时间戳

首页 > 解决方案 > BeatifulSoup 无法从滚动页面加载所有图像

python - BeatifulSoup 无法从滚动页面加载所有图像

问题描述

我正在尝试创建一个包含门窗图像的数据集。为此，我有兴趣从提供大量收藏的网站之一下载图像。该网页的唯一问题是要加载更多图像，我需要向下滚动。稍后，我将使用 BeautifulSoup 解析所有 HTML 内容，但我只能下载少量图像。

import requests
import os
import argparse
import time
from tqdm import tqdm
from bs4 import BeautifulSoup as bs
from urllib.parse import urlparse
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.keys import Keys
from webdriver_manager.firefox import GeckoDriverManager


def is_valid(url):
    """
    Checks whether the 'url' is a valid URL.
    """
    parsed = urlparse(url)
    return bool(parsed.netloc) and bool(parsed.scheme)

def get_all_images(url):
    """
    Returns all image URLs on a single 'url'
    """
    
    options = Options()
    options.headless = True
    driver = webdriver.Firefox(options=options)
    driver.get(url)
    
    elem = driver.find_element_by_tag_name("body")
    no_of_pagedowns = 40

    while no_of_pagedowns:
        elem.send_keys(Keys.PAGE_DOWN)
        time.sleep(0.2)
        no_of_pagedowns -= 1
    
    # beautiful soup allows parsing html of the webpage
    soup = bs(driver.page_source, "html.parser")
    driver.quit()

    urls = []
    for fig in tqdm(soup.find_all("figure"), "Extracting images"):
        try: 
            img_url = fig.find_all("img")[0]["src"]
        except:
            continue

        if not img_url:
            # if img does not contain src attribute then skip it
            continue

        # few images contain HTTP GET key value pairs, e.g. '/image.png?c=3.2.5'
        # we will remove the keys
        try:
            pos = img_url.index("?")
            img_url = img_url[:pos]
        except ValueError:
            pass

        if is_valid(img_url):
            urls.append(img_url)
    return urls

def main(args):
    # get all images
    imgs = get_all_images(args.url)

if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Download images from a given URL."
    )
    parser.add_argument("--url", type=str,
                        help="a URL from where to download images",
                        default="https://unsplash.com/s/photos/door")
    parser.add_argument("--path", type=str,
                        help="path to store the downloaded images locally",
                        default="Photos/Doors")
    args = parser.parse_args()
    main(args)

网页的 HTML 是这样的，在标签内figure是存在的img。感兴趣的图片是分享类_2VWD4 _2zEKz。由于每次下载的图像数量是随机的，因此分页次数几乎没有任何影响。我使用 BeautifulSoup 抓取网页内容的方式是否存在缺陷？我希望从这两个类别中下载大约 5000 张图像。

我已经引用了这个链接来滚动网页。

我下载图像的网站是unsplash。

标签： pythonseleniumbeautifulsouphtml-parsing

解决方案

你的工作现在变得简单多了。该网站进行 ajax 调用以加载返回带有图像链接的 json 的数据

import requests

page_no = 1
res = requests.get("https://unsplash.com/napi/search/photos?query=window&xp=&per_page=20&page={}".format(page_no))
print(res.json())

