Das deutsche Python-Forum

Code: Alles auswählen

import PyPDF2

print("String eingeben:")
String = input()

print("Eingabe: ", String)

open("test.pdf", "rb")
File = PyPDF2.PdfFileReader("test.pdf")

Seitenanzahl = File.getNumPages()
print("Seitenanzahl: ", Seitenanzahl)

ausgabe = []

for i in range(1, Seitenanzahl):
    Seite = File.getPage(i)
    y = ""
    y += Seite.extractText()
    x = y.encode('utf-8').lower()
    prüfe = x.find(String)
    if prüfe == True:
        ausgabe += i
print(ausgabe)

Code: Alles auswählen

import PyPDF2

print("String eingeben:")
search_string = input()

print("Eingabe: ", search_string)

pdf_file = PyPDF2.PdfFileReader("test.pdf")

page_count = pdf_file.getNumPages()
print("Seitenanzahl: ", page_count)

pages_found = []
for page_num in range(1, page_count): # ignore page 1
    page = pdf_file.getPage(page_num)
    page_text = page.extractText().lower()
	if search_string in page_text:
        pages_found.append(page_num)
print(pages_found)

Code: Alles auswählen

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter#process_pdf 
from pdfminer.pdfpage import PDFPage 
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
 
 
def pdf_to_text(pdfname): 

    rsrcmgr = PDFResourceManager() 
    sio = StringIO() 
    codec = 'utf-8' 
    laparams = LAParams() 
    device = TextConverter(rsrcmgr, sio, codec=codec, laparams=laparams) 
    interpreter = PDFPageInterpreter(rsrcmgr, device) 

    search_string = "CB6"
    Pages_Found = []
    Page_Num = 1

    fp = open(pdfname, 'rb')
    for page in PDFPage.get_pages(fp):
        print(Page_Num)
        Page_Num += 1
        interpreter.process_page(page)
        page_text = sio.getvalue()
        if search_string in page_text:
            Pages_Found.append(Page_Num)
    fp.close() 
 
 
    text = sio.getvalue() 

  
    device.close()
    sio.close() 
 
    return Pages_Found

x = pdf_to_text("test.pdf")
print(x)

Code: Alles auswählen

def get_page_content(page): 
    rsrcmgr = PDFResourceManager() 
    output = StringIO() 
    device = TextConverter(rsrcmgr, output, laparams=LAParams()) 
    interpreter = PDFPageInterpreter(rsrcmgr, device) 
    interpreter.process_page(page)
    return output.getvalue()
 
def search_pdf(pdfname, search_string):
    pages_found = []
    with open(pdfname, 'rb') as fp:
        for page_num, page in enumerate(PDFPage.get_pages(fp), 1):
            print(page_num)
            page_text = get_page_content(page)
            if search_string in page_text:
                pages_found.append(page_num)
    return pages_found