import PyPDF2
import re
 
pdfFileObj=open(r'C:\python\document.pdf',mode='rb')
pdfReader=PyPDF2.PdfFileReader(pdfFileObj)
number_of_pages=pdfReader.numPages
 
pages_text=[]
words_start_pos={}
words={}
 
searchwords=['Earth']
 
with open('Results.csv', 'w') as f:
    f.write('{0},{1}\n'.format("Page Number", "Search"))
    for word in searchwords:
        for page in range(number_of_pages):
            print(page)
            pages_text.append(pdfReader.getPage(page).extractText())
            words_start_pos[page]=[dwg.start() for dwg in re.finditer(word, pages_text[page].lower())]
            words[page]=[pages_text[page][value:value+len(word)] for value in words_start_pos[page]]
        for page in words:
            for i in range(0,len(words[page])):
               if str(words[page][i]) != 'nan':
                    f.write('{0},{1}\n'.format(page+1, words[page][i]))
                    print(page, words[page][i])

(Jan-07-2022, 11:21 PM)BashBedlam Wrote: Try a different PDF. Your code works as expected for me with some PDFs but not others. Some PDFs are made entirely of images of words so only OCR would be able to retrieve those.

(Jan-08-2022, 12:26 AM)atomxkai Wrote:

(Jan-07-2022, 11:21 PM)BashBedlam Wrote: Try a different PDF. Your code works as expected for me with some PDFs but not others. Some PDFs are made entirely of images of words so only OCR would be able to retrieve those.

I learned that it mostly works in Mac than in Windows? But I will try different pdf. Thanks.

(Jan-07-2022, 07:19 PM)cubangt Wrote: When you run the logic, are your variables being populated?
Like you have print(page) does that print out a number?
What if you add a print(word) right below the for statement and see if that contains anything

Since you are looping thru those searchwords and page numbers, if those are blank, then you wont get any results.

import pdfplumber

pdf_file = "sample.pdf"
search_word = 'end'
with pdfplumber.open(pdf_file) as pdf:
    pages = pdf.pages
    for page_nr, pg in enumerate(pages, 1):
        content = pg.extract_text()
        if search_word in content:
            print(f'<{search_word}> found at page number <{page_nr}> '\
                    f'at index <{content.index(search_word)}>')

Output:
<end> found at page number <2> at index <349>

(Jan-08-2022, 03:07 PM)BashBedlam Wrote: @snippsat I liked your post. Just out of curiosity, how would you find a second or third occurrence of the same word on the same page?

import pdfplumber

pdf_file = "sample.pdf"
search_word = 'more'
with pdfplumber.open(pdf_file) as pdf:
    pages = pdf.pages
    for page_nr, pg in enumerate(pages, 1):
        content = pg.extract_text().split()
        for word in content:
            if search_word in word:
                print(f'<{search_word}> found on page {page_nr}')

Output:
<more> found on page 1
<more> found on page 1
<more> found on page 1
.....
<more> found on page 2

import pdfplumber

pdf_file = "sample.pdf"
search_word = 'more'
lst = []
with pdfplumber.open(pdf_file) as pdf:
    pages = pdf.pages
    for page_nr, pg in enumerate(pages):
        content = pg.extract_text().split()
        for word in content:
            if search_word in word:
                lst.append(search_word)

print(f'Search word <{search_word}> found {len(lst)} times in {pdf_file}')

Output:
Search word <more> found 40 times in sample.pdf

(Jan-08-2022, 10:09 AM)snippsat Wrote: pdfplumber may be a better tool for this and more updated,
it's been 5-6 year since PyPDF2 was updated and has stuff that is none pythonic like CamelCase🐫 usage everywhere.

So i can write a quick test for this task,using this sample pdf.

import pdfplumber

pdf_file = "sample.pdf"
search_word = 'end'
with pdfplumber.open(pdf_file) as pdf:
    pages = pdf.pages
    for page_nr, pg in enumerate(pages, 1):
        content = pg.extract_text()
        if search_word in content:
            print(f'<{search_word}> found at page number <{page_nr}> '\
                    f'at index <{content.index(search_word)}>')

Output:
<end> found at page number <2> at index <349>