Skip to content
Snippets Groups Projects
Commit 8dbecf1b authored by Simon van Hemert's avatar Simon van Hemert
Browse files

last edits

parent 0d8da0df
No related branches found
No related tags found
No related merge requests found
......@@ -13,9 +13,9 @@ USER root
RUN apt-get update && \
apt-get install -y --no-install-recommends \
apt-utils \
# Display server xvfb needed for Selinas
xvfb \
# Geckodriver needed for Selinas
# Display server xvfb needed for Selenium
# xvfb \
# Geckodriver needed for Selenium
firefox-geckodriver
USER ${NB_USER}
......
......@@ -8,6 +8,8 @@ import os
import io
from PIL import Image
import requests
import pathlib
class Image_crawling:
def __init__(self, drive, waittime=0.1):
......@@ -73,7 +75,6 @@ class Image_crawling:
def scroll_to_end(self):
self.drive.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(self.sleep_between_interactions)
......@@ -81,12 +82,7 @@ class Image_crawling:
def download_image(self, folder_path:str):
imagenr = 0
for url in self.image_urls:
# Create directory for images
try:
os.mkdir(folder_path)
except FileExistsError:
pass
pathlib.Path(folder_path).mkdir(parents=True, exist_ok=True)
try:
image_content = requests.get(url).content
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment