def __init__(self,
stream,
pages=None,
laparams=None,
precision=0.001,
password=""):
self.laparams = None if laparams == None else LAParams(**laparams)
self.stream = stream
self.pages_to_parse = pages
self.precision = precision
rsrcmgr = PDFResourceManager()
self.doc = PDFDocument(PDFParser(stream), password=password)
self.metadata = {}
for info in self.doc.info:
self.metadata.update(info)
for k, v in self.metadata.items():
if hasattr(v, "resolve"):
v = v.resolve()
if type(v) == list:
self.metadata[k] = list(map(decode_text, v))
elif isinstance(v, PSLiteral):
self.metadata[k] = decode_text(v.name)
elif isinstance(v, bool):
self.metadata[k] = v
elif isinstance(v, dict):
pass
elif v is None:
pass
elif type(v) in [bytes, str]:
self.metadata[k] = decode_text(v)
self.device = PDFPageAggregator(rsrcmgr, laparams=self.laparams)
self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)
def __init__(self, stream, pages=None, laparams=None, precision=0.001):
self.laparams = None if laparams == None else LAParams(**laparams)
self.stream = stream
self.pages_to_parse = pages
self.precision = precision
rsrcmgr = PDFResourceManager()
self.doc = PDFDocument(PDFParser(stream))
self.metadata = {}
for info in self.doc.info:
self.metadata.update(info)
for k, v in self.metadata.items():
if hasattr(v, "resolve"):
v = v.resolve()
if type(v) == list:
self.metadata[k] = list(map(decode_text, v))
elif isinstance(v, PSLiteral):
self.metadata[k] = decode_text(v.name)
else:
self.metadata[k] = decode_text(v)
self.device = PDFPageAggregator(rsrcmgr, laparams=self.laparams)
self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)
def __init__(self, stream, pages=None, laparams=None, precision=0.001):
self.laparams = None if laparams == None else LAParams(**laparams)
self.stream = stream
self.pages_to_parse = pages
self.precision = precision
rsrcmgr = PDFResourceManager()
self.doc = PDFDocument(PDFParser(stream))
self.metadata = {}
for info in self.doc.info:
self.metadata.update(info)
for k, v in self.metadata.items():
if hasattr(v, "resolve"):
v = v.resolve()
self.metadata[k] = decode_text(v)
self.device = PDFPageAggregator(rsrcmgr, laparams=self.laparams)
self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)