Am making a digital assistant as final year project and I want to automate the browser tab by getting title of tab including the location of the detected words and use the coordinates to click the tab. I tried this answers I found here but not what I needed.
from pytesseract import *
from PIL import ImageGrab
pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
while True:
cap = ImageGrab.grab(bbox=(0, 0, 1182, 34)) # bounding box of the browser tab bar
text = pytesseract.image_to_data(cap, output_type=Output.DICT)
print(text)
data = {}
for i in range(len(text['line_num'])):
txt = text['text'][i]
block_num = text['block_num'][i]
line_num = text['line_num'][i]
top, left = text['top'][i], text['left'][i]
width, height = text['width'][i], text['height'][i]
if not txt == '' or txt.isspace():
tup = (txt, left, top, width, height)
if block_num in data:
if line_num in data[block_num]:
data[block_num][line_num].append(tup)
else:
data[block_num][line_num] = [tup]
else:
data[block_num] = {}
data[block_num][line_num] = [tup]
linedata = {}
idx = 0
for _, b in data.items():
for _, i in b.items():
linedata[idx] = i
idx += 1
line_idx = 1
for _, line in linedata.items():
xmin, ymin = line[0][1], line[0][2]
xmax, ymax = (line[-1][1] + line[-1][3]), (line[-1][2] + line[-1][4])
print(f'line{line_idx}, {xmin}, {ymin}, {xmax}, {ymax}, {txt}')
line_idx += 1
I need the title of each tab and their coordinates. Am pretty confident that pytesseract.image_to_data() is what I need but don't know how to extract the information that need
I'm looking to put black backgrounds on text using PIL in Python that automatically adjust to the width and height of the text.
Currently, I have code that constructs the text at equal distances from each other. How would I now put a black background on each line?
font_fname = r'user\arial.ttf'
font_size = 50
font = ImageFont.truetype(font_fname, font_size)
text = 'This is a picture of a dolphin having fun'
text_items = wrap(text, 25)
for i in range(4):
try:
number = str(i)
item = text_items[i]
exec(str("line" + number + ' = ''"""' + item + '"""'))
except:
pass
spacing = spacing + 30
par_spacing = 40
for i in range(len(opening_par_items) + 1):
line_number = str(i)
try:
exec("draw.text((130, " + str(spacing) + "), line_" + line_number + ", font=font , fill='rgb(255, 255, 255)')")
spacing = spacing + par_spacing
except:
pass
I want to create a word search generator but I'm finding it a little hard. Ive looked online and found this word search generator which works well but i would like to use my own grid from a text file. Is there way I can code this and place my text file instead of random choice letters.
##while True:
## intext=input('Enter file name: ')
##
## if not intext=='grid.txt':
## print("No such file was found! Enter file name.")
## continue
## else:
##
## break
##grid= open(intext,'r')
import string
import random
width = 12
height = 12
def put_word(word,grid):
word = random.choice([word,word[::-1]])
d = random.choice([[1,0],[0,1],[1,1]])
xsize = width if d[0] == 0 else width - len(word)
ysize = height if d[1] == 0 else height - len(word)
x = random.randrange(0,xsize)
y = random.randrange(0,ysize)
print([x,y])
for i in range(0,len(word)):
grid[y + d[1]*i][x + d[0]*i] = word[i]
return grid
grid = [[random.choice(string.ascii_uppercase) for i in range(0,width)] for j in range(0,height)]
for word in ["HELLO", "THERE", "AGAIN"]:
grid = put_word(word, grid)
print("\n".join(map(lambda row: " ".join(row), grid))
in the grid.txt files are:
xmfycxvtljlqbbybkoumjqwbt
caubmeknbeydqmcnzyjpvrank
aqactivexnyvwdvcoshoyaohg
paghzkctudptjdphsztprhttl
sbsnakjwqbouftmgnjqbtlinu
tsewohvobdsduqjiffkyylodo
oukwwefroyamapmlrrpvdolop
cqkfxtlksjvtmtrsbycmqrrri
kfervlqidqaxaoanfqjlmcpjh
yoyywrbpfcjlfbcbbcoecspwl
twbxetyuyufvvmauawjmbwlqh
txokdexmdbtgvhpsvsqtmljdx
dcatenrehteoxqdgeueljtrrn
jarteqvtxejfsqddkbuhcysfq
hpdrowssapxtrxhpdxcdhicon
I am trying to make a simple text editor using python. I am now trying to make a find function. This is what I've got:
def Find():
text = textArea.get('1.0', END+'-1c').lower()
input = simpledialog.askstring("Find", "Enter text to find...").lower()
startindex = []
endindex = []
lines = 0
if input in text:
text = textArea.get('1.0', END+'-1c').lower().splitlines()
for var in text:
character = text[lines].index(input)
start = str(lines + 1) + '.' + str(character)
startindex.append(start)
end = str(lines + 1) + '.' + str(character + int(len(input)))
endindex.append(end)
textArea.tag_add('select', startindex[lines], endindex[lines])
lines += 1
textArea.tag_config('select', background = 'green')
This will succesfully highlight words that match the users input with a green background. But the problem is, that it only highlights the first match every line, as you can see here.
