python - 如何返回最大尺寸的图像

Question

我已经能够过滤出页面中的所有图片网址，并一个接一个地显示它们

import requests
from bs4 import BeautifulSoup


article_URL = "https://medium.com/bhavaniravi/build-your-1st-python-web-app-with-flask-b039d11f101c"
response = requests.get(article_URL)
soup = bs4.BeautifulSoup(response.text,'html.parser')
images = soup.find('body').find_all('img')
i = 0
image_url = []
for im in images:
    print(im)
    i+=1
    url = im.get('src')
    image_url.append(url)
    print('Downloading: ', url) 
    try:
        response = requests.get(url, stream=True)
        with open(str(i) + '.jpg', 'wb') as out_file:
            shutil.copyfileobj(response.raw, out_file)
            del response
    except:
        print('Could not download: ', url)

new = [x for x in image_url if x is not None]
for url in new:
    resp = requests.get(url, stream=True).raw
    image = np.asarray(bytearray(resp.read()), dtype="uint8")
    image = cv2.imdecode(image, cv2.IMREAD_COLOR)
#     height, width, channels = image.shape
    height, width, _ = image.shape
    dimension = []
    for items in height, width:
        dimension.append(items)
#     print(height, width)
    print(dimension)

我想从URL列表中打印最大尺寸的图像
这是我从列表中得到的结果，这还不够好

[72, 72]
[95, 96]
[13, 60]
[227, 973]
[17, 60]
[229, 771]

Answer 1

我看到两个问题。

您可以在循环内创建dimention = []，以便删除先前的值。您必须在循环和内部循环使用之前创建dimention = []

dimension.append( (width, height) )

在循环之后，您可以使用max(dimension)与max width配对

您仅将width, height保留在dimension中，因此您不知道哪个文件具有此尺寸。您应该保留所有信息

dimension.append( (width, height, url, filename) ) 

我的版本。
我使用字典 data保留所有信息

data.append({
                'url': url,
                'path': filename,
                'width': width,
                'height': height,
            })

然后我在 key中使用 max()来获取最大 width的项目

max(data, key=lambda x:x['width'])

但是我可以使用 x['height']或 x['width'] * x['height']的方式相同

import requests
from bs4 import BeautifulSoup
import shutil
import cv2

article_URL = "https://medium.com/bhavaniravi/build-your-1st-python-web-app-with-flask-b039d11f101c"

response = requests.get(article_URL)
soup = BeautifulSoup(response.text, 'html.parser')
images = soup.find('body').find_all('img')

# --- loop --- 

data = []
i = 0

for img in images:
    print('HTML:', img)
    
    url = img.get('src')

    if url:  # skip `url` with `None`
        print('Downloading:', url) 
        try:
            response = requests.get(url, stream=True)

            i += 1
            url = url.rsplit('?', 1)[0]  # remove ?opt=20 after filename
            ext = url.rsplit('.', 1)[-1] # .png, .jpg, .jpeg
            filename = f'{i}.{ext}' 
            print('Filename:', filename)

            with open(filename, 'wb') as out_file:
                shutil.copyfileobj(response.raw, out_file)

            image = cv2.imread(filename)
            height, width = image.shape[:2]

            data.append({
                'url': url,
                'path': filename,
                'width': width,
                'height': height,
            })

        except Exception as ex:
            print('Could not download: ', url)
            print('Exception:', ex)

    print('---')

# --- after loop ---

print('max:', max(data, key=lambda x:x['width']))

all_sorted = sorted(data, key=lambda x:x['width'], reverse=True)

print('Top 3:', all_sorted[:3])
# or
for item in all_sorted[:3]:
    print(item['width'], item['url'])

BTW:仅使用 src获取图像

 .find_all('img', {'src': True})