def process_document(state, processing_date, fp, out_file):
if path.exists(out_file):
contents = open(out_file, "rb").read().decode("utf-8")
else:
parser = PDFParser(fp)
doc = PDFDocument(parser)
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
mgr = PDFResourceManager()
device = PDFPageAggregator(mgr)
interpreter = PDFPageInterpreter(mgr, device)
contents = ""
for page in PDFPage.create_pages(doc):
interpreter.process_page(page)
layout = device.get_result()
for element in layout:
if isinstance(element, LTChar):
contents += element.get_text()
open(out_file, "wb").write(contents.encode("utf-8"))
parsers = [p for p in ALL_PARSERS if p.can_parse(state, processing_date)]
if not parsers:
return None
parser = parsers[0]
return parser.parse_document(contents)