I want it to highlight all matches.
Full code here: https://pastebin.com/BkuXN5pk
Recommend using the text widget's built-in search capability. Shown using python3.
from tkinter import *
root = Tk()
textArea = Text(root)
textArea.grid()
textArea.tag_config('select', background = 'green')
f = open('mouse.py', 'r')
content = f.read()
f.close()
textArea.insert(END, content)
def Find(input):
start = 1.0
length = len(input)
while 1:
pos = textArea.search(input, start, END)
if not pos:
break
end_tag = pos + '+' + str(length) + 'c'
textArea.tag_add('select', pos, end_tag)
start = pos + '+1c'
Find('display')
root.mainloop()
I'm creating a web-app that serves a dynamic image, with text.
Each string drawn may be in multiple colors.
So far I've created a parse method, and a render method. The parse method just takes the string, and parses colors from it, they are in format like this: "§aThis is green§rthis is white" (Yeah, it is Minecraft).
So this is how my font module looks like:
# Imports from pillow
from PIL import Image, ImageDraw, ImageFont
# Load the fonts
font_regular = ImageFont.truetype("static/font/regular.ttf", 24)
font_bold = ImageFont.truetype("static/font/bold.ttf", 24)
font_italics = ImageFont.truetype("static/font/italics.ttf", 24)
font_bold_italics = ImageFont.truetype("static/font/bold-italics.ttf", 24)
max_height = 21 # 9, from FONT_HEIGHT in FontRederer in MC source, multiplied by
# 3, because each virtual pixel in the font is 3 real pixels
# This number is also returned by:
# font_regular.getsize("ABCDEFGHIJKLMNOPQRSTUVWXYZ")[1]
# Create the color codes
colorCodes = [0] * 32 # Empty array, 32 slots
# This is ported from the original MC java source:
for i in range(0, 32):
j = int((i >> 3 & 1) * 85)
k = int((i >> 2 & 1) * 170 + j)
l = int((i >> 1 & 1) * 170 + j)
i1 = int((i >> 0 & 1) * 170 + j)
if i == 6:
k += 85
if i >= 16:
k = int(k/4)
l = int(l/4)
i1 = int(i1/4)
colorCodes[i] = (k & 255) << 16 | (l & 255) << 8 | i1 & 255
def _get_colour(c):
''' Get the RGB-tuple for the color
Color can be a string, one of the chars in: 0123456789abcdef
or an int in range 0 to 15, including 15
'''
if type(c) == str:
if c == 'r':
c = int('f', 16)
else:
c = int(c, 16)
c = colorCodes[c]
return ( c >> 16 , c >> 8 & 255 , c & 255 )
def _get_shadow(c):
''' Get the shadow RGB-tuple for the color
Color can be a string, one of the chars in: 0123456789abcdefr
or an int in range 0 to 15, including 15
'''
if type(c) == str:
if c == 'r':
c = int('f', 16)
else:
c = int(c, 16)
return _get_colour(c+16)
def _get_font(bold, italics):
font = font_regular
if bold and italics:
font = font_bold_italics
elif bold:
font = font_bold
elif italics:
font = font_italics
return font
def parse(message):
''' Parse the message in a format readable by render
this will return a touple like this:
[((int,int),str,str)]
so if you where to send it directly to the rederer you have to do this:
render(pos, parse(message), drawer)
'''
result = []
lastColour = 'r'
total_width = 0
bold = False
italics = False
for i in range(0,len(message)):
if message[i] == '§':
continue
elif message[i-1] == '§':
if message[i] in "01234567890abcdef":
lastColour = message[i]
if message[i] == 'l':
bold = True
if message[i] == 'o':
italics = True
if message[i] == 'r':
bold = False
italics = False
lastColour = message[i]
continue
width, height = _get_font(bold, italics).getsize(message[i])
total_width += width
result.append(((width, height), lastColour, bold, italics, message[i]))
return result
def get_width(message):
''' Calculate the width of the message
The message has to be in the format returned by the parse function
'''
return sum([i[0][0] for i in message])
def render(pos, message, drawer):
''' Render the message to the drawer
The message has to be in the format returned by the parse function
'''
x = pos[0]
y = pos[1]
for i in message:
(width, height), colour, bold, italics, char = i
font = _get_font(bold, italics)
drawer.text((x+3, y+3+(max_height-height)), char, fill=_get_shadow(colour), font=font)
drawer.text((x, y+(max_height-height)), char, fill=_get_colour(colour), font=font)
x += width
And it does work, but characters who are supposed to go below the ground line of the font, like g, y and q, are rendered on the ground line, so it looks strange, Here's an example:
Any ideas on how I can make them display corectly? Or do I have to make my own offset table, where I manually put them?
