Mirrors/kleinanzeigen-bot
1
0
Fork 0
mirror of https://github.com/Second-Hand-Friends/kleinanzeigen-bot.git synced 2026-03-12 02:31:45 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: downloaded images have wrong file extension #348

Browse Source
This commit is contained in:
sebthom
2024-11-21 22:53:35 +01:00
parent fe13131dee
commit 86c3aeea85
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/kleinanzeigen_bot/extract.py
View File

@@ -5,6 +5,7 @@ SPDX-ArtifactOfProjectHomePage: https://github.com/Second-Hand-Friends/kleinanze
""" """
import logging, os, shutil import logging, os, shutil
import urllib.request as urllib_request import urllib.request as urllib_request
import mimetypes
from datetime import datetime from datetime import datetime
from typing import Any, Final from typing import Any, Final
@@ -77,12 +78,15 @@ class AdExtractor(WebScrapingMixin):
current_img_url = img_element.attrs['src'] # URL of the image current_img_url = img_element.attrs['src'] # URL of the image
if current_img_url is None: if current_img_url is None:
continue continue
file_ending = current_img_url.split('.')[-1].lower()
img_path = directory + '/' + img_fn_prefix + str(img_nr) + '.' + file_ending with urllib_request.urlopen(current_img_url) as response: # nosec B310
if current_img_url.startswith('https'): # verify https (for Bandit linter) content_type = response.info().get_content_type()
urllib_request.urlretrieve(current_img_url, img_path) # nosec B310 file_ending = mimetypes.guess_extension(content_type)
dl_counter += 1 img_path = f"{directory}/{img_fn_prefix}{img_nr}{file_ending}"
img_paths.append(img_path.split('/')[-1]) with open(img_path, 'wb') as f:
shutil.copyfileobj(response, f)
dl_counter += 1
img_paths.append(img_path.rsplit('/', maxsplit = 1)[-1])
# navigate to next image (if exists) # navigate to next image (if exists)
if img_nr < n_images: if img_nr < n_images: