split resources out

This commit is contained in:
lza_menace 2023-04-04 00:00:37 -07:00
parent 726d2766e8
commit 2fb28e90fb
16 changed files with 532 additions and 481 deletions

View file

@ -4,28 +4,28 @@ import os
import requests
import bs4
os.system('mkdir -p infodump/thumbs')
url = 'https://moneroinfodump.neocities.org/'
os.system("mkdir -p infodump/thumbs")
url = "https://moneroinfodump.neocities.org/"
contents = requests.get(url, timeout=15).content
soup = bs4.BeautifulSoup(contents, 'html.parser')
images = soup.find_all('img')
links = soup.find_all('a')
soup = bs4.BeautifulSoup(contents, "html.parser")
images = soup.find_all("img")
links = soup.find_all("a")
for image in images:
img = image.get('src')
if img.startswith('http'):
os.system(f'wget -q --no-clobber -O infodump/{os.path.basename(img)} {img}')
image['src'] = os.path.basename(img)
elif img.startswith('data:image/png'):
img = image.get("src")
if img.startswith("http"):
os.system(f"wget -q --no-clobber -O infodump/{os.path.basename(img)} {img}")
image["src"] = os.path.basename(img)
elif img.startswith("data:image/png"):
pass
else:
os.system(f'wget -q --no-clobber -O infodump/{img} {img}')
image['src'] = img
os.system(f"wget -q --no-clobber -O infodump/{img} {img}")
image["src"] = img
for link in links:
href = link.get('href')
if href and href.startswith('https://i.imgur.com'):
link['href'] = os.path.basename(href)
href = link.get("href")
if href and href.startswith("https://i.imgur.com"):
link["href"] = os.path.basename(href)
with open('infodump/index.html', 'w') as f:
f.write(str(soup))
with open("infodump/index.html", "w") as f:
f.write(str(soup))