Created
September 1, 2017 04:58
-
-
Save roma-guru/2f3b57e1a7da9fd9d82daa12cc3a1687 to your computer and use it in GitHub Desktop.
Simple Python script to download favicons from list of domains (first argument). Used for custom Keepass entry icons.
This file contains hidden or 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 sys | |
import bs4 | |
import requests | |
from urllib.parse import urlparse, urlunparse | |
def find_icon(domain): | |
resp = requests.get("http://{}/".format(domain)) | |
page = bs4.BeautifulSoup(resp.text, 'html.parser') | |
res = "http://{}/favicon.ico".format(domain) | |
icons = [e for e in page.find_all(name='link') if 'icon' in e.attrs.get('rel')] | |
if icons: | |
res = icons[0].attrs.get('href') | |
url = urlparse(res, scheme='http') | |
if not url.netloc: | |
res = urlunparse((url.scheme, domain, url.path, '', '', '')) | |
return res | |
def download(domain, icon_url): | |
i = icon_url.find('.', len(icon_url)-4) | |
if i>=0: | |
ext = icon_url[i+1:] | |
else: | |
ext = 'ico' | |
fname = "{}.{}".format(domain, ext) | |
resp = requests.get(icon_url) | |
with open(fname, 'wb') as out: | |
out.write(resp.content) | |
if __name__=='__main__': | |
if len(sys.argv)<2: | |
print('Need txt file!') | |
sys.exit() | |
sites = sys.argv[1] | |
with open(sites, 'r') as sites: | |
for d in sites.readlines(): | |
d = d.strip() | |
download(d, find_icon(d)) |
This file contains hidden or 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
requests | |
BeautifulSoup4 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment