Raschiare e scaricare Google Immagini con Python

target_image_path = ".isv-r.PNCib.MSM1fd.BUooTd"
targetted_image_base_html_path = ".VFACy.kGQAp.sMi44c.lNHeqe.WGvvNb"

html = request.get(“https://www.google.com/search”, params=queryParameters, headers=headers, timeout=30)
minestra = BeautifulSoup(html.text, “lxml”)

google_immagini = []

def scrape_and_download_google_images():

images_data_in_json = convert_image_to_json()

matched_image_data = re.findall(r'\”b-GRID_STATE0\”(.*)sideChannel:\s?{}}', images_data_in_json)

remove_matched_thumbnails = remove_matched_get_thumbnails(matched_google_image_data=matched_image_data)

matched_resolution_images = re.findall(r”(?:'|,),\[\”(https:|http.*?)\”,\d+,\d+\]”, removed_matched_thumbnails)

full_resolution_images = get_resolution_image(matched_resolution_images=matched_resolution_images)

per index, (image_data, image_link) in enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1):

append_image_to_list(image_data=image_data, image_link=image_link)

print(f'{index}. l'immagine ha iniziato a scaricarsi')

download_image(image_link=image_link, index=indice)

print(f'{index}. immagine scaricata con successo')

print(f'immagini raschiate e scaricate: {google_images}')

def remove_matched_get_thumbnails(matched_google_image_data):
return re.sub(
r'\[\”(https\:\/\/encrypted-tbn0\.gstatic\.com\/images\?.*?)\”,\d+,\d+\]', “”, str(matched_google_image_data ))

def get_resolution_image(matched_resolution_images):
ritorno [
bytes(bytes(img, “ascii”).decode(“unicode-escape”), “ascii”).decode(“unicode-escape”) for img in matched_resolution_images
]

def convert_image_to_json():
all_script_tags = soup.select(“script”)
images_data = “”.join(re.findall(r”AF_initDataCallback\(([^<]+)\);”, str(all_script_tags)))
fixed_images_data = json.dumps(images_data)
restituisce json.loads(fixed_images_data)

def append_image_to_list(image_data, image_link):
google_images.append({
“image_title”: image_data.select_one(targetted_image_base_html_path)[“title”],
"image_source_link": image_data.select_one(targetted_image_base_html_path)["href"],
"collegamento_immagine": collegamento_immagine
})

def scarica_immagine(collegamento_immagine, indice):
opener=urllib.request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, come Gecko) Chrome/101.0.4951.54 Safari/537.36′)]
urllib.request.install_opener(apri)
urllib.request.urlretrieve(image_link, f'Scraped_Images/Image_{index}.jpg')

scrape_and_download_google_images()

html = request.get(“https://www.google.com/search”, params=queryParameters, headers=headers, timeout=30)
minestra = BeautifulSoup(html.text, “lxml”)

google_immagini = []

images_data_in_json = convert_image_to_json()

matched_image_data = re.findall(r'\”b-GRID_STATE0\”(.*)sideChannel:\s?{}}', images_data_in_json)

remove_matched_thumbnails = remove_matched_get_thumbnails(matched_google_image_data=matched_image_data)

matched_resolution_images = re.findall(r”(?:'|,),\[\”(https:|http.*?)\”,\d+,\d+\]”, removed_matched_thumbnails)

full_resolution_images = get_resolution_image(matched_resolution_images=matched_resolution_images)

per index, (image_data, image_link) in enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1):

append_image_to_list(image_data=image_data, image_link=image_link)

print(f'{index}. l'immagine ha iniziato a scaricarsi')

download_image(image_link=image_link, index=indice)

print(f'{index}. immagine scaricata con successo')

print(f'immagini raschiate e scaricate: {google_images}')