Given that you can't get the offsets from PIL, you could do this by slicing up images since PIL combines multiple characters appropriately. Here I have two approaches, but I think the first presented is better, though both are just a few lines. The first approach gives this result (it's also a zoom in on a small font which is why it's pixelated):
To explain the idea here, say I want the letter 'j', and instead of just making an image of just 'j', I make an image of ' o j' since that will keep the 'j' aligned correctly. Then I crop of the part I don't want and just keep the 'j' (by using textsize on both ' o ' and ' o j').
import Image, ImageDraw
from random import randint
make_color = lambda : (randint(50, 255), randint(50, 255), randint(50,255))
image = Image.new("RGB", (1200,20), (0,0,0)) # scrap image
draw = ImageDraw.Draw(image)
image2 = Image.new("RGB", (1200, 20), (0,0,0)) # final image
fill = " o "
x = 0
w_fill, y = draw.textsize(fill)
x_draw, x_paste = 0, 0
for c in "The quick brown fox jumps over the lazy dog.":
w_full = draw.textsize(fill+c)[0]
w = w_full - w_fill # the width of the character on its own
draw.text((x_draw,0), fill+c, make_color())
iletter = image.crop((x_draw+w_fill, 0, x_draw+w_full, y))
image2.paste(iletter, (x_paste, 0))
x_draw += w_full
x_paste += w
image2.show()
Btw, I use ' o ', rather than just 'o' since adjacent letters seem to slightly corrupt each other.
The second way is to make an image of the whole alphabet, slice it up, and then repaste this together. It's easier than it sounds. Here's an example, and both building the dictionary and concatenating into the images is only a few lines of code each:
import Image, ImageDraw
import string
A = " ".join(string.printable)
image = Image.new("RGB", (1200,20), (0,0,0))
draw = ImageDraw.Draw(image)
# make a dictionary of character images
xcuts = [draw.textsize(A[:i+1])[0] for i in range(len(A))]
xcuts = [0]+xcuts
ycut = draw.textsize(A)[1]
draw.text((0,0), A, (255,255,255))
# ichars is like {"a":(width,image), "b":(width,image), ...}
ichars = dict([(A[i], (xcuts[i+1]-xcuts[i]+1, image.crop((xcuts[i]-1, 0, xcuts[i+1], ycut)))) for i in range(len(xcuts)-1)])
# Test it...
image2 = Image.new("RGB", (400,20), (0,0,0))
x = 0
for c in "This is just a nifty text string":
w, char_image = ichars[c]
image2.paste(char_image, (x, 0))
x += w
Here's a (zoomed in) image of the resulting string:
Here's an image of the whole alphabet:
One trick here was that I had to put a space in between each character in my original alphabet image or I got the neighboring characters affecting each other.
I guess if you needed to do this a for a finite range of fonts and characters, it would be a good idea precalculate a the alphabet image dictionary.
Or, for a different approach, using a tool like numpy you could easily determine the yoffset of each character in the ichar dictionary above (eg, take the max along each horizontal row, and then find the max and min on the nonzero indices).
I simply solved this problem like this:
image = Image.new("RGB", (1000,1000), (255,255,255)) # 1000*1000 white empty image
# image = Image.fromarray(frame) # or u can get image from cv2 frame
draw = ImageDraw.Draw(image)
fontpath = "/etc/fonts/bla/bla/comic-sans.ttf"
font = ImageFont.truetype(fontpath, 35) # U can use default fonts
x = 20 # image draw start pixel x position
y = 100 # image draw start pixel y position
xDescPxl = draw.textsize("Descrition", font= font)[0]
draw.text((x, y), "Descrition" , font = font, fill = (0, 255, 0, 0)) # Green Color
draw.text((x + xDescPxl, y), ": u can do bla bla", font = font, fill = (0, 0, 0, 0)) # Black Color
Result:
Description: u can do bla bla
(20px space)---(Green Part)--(Black Part)