(dest.name))
if isinstance(dest, dict):
dest = dest['D']
if isinstance(dest, PDFObjRef):
dest = dest.resolve()
return dest
try:
outlines = doc.get_outlines()
outfp.write('<outlines>\n')
for (level, title, dest, a, se) in outlines:
pageno = None
if dest:
dest = resolve_dest(dest)
pageno = pages[dest[0].objid]
elif a:
action = a
if isinstance(action, dict):
subtype = action.get('S')
if subtype and repr(subtype) == '/\'GoTo\'' and action.get(
'D'):
dest = resolve_dest(action['D'])
pageno = pages[dest[0].objid]
s = e(title).encode('utf-8', 'xmlcharrefreplace')
outfp.write('<outline level="%r" title="%s">\n' % (level, s))
if dest is not None:
outfp.write('<dest>')
dumpxml(outfp, dest)
outfp.write('</dest>\n')
if pageno is not None:
outfp.write('<pageno>%r</pageno>\n' % pageno)
outfp.write('</outline>\n')
outfp.write('</outlines>\n')
except PDFNoOutlines:
pass
parser.close()
fp.close()
return
def get_ToC(file):
"""This funciton will locate the Table of Content, and return a dataframe with the corresponding ToC-number and name
Args:
file (the pdf-file that will be read): reads and extract the specific words from the string
"""
# Open a PDF document.
fp = open(file, 'rb')
parser = PDFParser(fp)
document = PDFDocument(parser)
# Get the outlines of the document.
outlines = document.get_outlines()
for (level, title, dest, a, se) in outlines:
print(level, title)