Difference between revisions of "Python: Read PDF"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) (Created page with " ==Pranala Menarik== * Python") |
Onnowpurbo (talk | contribs) |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | Install | ||
| + | pip install PyPDF2 | ||
| + | |||
| + | ==Script Cek Jumlah Halaman== | ||
| + | |||
| + | # importing all the required modules | ||
| + | import PyPDF2 | ||
| + | |||
| + | # creating an object | ||
| + | file = open('example.pdf', 'rb') | ||
| + | |||
| + | # creating a pdf reader object | ||
| + | fileReader = PyPDF2.PdfFileReader(file) | ||
| + | |||
| + | # print the number of pages in pdf file | ||
| + | print(fileReader.numPages) | ||
| + | |||
| + | |||
| + | ==Script Print Satu Page== | ||
| + | |||
| + | # extracting_text.py | ||
| + | |||
| + | from PyPDF2 import PdfFileReader | ||
| + | |||
| + | |||
| + | def text_extractor(path): | ||
| + | with open(path, 'rb') as f: | ||
| + | pdf = PdfFileReader(f) | ||
| + | |||
| + | # get the first page | ||
| + | page = pdf.getPage(1) | ||
| + | print(page) | ||
| + | print('Page type: {}'.format(str(type(page)))) | ||
| + | |||
| + | text = page.extractText() | ||
| + | print(text) | ||
| + | |||
| + | if __name__ == '__main__': | ||
| + | path = 'reportlab-sample.pdf' | ||
| + | text_extractor(path) | ||
Latest revision as of 16:22, 28 October 2018
Install
pip install PyPDF2
Script Cek Jumlah Halaman
# importing all the required modules import PyPDF2
# creating an object
file = open('example.pdf', 'rb')
# creating a pdf reader object fileReader = PyPDF2.PdfFileReader(file)
# print the number of pages in pdf file print(fileReader.numPages)
Script Print Satu Page
# extracting_text.py
from PyPDF2 import PdfFileReader
def text_extractor(path):
with open(path, 'rb') as f:
pdf = PdfFileReader(f)
# get the first page
page = pdf.getPage(1)
print(page)
print('Page type: {}'.format(str(type(page))))
text = page.extractText()
print(text)
if __name__ == '__main__':
path = 'reportlab-sample.pdf'
text_extractor(path)