Python으로 Google 이미지 스크랩 및 다운로드

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

html = requests.get(“https://www.google.com/search”, params=queryParameters, headers=headers, timeout=30)
수프 = 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)

removed_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(일치된_해상도_이미지=일치된_해상도_이미지)

색인의 경우 enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1)의 (image_data, image_link):

append_image_to_list(이미지_데이터=이미지_데이터, 이미지_링크=이미지_링크)

print(f'{index}.이미지 다운로드 시작')

download_image(이미지_링크=이미지_링크, 색인=색인)

print(f'{index}. 이미지 다운로드 성공')

print(f'스크랩 및 다운로드한 이미지: {google_images}')

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

def get_resolution_image(일치된_해상도_이미지):
반품 [
bytes(bytes(img, "ascii").decode("unicode-escape"), "ascii").decode("unicode-escape") for img in matching_resolution_images
]

def convert_image_to_json():
all_script_tags = soup.select("스크립트")
images_data = "".join(re.findall(r"AF_initDataCallback\(([^<]+)\);", ​​str(all_script_tags)))
fixed_images_data = json.dumps(이미지_데이터)
json.loads(fixed_images_data) 반환

def append_image_to_list(이미지_데이터, 이미지_링크):
google_images.append({
"이미지_제목": image_data.select_one(targetted_image_base_html_path)["제목"],
"이미지_소스_링크": image_data.select_one(targetted_image_base_html_path)["href"],
"이미지_링크": 이미지_링크
})

def download_image(이미지_링크, 색인):
opener=urllib.request.build_opener()
opener.addheaders=[('사용자 에이전트','Mozilla/5.0(Windows NT 10.0; Win64; x64) AppleWebKit/537.36(Gecko와 같은 KHTML) Chrome/101.0.4951.54 Safari/537.36')]
urllib.request.install_opener(열기)
urllib.request.urlretrieve(image_link, f'Scraped_Images/Image_{index}.jpg')

scrape_and_download_google_images()

html = requests.get(“https://www.google.com/search”, params=queryParameters, headers=headers, timeout=30)
수프 = 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)

removed_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(일치된_해상도_이미지=일치된_해상도_이미지)

색인의 경우 enumerate(zip(soup.select(target_image_path), full_resolution_images), start=1)의 (image_data, image_link):

append_image_to_list(이미지_데이터=이미지_데이터, 이미지_링크=이미지_링크)

print(f'{index}.이미지 다운로드 시작')

download_image(이미지_링크=이미지_링크, 색인=색인)

print(f'{index}. 이미지 다운로드 성공')

print(f'스크랩 및 다운로드한 이미지: {google_images}')