Created
January 10, 2021 13:09
-
-
Save SeanDS/3b0e5eefa837f5ff0a136b71f9a54d26 to your computer and use it in GitHub Desktop.
Download tagged photos from Facebook
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
"""Facebook tagged photos download script. | |
Requires a Facebook API token - see the following blog post for more | |
information: https://attackllama.com/2021/01/downloading-tagged-photos-from-facebook/ | |
Sean Leavey | |
https://attackllama.com/ | |
https://github.com/SeanDS/ | |
""" | |
import os | |
import pickle | |
import datetime | |
import time | |
import requests | |
SLEEP = 3600 // 200 # One hour / max requests per hour. | |
ACCESS_TOKEN = "replace-with-long-API-token-string" | |
OUTPUT_DIR = "/tmp" | |
PICKLE_FILE = "/tmp/photos.pickle" | |
def fetch(): | |
if os.path.isfile(PICKLE_FILE): | |
print("Using existing photo list") | |
with open(PICKLE_FILE, "rb") as fobj: | |
data = pickle.load(fobj) | |
else: | |
print("Dumping photo list") | |
url = f"https://graph.facebook.com/me/photos" | |
result = requests.get( | |
url, params={"limit": 10000, "access_token": ACCESS_TOKEN} | |
) | |
result.raise_for_status() | |
data = result.json()["data"] | |
with open(PICKLE_FILE, "wb") as fobj: | |
pickle.dump(data, fobj) | |
ndata = len(data) | |
for i, photo in enumerate(data, start=1): | |
print(f"{i}/{ndata}") | |
imagedate = datetime.datetime.strptime( | |
photo["created_time"], "%Y-%m-%dT%H:%M:%S%z" | |
) | |
imagepath = f"{imagedate.strftime('%Y%m%d%H%M%S')}-{photo['id']}.jpg" | |
filename = f"{OUTPUT_DIR}/{imagepath}" | |
if os.path.isfile(filename): | |
print(f"Skipping already downloaded file {filename}") | |
continue | |
image_url = f"https://graph.facebook.com/v9.0/{photo['id']}" | |
image_result = requests.get( | |
image_url, | |
params={"fields": ["images"], "access_token": ACCESS_TOKEN} | |
) | |
image_result.raise_for_status() | |
images = image_result.json()["images"] | |
os.system(f"wget -O '{filename}' '{images[0]['source']}'") | |
print(f"Sleeping for {SLEEP} s") | |
time.sleep(SLEEP) | |
if __name__ == "__main__": | |
fetch() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment