Provide access to page::text_list about pdftotext HOT 1 OPEN

from poppler import load_from_file

# load the file
pdf = load_from_file("somefile.pdf")

# argument can be either 0-based index or a "page label" (whatever the latter is)
# note that this doesn't really "create" a page (in the sense of modifying the
# original or a copy of the PDF), it simply returns a `Page` object
page = pdf.create_page(0) 

# go over the text list
for item in page.text_list():
    print(item.bbox.as_tuple(),item.text)

# getting text from some (rectangular) region
from poppler import Rectangle
text_in_region = page.text(Rectangle(x, y, width, height))