Joakim Persson
55 lines
1.6 KiB
Python
55 lines
1.6 KiB
Python
import os
|
|
import re
|
|
from bs4 import BeautifulSoup
|
|
import requests
|
|
from urllib.parse import urljoin
|
|
|
|
def ladda_ner_bilder(url):
|
|
# Hämta HTML-sidan
|
|
svar = requests.get(url)
|
|
soup = BeautifulSoup(svar.text, 'html.parser')
|
|
|
|
# Hitta alla bilder
|
|
bilder = []
|
|
for img in soup.find_all('img'):
|
|
src = img.get('src')
|
|
if src:
|
|
bilder.append(src)
|
|
|
|
# Hantera inline-bilder i base64
|
|
INLINE_BILD_MÖNSTER = r'data:image/(.*?);base64,(.*)'
|
|
matcher = re.compile(INLINE_BILD_MÖNSTER)
|
|
for match in matcher.finditer(svar.text):
|
|
bild_typ = match.group(1)
|
|
bild_data = match.group(2)
|
|
bilder.append(f"data:{bild_typ};base64,{bild_data}")
|
|
|
|
# Ladda ner bilderna
|
|
bild_katalog = "bilder"
|
|
if not os.path.exists(bild_katalog):
|
|
os.makedirs(bild_katalog)
|
|
|
|
for bild_url in bilder:
|
|
if not bild_url.startswith('http'):
|
|
bild_url = urljoin(url, bild_url)
|
|
|
|
svar = requests.get(bild_url)
|
|
if svar.status_code == 200:
|
|
filnamn = os.path.basename(bild_url)
|
|
fil_sökväg = os.path.join(bild_katalog, filnamn)
|
|
with open(fil_sökväg, 'wb') as f:
|
|
f.write(svar.content)
|
|
print(f"Bilden {filnamn} har laddats ner till {bild_katalog}.")
|
|
|
|
def main():
|
|
url = input("Ange URL till sidan från vilken du vill hämta bilder: ")
|
|
if not url.startswith('http'):
|
|
url = 'http://' + url
|
|
try:
|
|
ladda_ner_bilder(url)
|
|
except Exception as e:
|
|
print(f"Fel inträffade: {e}")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|