def getPDFIntrospection(aPDF):
#logging.info("Method getPDFIntrospection for:" + str(aPDF))
content = " "
pdf = open(aPDF, 'rb')
reader = PdfFileReader(pdf)
if reader.isEncrypted:
reader._override_encryption = True
reader.decrypt('')
content = reader.getPage(0).extractText() + "\n"
content = " ".join(content.replace(u"\xa0", " ").strip().split())
pdf.close()
return content
def getPubDate(aPDF):
#logging.info("Method getPubDate for:" + str(aPDF))
publication_date = " "
temp_PDF = PdfFileReader(open(aPDF, "rb"))
if temp_PDF.isEncrypted:
temp_PDF._override_encryption = True
temp_PDF.decrypt('')
pdf_info = temp_PDF.getDocumentInfo()
for key, val in pdf_info.items():
if key == '/CreationDate':
if str(type(val)
)[8:39] != 'PyPDF2.generic.TextStringObject' or key == " ":
publication_date = "No_Year"
else:
publication_date = val[:6]
publication_date = publication_date[2:]
if publication_date == " ":
publication_date = "No_Year"
return publication_date