python3でPyOCRを使って画像を文字列に変換する方法

python -m pip install pyocr

pip install pyocr

from PIL import Image
import sys
import pyocr
import pyocr.builders

# pngファイルの自動読み取り
def png_to_text(png_name):
    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(png_name),
        lang=lang,
        builder=pyocr.builders.TextBuilder()
    )
    # txt is a Python string

    return txt

# img.pngの内容をテキスト化
keyword_text = png_to_text('img.png')

from time import sleep
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from PIL import Image
import sys
import pyocr
import pyocr.builders

# pngファイルの自動読み取り
def png_to_text(png_name):
    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(png_name),
        lang=lang,
        builder=pyocr.builders.TextBuilder()
    )
    # txt is a Python string

    return txt


USER = 'IDをここに記入'
PASS = 'PASSをここに記入'

# seleniumの準備
options = webdriver.ChromeOptions()
# 必須
options.add_argument('--disable-gpu')
options.add_argument('--disable-infobars')
# エラーの許容
options.add_argument('--ignore-certificate-errors')
options.add_argument('--allow-running-insecure-content')
options.add_argument('--disable-web-security')
# headlessでは不要そうな機能
options.add_argument('--disable-desktop-notifications')
options.add_argument("--disable-extensions")
# UA
options.add_argument('--user-agent=hogehoge')
# 言語
options.add_argument('--lang=ja-JP,ja;q=0.9,en-US;q=0.8,en;q=0.7')

# ブラウザーを起動
driver = webdriver.Chrome(chrome_options=options)

# HPにアクセス
driver.get('ログインページURLをここに記入')

# ちょっとだけ待機
sleep(2)

# ID/PASSを入力
id = driver.find_element_by_xpath("実際のidを入れるフォームのxpathを入力してください")
id.send_keys(USER)
sleep(1)
password = driver.find_element_by_xpath("実際のpasswordを入れるフォームのxpathを入力してください")
password.send_keys(PASS)
sleep(1)

# キーワード部分を画像化
png = driver.find_element_by_xpath("OCRにかけたい画像のxpathを入力してください").screenshot_as_png
with open('./img.png', 'wb') as f:
f.write(png)

# 画像を文字列に変換してフォームに入力
keyword_text = png_to_text('img.png')
keyword = driver.find_element_by_xpath("実際のkeywordを入れるフォームのxpathを入力してください")
keyword.send_keys(keyword_text)

# ログインボタンを押す
login_button = driver.find_element_by_xpath("ログインボタンのxpathを入力してください")
login_button.click()