您可以遍历 json 以获取图像 url，也可以更改页码。

输出：

{'total': 52107, 'total_pages': 2606, 'results': [{'id': '4gRNmhGzYZE', 'created_at': '2018-05-26T12:54:44-04:00', 'updated_at': '2020-07-07T01:27:39-04:00', 'promoted_at': '2018-05-27T06:46:05-04:00', 'width': 4000, 'height': 6000, 'color': '#D9D9E5', 'description': None, 'alt_description': 'gray wooden windowpane', 'urls': {'raw': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}, 'links': {'self': 'https://api.unsplash.com/photos/4gRNmhGzYZE', 'html': 'https://unsplash.com/photos/4gRNmhGzYZE', 'download': 'https://unsplash.com/photos/4gRNmhGzYZE/download', 'download_location': 'https://api.unsplash.com/photos/4gRNmhGzYZE/download'}, 'categories': [], 'likes': 269, 'liked_by_user': False, 'current_user_collections': [], 'sponsorship': None, 'user': {'id': 'FkDy50M-Pvk', 'updated_at': '2020-07-28T15:30:30-04:00', 'username': 'slrncl', 'name': 'Nicolas Solerieu', 'first_name': 'Nicolas', 'last_name': 'Solerieu', 'twitter_username': None, 'portfolio_url': 'http://slrncl.com/', 'bio': '193x92x35 — Fujifilm\r\nMostly plants and landscape, I travel slow when I do.', 'location': 'San Francisco', 'links': {'self': 'https://api.unsplash.com/users/slrncl', 'html': 'https://unsplash.com/@slrncl', 'photos': 'https://api.unsplash.com/users/slrncl/photos', 'likes': 'https://api.unsplash.com/users/slrncl/likes', 'portfolio': 'https://api.unsplash.com/users/slrncl/portfolio', 'following': 'https://api.unsplash.com/users/slrncl/following', 'followers': 'https://api.unsplash.com/users/slrncl/followers'}, 'profile_image': {'small': 'https://images.unsplash.com/profile-1553381672056-e843a19634d1?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=32&w=32', 'medium': 'https://images.unsplash.com/profile-1553381672056-e843a19634d1?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=64&w=64', 'large': 'https://images.unsplash.com/profile-1553381672056-e843a19634d1?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=128&w=128'}, 'instagram_username': 'solerieunicolas', 'total_collections': 1, 'total_likes': 65, 'total_photos': 94, 'accepted_tos': True}, 'tags': [{'type': 'landing_page', 'title': 'window', 'source': {'ancestry': {'type': {'slug': 'wallpapers', 'pretty_slug': 'HD Wallpapers'}, 'category': {'slug': 'desktop', 'pretty_slug': 'Desktop'}, 'subcategory': {'slug': 'windows', 'pretty_slug': 'Windows'}}, 'title': 'HD Windows Wallpapers', 'subtitle': 'Download Free Windows Wallpapers', 'description': 'Choose from a curated selection of Windows wallpapers for your mobile and desktop screens. Always free on Unsplash.', 'meta_title': 'Windows Wallpapers: Free HD Download [500+ HQ] | Unsplash', 'meta_description': 'Choose from hundreds of free Windows wallpapers. Download HD wallpapers for free on Unsplash.', 'cover_photo': {'id': 'R9OS29xJb-8', 'created_at': '2017-07-13T19:38:01-04:00', 'updated_at': '2020-07-21T01:05:51-04:00', 'promoted_at': '2017-07-14T22:49:56-04:00', 'width': 3456, 'height': 2304, 'color': '#9DB2CD', 'description': 'Ergh Jebbi', 'alt_description': 'sand landscape', 'urls': {'raw': 'https://images.unsplash.com/photo-1499988921418-b7df40ff03f9?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjQzMzEwfQ', 'full': 'https://images.unsplash.com/photo-1499988921418-b7df40ff03f9?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjQzMzEwfQ', 'regular': 'https://images.unsplash.com/photo-1499988921418-b7df40ff03f9?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjQzMzEwfQ', 'small': 'https://images.unsplash.com/photo-1499988921418-b7df40ff03f9?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjQzMzEwfQ', 'thumb': 'https://images.unsplash.com/photo-1499988921418-b7df40ff03f9?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjQzMzEwfQ'}, 'links': {'self': 'https://api.unsplash.com/photos/R9OS29xJb-8', 'html': 'https://unsplash.com/photos/R9OS29xJb-8', 'download': 'https://unsplash.com/photos/R9OS29xJb-8/download', 'download_location': 'https://api.unsplash.com/photos/R9OS29xJb-8/download'}, 'categories': [], 'likes': 1460, 'liked_by_user': False, 'current_user_collections': [], 'sponsorship': None, 'user': {'id': 'zpgEV0k9XAA', 'updated_at': '2020-07-23T09:39:36-04:00', 'username': 'm______________e', 'name': 'Mark Eder', 'first_name': 'Mark', 'last_name': 'Eder', 'twitter_username': None, 'portfolio_url': 'http://www.markeder.photography', 'bio': None, 'location': 'Vienna', 'links': {'self': 'https://api.unsplash.com/users/m______________e', 'html': 'https://unsplash.com/@m______________e', 'photos': 'https://api.unsplash.com/users/m______________e/photos', 'likes': 'https://api.unsplash.com/users/m______________e/likes', 'portfolio': 'https://api.unsplash.com/users/m______________e/portfolio', 'following': 'https://api.unsplash.com/users/m______________e/following', 'followers': 'https://api.unsplash.com/users/m______________e/followers'}, 'profile_image': {'small': 'https://images.unsplash.com/profile-1488557507434-790fb0197775?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=32&w=32', 'medium': 'https://images.unsplash.com/profile-1488557507434-790fb0197775?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=64&w=64', 'large': 'https://images.unsplash.com/profile-1488557507434-790fb0197775?ixlib=rb-1.2.1&q=80&fm=jpg&crop=faces&cs=tinysrgb&fit=crop&h=128&w=128'}, 'instagram_username': 'm_______________________e', 'total_collections': 0, 'total_likes': 19, 'total_photos': 14, 'accepted_tos': False}}}}, {'type': 'landing_page', 'title': 'transparent', 'source': {'ancestry': {'type': {'slug': 'backgrounds', 'pretty_slug': 'Backgrounds'}, 'category': {'slug': 'art', 'pretty_slug': 'Art'}, 'subcategory': {'slug': 'transparent', 'pretty_slug': 'Transparent'}}, 'title': 'Transparent Backgrounds', 'subtitle': 'Download free transparent background images', 'description': "Looking to keep your backgrounds simple? Choose a transparent background from Unsplash's catalogue of professional-quality, high resolution photos. Always free on Unsplash.", 'meta_title': '900+ Transparent Background Images: Download HD Backgrounds on Unsplash', 'meta_description': 'Choose from hundreds of free transparent backgrounds. Download beautiful, curated free backgrounds on Unsplash.', 'cover_photo': {'id': '3cWA3U8xb5w', 'created_at': '2017-06-07T01:54:27-04:00', 'updated_at': '2020-07-28T01:20:31-04:00', 'promoted_at': '2017-06-08T05:20:00-04:00', 'width': 3872, 'height': 2592, 'color': '#F4F4F6', 'description': 'Ice shapes the mountains.', 'alt_description': 'person holding clear glass panel', 'urls': {'raw': 'https://images.unsplash.com/photo-1496814801204-280c839ea15a?ixlib=rb-1.2.1', 'full': 'https://images.unsplash.com/photo-1496814801204-280c839ea15a?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb', 'regular': 'https://images.unsplash.com/photo-1496814801204-280c839ea15a?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max', 'small': 'https://images.unsplash.com/photo-1496814801204-280c839ea15a?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max', 'thumb': 'https://images.unsplash.com/photo-1496814801204-280c839ea15a?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max'}, 'links

