From f363755ee453f062ad1ccf50f84c77f581e0e987 Mon Sep 17 00:00:00 2001
From: s464852 <barbro4@st.amu.edu.pl>
Date: Thu, 26 May 2022 17:01:04 +0200
Subject: [PATCH] Add google images scrapper

---
 assets/scripts/google_images_scrapper.py | 91 ++++++++++++++++++++++++
 1 file changed, 91 insertions(+)
 create mode 100644 assets/scripts/google_images_scrapper.py

diff --git a/assets/scripts/google_images_scrapper.py b/assets/scripts/google_images_scrapper.py
new file mode 100644
index 0000000..a27a328
--- /dev/null
+++ b/assets/scripts/google_images_scrapper.py
@@ -0,0 +1,91 @@
+import hashlib
+import io
+import os
+import time
+import requests
+
+from PIL import Image
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+
+
+def fetch_image_urls(query: str, max_links_to_fetch: int, wd: webdriver, sleep_between_interactions: int = 1):
+    def scroll_to_end(wd):
+        wd.execute_script("window.scrollTo(0, document.body.scrollHeight);")
+        time.sleep(sleep_between_interactions)
+
+    search_url = "https://www.google.com/search?safe=off&site=&tbm=isch&source=hp&q={q}&oq={q}&gs_l=img"
+
+    wd.get(search_url.format(q=query))
+
+    image_urls = set()
+    image_count = 0
+    results_start = 0
+
+    while image_count < max_links_to_fetch:
+        scroll_to_end(wd)
+        thumbnail_results = wd.find_elements(by=By.CSS_SELECTOR, value="img.Q4LuWd")
+        number_results = len(thumbnail_results)
+
+        print(f"Found: {number_results} search results. Extracting links from {results_start}:{number_results}")
+
+        for img in thumbnail_results[results_start:number_results]:
+            try:
+                img.click()
+                time.sleep(sleep_between_interactions)
+            except Exception:
+                continue
+
+            actual_images = wd.find_elements(by=By.CSS_SELECTOR, value="img.n3VNCb")
+            for actual_image in actual_images:
+                if actual_image.get_attribute('src') and 'http' in actual_image.get_attribute('src'):
+                    image_urls.add(actual_image.get_attribute('src'))
+
+            image_count = len(image_urls)
+
+            if len(image_urls) >= max_links_to_fetch:
+                print(f"Found: {len(image_urls)} image links, done!")
+                break
+        else:
+            print("Found:", len(image_urls), "image links, looking for more ...")
+            time.sleep(1)
+        results_start = len(thumbnail_results)
+
+    return image_urls
+
+def download_image(folder_path:str, url:str):
+    try:
+        image_content = requests.get(url).content
+
+    except Exception as e:
+        print(f"ERROR - Could not download {url} - {e}")
+
+    try:
+        image_file = io.BytesIO(image_content)
+        image = Image.open(image_file).convert('RGB')
+        file_path = os.path.join(folder_path,hashlib.sha1(image_content).hexdigest()[:10] + '.jpg')
+        with open(file_path, 'wb') as f:
+            image.save(f, "JPEG", quality=100)
+        print(f"SUCCESS - saved {url} - as {file_path}")
+    except Exception as e:
+        print(f"ERROR - Could not save {url} - {e}")
+
+def search_and_download(search_term:str, target_path='../learning/train', number_images=int):
+    target_folder = os.path.join(target_path, '_'.join(search_term.lower().split(' ')))
+
+    if not os.path.exists(target_folder):
+        os.makedirs(target_folder)
+
+    with webdriver.Chrome() as wd:
+        res = fetch_image_urls(search_term, number_images, wd=wd, sleep_between_interactions=0.5)
+
+    for elem in res:
+        download_image(target_folder, elem)
+
+print("Input search term: ", end='')
+search_term = input()
+print("Input number of images to download: ", end='')
+number_images = int(input())
+
+search_and_download(search_term=search_term, number_images=number_images)
+
-- 
2.20.1