from PIL import Image
import sys

import pyocr
import pyocr.builders

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
    sys.exit(1)
# The tools are returned in the recommended order of usage
tool = tools[0]
print("Will use tool '%s'" % (tool.get_name()))
# Ex: Will use tool 'libtesseract'

langs = tool.get_available_languages()
print("Available languages: %s" % ", ".join(langs))
lang = langs[0]
print("Will use lang '%s'" % (lang))
# Ex: Will use lang 'fra'
# Note that languages are NOT sorted in any way. Please refer
# to the system locale settings for the default language
# to use.

txt = tool.image_to_string(
    Image.open('test.png'),
    lang=lang,
    builder=pyocr.builders.TextBuilder()
)
# txt is a Python string

word_boxes = tool.image_to_string(
    Image.open('test.png'),
    lang="eng",
    builder=pyocr.builders.WordBoxBuilder()
)
# list of box objects. For each box object:
#   box.content is the word in the box
#   box.position is its position on the page (in pixels)
#
# Beware that some OCR tools (Tesseract for instance)
# may return empty boxes

line_and_word_boxes = tool.image_to_string(
    Image.open('test.png'), lang="fra",
    builder=pyocr.builders.LineBoxBuilder()
)
# list of line objects. For each line object:
#   line.word_boxes is a list of word boxes (the individual words in the line)
#   line.content is the whole text of the line
#   line.position is the position of the whole line on the page (in pixels)
#
# Beware that some OCR tools (Tesseract for instance)
# may return empty boxes

# Digits - Only Tesseract (not 'libtesseract' yet !)
digits = tool.image_to_string(
    Image.open('test-digits.png'),
    lang=lang,
    builder=pyocr.tesseract.DigitBuilder()
)
# digits is a python string

if tool.can_detect_orientation():
    try:
        orientation = tool.detect_orientation(
            Image.open('test.png'),
            lang='fra'
        )
    except pyocr.PyocrException as exc:
        print("Orientation detection failed: {}".format(exc))
        return
    print("Orientation: {}".format(orientation))
# Ex: Orientation: {
#   'angle': 90,
#   'confidence': 123.4,
# }

import codecs
import pyocr
import pyocr.builders

tool = pyocr.get_available_tools()[0]
builder = pyocr.builders.TextBuilder()

txt = tool.image_to_string(
    Image.open('test.png'),
    lang=lang,
    builder=builder
)
# txt is a Python string

with codecs.open("toto.txt", 'w', encoding='utf-8') as file_descriptor:
    builder.write_file(file_descriptor, txt)
# toto.txt is a simple text file, encoded in utf-8

import codecs
import pyocr.builders

builder = pyocr.builders.TextBuilder()
with codecs.open("toto.txt", 'r', encoding='utf-8') as file_descriptor:
    txt = builder.read_file(file_descriptor)
# txt is a Python string

import codecs
import pyocr
import pyocr.builders

tool = pyocr.get_available_tools()[0]
builder = pyocr.builders.LineBoxBuilder()

line_boxes = tool.image_to_string(
    Image.open('test.png'),
    lang=lang,
    builder=builder
)
# list of LineBox (each box points to a list of word boxes)

with codecs.open("toto.html", 'w', encoding='utf-8') as file_descriptor:
    builder.write_file(file_descriptor, line_boxes)
# toto.html is a valid XHTML file

import codecs
import pyocr.builders

builder = pyocr.builders.LineBoxBuilder()
with codecs.open("toto.html", 'r', encoding='utf-8') as file_descriptor:
    line_boxes = builder.read_file(file_descriptor)
# list of LineBox (each box points to a list of word boxes)