-
-
Save MrCheatEugene/46ad8173e83efb70cf6543cb36629403 to your computer and use it in GitHub Desktop.
Python 3 script to extract images from HTTP Archive (HAR) files (Tested & working on Python 3.11)
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 json | |
import base64 | |
import os | |
# make sure the output directory exists before running! | |
folder = os.path.join(os.getcwd(), "imgs") | |
if not os.path.exists(folder): | |
os.mkdir(folder,777) | |
ext = { | |
"image/webp": "webp", | |
"image/jpeg": "jpg", | |
"image/png": "png", | |
"image/svg+xml": "svg" | |
} | |
with open("har.har", "r",encoding="utf8") as f: | |
har = json.loads(f.read()) | |
entries = har["log"]["entries"] | |
for entry in entries: | |
mimetype = entry["response"]["content"]["mimeType"] | |
filename = entry["request"]["url"].split("/")[-1] | |
if mimetype in ext: | |
image64 = entry["response"]["content"]["text"] | |
ext.get(mimetype) | |
file = os.path.join(folder, f"{filename}") | |
with open(file, "wb") as f: | |
f.write(base64.b64decode(image64)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Note that this gist will overwrite files with the same filename and different URL paths, since the code is not creating subfolders.
For updated version with subfolders creation and parametrised (specifiable) input file and output folder, see the fork here:
https://gist.github.com/FurloSK/0477e01024f701db42341fc3223a5d8c