如何使用 beautifulSoup 从网站提取和下载所有图像？

Question

我正在尝试从 url 中提取和下载所有图像。我写了一个脚本

import urllib2
import re
from os.path import basename
from urlparse import urlsplit

url = "http://filmygyan.in/katrina-kaifs-top-10-cutest-pics-gallery/"
urlContent = urllib2.urlopen(url).read()
# HTML image tag: <img src="url" alt="some_text"/>
imgUrls = re.findall('img .*?src="(.*?)"', urlContent)

# download all images
for imgUrl in imgUrls:
    try:
        imgData = urllib2.urlopen(imgUrl).read()
        fileName = basename(urlsplit(imgUrl)[2])
        output = open(fileName,'wb')
        output.write(imgData)
        output.close()
    except:
        pass

我不想提取此页面的图像看到此图像http://i.share.pho.to/1c9884b1_l.jpeg我只想获取所有图像而不单击“下一步”按钮我不知道怎么能我得到了“下一个”class 中的所有图片。？我应该在 findall 中做哪些更改？

Answer 1

以下内容应从给定页面中提取所有图像并将其写入正在运行脚本的目录。

import re
import requests
from bs4 import BeautifulSoup

site = 'http://pixabay.com'

response = requests.get(site)

soup = BeautifulSoup(response.text, 'html.parser')
img_tags = soup.find_all('img')

urls = [img['src'] for img in img_tags]


for url in urls:
    filename = re.search(r'/([\w_-]+[.](jpg|gif|png))$', url)
    if not filename:
         print("Regex didn't match with the url: {}".format(url))
         continue
    with open(filename.group(1), 'wb') as f:
        if 'http' not in url:
            # sometimes an image source can be relative 
            # if it is provide the base url which also happens 
            # to be the site variable atm. 
            url = '{}{}'.format(site, url)
        response = requests.get(url)
        f.write(response.content)

Answer 2

对 Jonathan 的回答稍作修改（因为我无法发表评论）：向网站添加“www”将修复大多数“不支持文件类型”的错误。

import re
import requests
from bs4 import BeautifulSoup

site = 'http://www.google.com'

response = requests.get(site)

soup = BeautifulSoup(response.text, 'html.parser')
img_tags = soup.find_all('img')

urls = [img['src'] for img in img_tags]


for url in urls:
    filename = re.search(r'/([\w_-]+[.](jpg|gif|png))$', url)
    if not filename:
         print("Regex didn't match with the url: {}".format(url))
         continue
    with open(filename.group(1), 'wb') as f:
        if 'http' not in url:
            # sometimes an image source can be relative 
            # if it is provide the base url which also happens 
            # to be the site variable atm. 
            url = '{}{}'.format(site, url)
        response = requests.get(url)
        f.write(response.content)

Answer 3

from bs4 import *
import requests
import os


def folder_create(images):
    try:
        folder_name = input("Enter Folder Name:- ")
        # folder creation
        os.mkdir(folder_name)

    
    except:
        print("Folder Exist with that name!")
        folder_create()

    
    download_images(images, folder_name)


def download_images(images, folder_name):
    count = 0
    print(f"Total {len(images)} Image Found!")
    if len(images) != 0:
        for i, image in enumerate(images):          
            try:    
                image_link = image["data-srcset"]
            except:
                try:
                    
                    image_link = image["data-src"]
                except:
                    try:
                        
                        image_link = image["data-fallback-src"]
                    except:
                        try:
                            
                            image_link = image["src"]

                        
                        except:
                            pass

            
            
            try:
                r = requests.get(image_link).content
                try:

                    # possibility of decode
                    r = str(r, 'utf-8')

                except UnicodeDecodeError:

                    with open(f"{folder_name}/images{i+1}.jpg", "wb+") as f:
                        f.write(r)
                    count += 1
            except:
                pass
        
        
        if count == len(images):
            print("All Images Downloaded!")
            
        else:
            print(f"Total {count} Images Downloaded Out of {len(images)}")

def main(url):
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    images = soup.findAll('img')
    folder_create(images)

url = input("Enter URL:- ")
main(url)`

Answer 4

如果您只想要图片，那么您可以直接下载它们，甚至无需删除网页。 都具有相同的 URL：

http://filmygyan.in/wp-content/gallery/katrina-kaifs-top-10-cutest-pics-gallery/cute1.jpg
http://filmygyan.in/wp-content/gallery/katrina-kaifs-top-10-cutest-pics-gallery/cute2.jpg
...
http://filmygyan.in/wp-content/gallery/katrina-kaifs-top-10-cutest-pics-gallery/cute10.jpg

如此简单的代码将为您提供所有图像：

import os
import urllib
import urllib2


baseUrl = "http://filmygyan.in/wp-content/gallery/katrina-kaifs-top-10-"\
      "cutest-pics-gallery/cute%s.jpg"

for i in range(1,11):
    url = baseUrl % i
    urllib.urlretrieve(url, os.path.basename(url))

使用 Beautifulsoup，您必须单击或转到下一页才能删除图像。 如果您想单独废弃每个页面，请尝试使用该类对它们进行刮擦，该类是shutterset_katrina-kaifs-top-10-cutest-pics-gallery