Last active
July 2, 2020 20:56
-
-
Save starcraft66/6c89344bce73fdf4db2744b71880296f to your computer and use it in GitHub Desktop.
Extract files from the Firefox for Android cache using html dumps of "Cache entry information" pages on devices where extracting the Firefox cache is not possible (non-rooted Android devices). Currently hardcoded to write files with the webp extension.
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 re | |
import glob | |
from bs4 import BeautifulSoup | |
inputs = glob.glob("input/*.html") | |
for input in inputs: | |
ba = bytearray() | |
with open(input, 'r') as file: | |
soup = BeautifulSoup(file, 'html.parser') | |
data = soup.find_all('pre')[0].contents[0] | |
foundbytes = re.findall("[0-9a-f]{8}:((\ \ [0-9a-f]{2}){1,16})", data) | |
for byteline in foundbytes: | |
cleanbyteline = re.sub(' ', '', byteline[0]) | |
thebytes = bytes.fromhex(cleanbyteline) | |
for b in thebytes: | |
ba.append(b) | |
with open(f"output/{input[6:-5]}.webp", "wb") as out: | |
out.write(ba) | |
out.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment