Anson/grad
1
0
Fork 0
mirror of https://gitlab.com/MisterBiggs/grad.git synced 2025-06-15 22:36:39 +00:00
Code Releases Activity

updated code to work on linux

Browse Source
This commit is contained in:
Anson Biggs 2020-05-23 16:36:02 +00:00
parent a7d79dd3e3
commit 305ca556a1
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
grad.py
View File

@ -5,9 +5,9 @@ import pandas as pd
import swifter
import glob
pytesseract.pytesseract.tesseract_cmd = (
r"C:\\Program Files\\Tesseract-OCR\\tesseract.exe"
)
# pytesseract.pytesseract.tesseract_cmd = (
# r"C:/Program Files/Tesseract-OCR/tesseract.exe"
# )
# Coords of where names appear on screen
t = 830
@ -16,13 +16,14 @@ b = 945
l = 530
crop_coords = (l, t, r, b)
frames_path = "C:\\Coding\\grad\\frames2"
f_paths = glob.glob(frames_path + "\\*jpg")
frames_path = "../frames"
f_paths = glob.glob(frames_path + "/*jpg")[10000:10100]
print("Frames loaded:", len(f_paths))
# Make dataframe with frame number as index and frame_path as a column
df = pd.DataFrame(
{"frame_path": f_paths},
index=[int(f_path.split("\\")[-1][:-4]) - 1 for f_path in f_paths],
index=[int(f_path.split("/")[-1][:-4]) - 1 for f_path in f_paths],
)
@ -30,7 +31,7 @@ df = df.reset_index(drop=True)
def im_str(im_path):
# im = f"C:\\Coding\\grad\\frames2\\{im_name}.jpg"
# im = f"C:/Coding/grad/frames2/{im_name}.jpg"
im = Image.open(im_path)
im = im.crop(crop_coords)
return pytesseract.image_to_string(im)
@ -38,6 +39,8 @@ def im_str(im_path):
df["text"] = df["frame_path"].swifter.apply(im_str)
# df = df[df["text"] != ""]
print(df)
df.to_feather("C:\\Coding\\grad\\out\\full.feather")
df.to_feather("./out/full.feather")