מגדר PDF קבצים, Extract Text תמונות דרך ספריית Python חינם

להתקין PyMuPDF באמצעות צינורות

 python -m pip install --upgrade pip
python -m pip install --upgrade pymupdf
 

Clone PyMuPDF באמצעות חשבון Git

 git clone https://github.com/pymupdf/PyMuPDF.git 

חיפוש איפה על PDF עמודים טקסט מחרוזת יופיע דרך Python

areas = page.search_for("mupdf") 

כיצד להוציא טקסט מ PDF דרך Python API

from operator import itemgetter
from itertools import groupby
import fitz
doc = fitz.open( 'mydocument.pdf' )
pages = [ doc[ i ] for i in range( doc.pageCount ) ]
for page in pages:
  text_words = page.getTextWords()
  # The words should be ordered by y1 and x0
  sorted_words = SortedCollection( key = itemgetter( 3, 0 ) )
  for word in text_words:
    sorted_words.insert( word )
  # At this point you already have an ordered list. If you need to 
  # group the content by lines, use groupby with y1 as a key
  lines = groupby( sorted_words, key = itemgetter( 3 ) )

יצירת מסמכים חדשים מהעמודים הראשונים והאחרונים

doc2 = fitz.open()                 # new empty PDF
doc2.insert_pdf(doc1, to_page = 9)  # first 10 pages
doc2.insert_pdf(doc1, from_page = len(doc1) - 10) # last 10 pages
doc2.save("first-and-last-10.pdf")

ייצוא PDF Metadata עד CSV דרך פיתון API

import csv
import fitz
import argparse
parser = argparse.ArgumentParser(description="Enter CSV delimiter [;], CSV filename and documment filename")
parser.add_argument('-d', help='CSV delimiter [;]', default = ';')
parser.add_argument('-x', help='delete XML info [n]', default = 'n')
parser.add_argument('-csv', help='CSV filename')
parser.add_argument('-pdf', help='PDF filename')
args = parser.parse_args()
delim = args.d               # requested CSV delimiter character
assert args.csv, "missing CSV filename"
assert args.pdf, "missing PDF filename"
print "delimiter", args.d
print "xml delete", args.x
print "csv file", args.csv
print "pdf file", args.pdf
print "----------------------------------------"
doc = fitz.open(args.pdf)
oldmeta = doc.metadata
print "old metadata:"
for k,v in oldmeta.items():
    print k, ":",v
with open(args.csv) as tocfile:
    tocreader = csv.reader(tocfile, delimiter = delim)
    for row in tocreader:
        assert len(row) == 2, "each row must contain 2 entries"
        oldmeta[row[0]] = row[1]
print "----------------------------------------"
print "\nnew metadata:"
for k,v in oldmeta.items():
    print k, ":",v
doc.set_metadata(oldmeta)
doc.saveIncr()