pip install pdfminer.six

from pdfminer.high_level import extract_text
text = extract_text("example.pdf")
print(text)

from pdfminer.layout import LAParams, LTTextBox, LTTextLine
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator

resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = PDFPageAggregator(resource_manager, fake_file_handle, laparams=LAParams())
page_interpreter = PDFPageInterpreter(resource_manager, converter)

with open("example.pdf", "rb") as pdf_file:
    for page in PDFPage.get_pages(pdf_file):
        page_interpreter.process_page(page)
        layout = converter.get_result()
        for lt_obj in layout:
            if isinstance(lt_obj, (LTTextBox, LTTextLine)):
                text = lt_obj.get_text()
                x, y, width, height = lt_obj.bbox
                font = lt_obj._objs[0].fontname
                font_size = lt_obj._objs[0].size
                print(f"Text: {text.strip()}, Position: ({x:.2f}, {y:.2f}), Font: {font}, Size: {font_size:.2f}")

from pdfminer.high_level import extract_text
import tabula

table_text = extract_text("table_example.pdf")
print(table_text)

tables = tabula.read_pdf("table_example.pdf", pages="all")
for df in tables:
    print(df)

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdftypes import PDFStream
import io
from PIL import Image

with open('example.pdf', 'rb') as file:
    parser = PDFParser(file)
    document = PDFDocument(parser)
    if document.is_extractable:
        for xref in document.xrefs:
            if xref.get_subtype() == '/Image':
                stream_obj = xref.get_object()
                if isinstance(stream_obj, PDFStream):
                    data = stream_obj.get_rawdata()
                    image = Image.open(io.BytesIO(data))
                    image.show()