def delivery_type(page: pdf.PageObject) -> dict:
result = dict()
page_text = page.extractText()
if re.search("Tracking", page_text) is not None:
result["type"] = "Label"
result["amount"] = len((re.findall("Tracking", page_text)))
return result
elif is_it_blank_page(page):
result["type"] = "Empty Page"
result["amount"] = 0
return result
else:
result["type"] = "Shipping List"
result["amount"] = 1
return result
def is_it_blank_page(page: pdf.PageObject) -> bool:
if page.extractText() == '' and '/XObject' not in page['/Resources']:
return True
return False
from PyPDF2.pdf import PageObject
from PyPDF2 import PdfFileReader, PdfFileWriter
file_path = "Daycoval.pdf"
pdf = PdfFileReader(file_path)
with open('Daycoval.txt', 'w') as f:
for page_num in range(pdf.numPages):
print('Page: {0}'.format(page_num))
PageObject = pdf.getPage(page_num)
try:
txt = PageObject.extractText()
print(''.center(100, '-'))
except:
pass
else:
f.write('Page {0}\n'.format(page_num +1))
f.write(''.center(100, '-'))
f.write(txt)
f.close()