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 codecs | |
import sys | |
from lxml import etree | |
from lxml.html.clean import Cleaner | |
def sanitize(dirty_html): | |
cleaner = Cleaner(page_structure=True, | |
meta=True, |
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 cv2.cv as cv | |
import tesseract | |
gray = cv.LoadImage('captcha.jpeg', cv.CV_LOAD_IMAGE_GRAYSCALE) | |
cv.Threshold(gray, gray, 231, 255, cv.CV_THRESH_BINARY) | |
api = tesseract.TessBaseAPI() | |
api.Init(".","eng",tesseract.OEM_DEFAULT) | |
api.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyz") | |
api.SetPageSegMode(tesseract.PSM_SINGLE_WORD) | |
tesseract.SetCvImage(gray,api) | |
print api.GetUTF8Text() |