def do(filename=''): fp = open(filename, 'rb') parser = PDFParser(fp) doc = PDFDocument(parser) parser.set_document(doc) # doc.set_parser(parser) # doc.initialize() print doc.info # The "Info" metadata if 'Metadata' in doc.catalog: metadata = resolve1(doc.catalog['Metadata']).get_data() print metadata # The raw XMP metadata print xmp_to_dict(metadata) return doc,doc.info[0]
def do(filename=''):
fp = open(filename, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser)
parser.set_document(doc)
# doc.set_parser(parser)
# doc.initialize()
print doc.info # The "Info" metadata
if 'Metadata' in doc.catalog:
metadata = resolve1(doc.catalog['Metadata']).get_data()
print metadata # The raw XMP metadata
print xmp_to_dict(metadata)
return doc, doc.info[0]
def _get_xmp_metadata(self):
t = a = None
metadata = resolve1(self.doc.catalog["Metadata"]).get_data()
try:
md = xmp_to_dict(metadata)
except:
return t, a
try:
t = md["dc"]["title"]["x-default"]
except KeyError:
pass
try:
a = md["dc"]["creator"]
except KeyError:
pass
else:
if type(a) is bytes:
a = a.decode("utf-8")
if type(a) is str:
a = [a]
a = list(filter(bool, a)) # remove None, empty strings, ...
if len(a) > 1:
a = " ".join((self._au_last_name(a[0]), self._au_last_name(a[-1])))
elif len(a) == 1:
a = self._au_last_name(a[0])
else:
a = None
return t, a
def _get_xmp_metadata(self):
t = a = None
metadata = resolve1(self.doc.catalog['Metadata']).get_data()
try:
md = xmp_to_dict(metadata)
except:
return t, a
try:
t = md['dc']['title']['x-default']
except KeyError:
pass
try:
a = md['dc']['creator']
except KeyError:
pass
else:
if type(a) is bytes:
a = a.decode('utf-8')
if type(a) is str:
a = [a]
a = list(filter(bool, a)) # remove None, empty strings, ...
if len(a) > 1:
a = '%s %s' % (self._au_last_name(
a[0]), self._au_last_name(a[-1]))
elif len(a) == 1:
a = self._au_last_name(a[0])
else:
a = None
return t, a
def _get_xmp_metadata(self):
t = a = None
metadata = resolve1(self.doc.catalog['Metadata']).get_data()
try:
md = xmp_to_dict(metadata)
except:
return t, a
try:
t = md['dc']['title']['x-default']
except KeyError:
pass
try:
a = md['dc']['creator']
except KeyError:
pass
else:
if type(a) is str:
a = [a]
a = filter(bool, a) # remove None, empty strings, ...
if len(a) > 1:
a = '%s %s' % (self._au_last_name(a[0]),
self._au_last_name(a[-1]))
elif len(a) == 1:
a = self._au_last_name(a[0])
else:
a = None
return t, a
def proc(self, pdfFp):
"""Get meta-data as available from a PDF document"""
parser = PDFParser(pdfFp)
doc = PDFDocument(parser)
parser.set_document(doc)
doc.initialize()
self.info = doc.info
if 'Metadata' in doc.catalog:
self.metadata = xmp_to_dict(
resolve1(doc.catalog['Metadata']).get_data()
)
self.raw_doc = pdfFp.getvalue()
def _get_xmp_metadata(self):
t = a = None
try:
metadata = resolve1(self.doc.catalog['Metadata']).get_data()
except:
return t, a
try:
md = xmp_to_dict(metadata)
except:
return t, a
try:
t = md['dc']['title']['x-default']
except TypeError:
# The 'title' field might be a string or bytes instead of a dict
# https://github.com/jdmonaco/pdf-title-rename/issues/7
titleval = md['dc']['title']
if type(titleval) is str:
t = titleval
elif type(titleval) is bytes:
t = titleval.decode()
except KeyError:
pass
try:
a = md['dc']['creator']
except KeyError:
pass
else:
if type(a) is bytes:
a = a.decode('utf-8')
if type(a) is str:
a = [a]
a = list(filter(bool, a)) # remove None, empty strings, ...
if len(a) > 1:
a = '%s %s' % (self._au_last_name(
a[0]), self._au_last_name(a[-1]))
elif len(a) == 1 and not a[0].isspace():
a = self._au_last_name(a[0])
else:
a = None
return t, a
def _get_xmp_metadata(self):
t = a = None
metadata = resolve1(self.doc.catalog['Metadata']).get_data()
try:
md = xmp_to_dict(metadata)
except:
return t, a
try:
t = md['dc']['title']['x-default']
except TypeError:
# The 'title' field might be a string or bytes instead of a dict
# https://github.com/jdmonaco/pdf-title-rename/issues/7
titleval = md['dc']['title']
if type(titleval) is str:
t = titleval
elif type(titleval) is bytes:
t = titleval.decode()
except KeyError:
pass
try:
a = md['dc']['creator']
except KeyError:
pass
else:
if type(a) is bytes:
a = a.decode('utf-8')
if type(a) is str:
a = [a]
a = list(filter(bool, a)) # remove None, empty strings, ...
if len(a) > 1:
a = '%s %s' % (self._au_last_name(a[0]), self._au_last_name(a[-1]))
elif len(a) == 1:
a = self._au_last_name(a[0])
else:
a = None
return t, a
return False
# loop through directories
for subdir, dirs, files in os.walk(arg_path):
for file in files:
file_count += 1
filepath = subdir + os.sep + file
if filepath.endswith(".pdf"):
pdffilecount += 1
try:
pdfdoc = parsePDFfile(filepath)
if checkMetadata(pdfdoc):
metadata = resolve1(pdfdoc.catalog['Metadata']).get_data()
dirname = subdir.split(os.path.sep)[-1]
pdfdict = xmp_to_dict(metadata)
dict1 = pdfdoc.info[0]
xkeywords = None
xdesc = None
xcreator = None
xtitle = None
xfolder = None
try:
xkeywords = str(pdfdict['pdf']['Keywords']).replace(
'\r\n', ', ')
except:
xkeywords = ''
pass
try:
xdesc = pdfdict['dc']['description']['x-default']
except:
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdftypes import resolve1
from xmp import xmp_to_dict
fp = open(
'c:/Users/mihal/OneDrive/Documents/pyprj/pdf-metadata-master/example/docs/methods_of_web_philology.pdf',
'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser)
parser.set_document(doc)
print(doc.info) # The "Info" metadata
if 'Metadata' in doc.catalog:
metadata = resolve1(doc.catalog['Metadata']).get_data()
print(metadata) # The raw XMP metadata
print(xmp_to_dict(metadata))
"""
c:/Users/mihal/OneDrive/Documents/pyprj/pdf-metadata-master/example/docs/Haltermanpythonbook.pdf
c:/Users/mihal/OneDrive/Documents/pyprj/pdf-metadata-master/example/docs/methods_of_web_philology.pdf
c:/Users/mihal/OneDrive/Documents/pyprj/pdf-metadata-master/example/docs/pdf_wiki.pdf
"""
