This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import asyncio | |
import os | |
import winrt | |
from PIL import Image | |
from winrt.windows.graphics.imaging import BitmapDecoder, BitmapPixelFormat, SoftwareBitmap | |
from winrt.windows.media.ocr import OcrEngine | |
from winrt.windows.storage import StorageFile, FileAccessMode | |
import winrt.windows.storage.streams as streams |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
from bs4 import BeautifulSoup | |
from bs4 import SoupStrainer | |
from nltk import tokenize | |
from xml.etree import ElementTree | |
NAMESPACES = { | |
'content': 'http://purl.org/rss/1.0/modules/content/', |