def mine_isbn(self):
obuf = StringIO()
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = TextConverter(rsrcmgr, outfp=obuf, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
if True:
for page in self.document.get_pages():
interpreter.process_page(page)
curpg = obuf.getvalue()
part = curpg.partition("ISBN")
if part[1] == 'ISBN':
isbn = []
part = part[2].partition(" ")
for c in part[2]:
try:
isbn.append(int(c))
except:
pass
if c == '\n':
break
if isbn[:3] == [9,7,8]:
if len(isbn) == 12:
return isbn + [ISBN.checksum_isbn13(isbn)]
elif len(isbn) == 9:
return isbn + [ISBN.checksum_isbn10(isbn)]
print("ISBN " + ISBN.to_string(isbn) + " incomplete! continue...")
#except Exception:
#raise RuntimeError("ExtractionError")
raise RuntimeError("ExtractionError")
def extract_isbn(self):
if self.use_external == True:
process = subprocess.Popen(self.program, stdout=subprocess.PIPE)
txt = process.communicate()[0].decode(encoding='UTF-8')
part = txt.partition("ISBN")
if part[1] == 'ISBN':
isbn = []
part = part[2].partition(" ")
for c in part[2]:
try:
isbn.append(int(c))
except:
pass
if c == '\n':
break
if isbn[:3] == [9,7,8]:
if len(isbn) == 12:
return isbn + [ISBN.checksum_isbn13(isbn)]
elif len(isbn) == 9:
return isbn + [ISBN.checksum_isbn10(isbn)]
else:
return self.mine_isbn()
raise RuntimeError("ExtractionError")