....
....
...

该网站的美妙之处在于它返回具有不同分辨率的图像。

import requests

page_no = 1
res = requests.get("https://unsplash.com/napi/search/photos?query=window&xp=&per_page=20&page={}".format(page_no))
data = res.json()

for row in data["results"]:
    print(row["urls"])
    print("--" * 10)

输出：

{'raw': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1527352774566-e4916e36c645?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}
--------------------
{'raw': 'https://images.unsplash.com/photo-1509644851169-2acc08aa25b5?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1509644851169-2acc08aa25b5?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1509644851169-2acc08aa25b5?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1509644851169-2acc08aa25b5?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1509644851169-2acc08aa25b5?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}
--------------------
{'raw': 'https://images.unsplash.com/photo-1484068043587-e86f6124d2ee?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1484068043587-e86f6124d2ee?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1484068043587-e86f6124d2ee?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1484068043587-e86f6124d2ee?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1484068043587-e86f6124d2ee?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}
--------------------
{'raw': 'https://images.unsplash.com/photo-1473252812967-d565c3607e28?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1473252812967-d565c3607e28?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1473252812967-d565c3607e28?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1473252812967-d565c3607e28?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1473252812967-d565c3607e28?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}
--------------------
{'raw': 'https://images.unsplash.com/photo-1520971434558-0b482cb0013f?ixlib=rb-1.2.1&ixid=eyJhcHBfaWQiOjEyMDd9', 'full': 'https://images.unsplash.com/photo-1520971434558-0b482cb0013f?ixlib=rb-1.2.1&q=85&fm=jpg&crop=entropy&cs=srgb&ixid=eyJhcHBfaWQiOjEyMDd9', 'regular': 'https://images.unsplash.com/photo-1520971434558-0b482cb0013f?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=1080&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'small': 'https://images.unsplash.com/photo-1520971434558-0b482cb0013f?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=400&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9', 'thumb': 'https://images.unsplash.com/photo-1520971434558-0b482cb0013f?ixlib=rb-1.2.1&q=80&fm=jpg&crop=entropy&cs=tinysrgb&w=200&fit=max&ixid=eyJhcHBfaWQiOjEyMDd9'}
--------------------
....
...

推荐阅读