Kikis dan Unduh Gambar Google dengan 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, batas waktu=30)
sup = BeautifulSoup(html.text, “lxml”)

google_images = []

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 = hapus_matched_get_thumbnails(matched_google_image_data=matched_image_data)

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

gambar_resolusi_penuh = dapatkan_resolusi_gambar(gambar_sesuai_resolusi=gambar_sesuai_resolusi)

untuk indeks, (image_data, image_link) di enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1):

tambahkan_gambar_ke daftar(data_gambar=data_gambar, tautan_gambar=tautan_gambar)

print(f'{index}.image mulai diunduh')

unduh_gambar(tautan_gambar=tautan_gambar, indeks=indeks)

print(f'{index}.image berhasil diunduh')

print(gambar yang diambil dan diunduh: {google_images}')

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

def dapatkan_resolusi_gambar(cocok_resolusi_gambar):
kembali [
bytes(bytes(img, “ascii”).decode(“unicode-escape”), “ascii”).decode(“unicode-escape”) untuk img di 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)
kembalikan 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)[“judul”],
"image_source_link": image_data.select_one(targetted_image_base_html_path)["href"],
“tautan_gambar”: tautan_gambar
})

def unduh_gambar(tautan_gambar, indeks):
pembuka=urllib.request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, seperti Gecko) Chrome/101.0.4951.54 Safari/537.36′)]
urllib.request.install_opener(pembuka)
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, batas waktu=30)
sup = BeautifulSoup(html.text, “lxml”)

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 = hapus_matched_get_thumbnails(matched_google_image_data=matched_image_data)

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

gambar_resolusi_penuh = dapatkan_resolusi_gambar(gambar_sesuai_resolusi=gambar_sesuai_resolusi)

untuk indeks, (image_data, image_link) di enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1):

tambahkan_gambar_ke daftar(data_gambar=data_gambar, tautan_gambar=tautan_gambar)

print(f'{index}.image mulai diunduh')

unduh_gambar(tautan_gambar=tautan_gambar, indeks=indeks)

print(f'{index}.image berhasil diunduh')

print(gambar yang diambil dan diunduh: {google_images}')