python - 修改url参数以从多个网站下载图片

Question

我试图从 CaseIDs 数组中包含的所有案例中下载图像，但它不起作用。我希望代码能够在所有情况下运行。

from bs4 import BeautifulSoup
import requests as rq
from urllib.parse import urljoin
from tqdm import tqdm

CaseIDs = [100237, 99817, 100271]

with rq.session() as s:
    for caseid in tqdm(CaseIDs):
        url = 'https://crashviewer.nhtsa.dot.gov/nass-CIREN/CaseForm.aspx?xsl=main.xsl&CaseID= {caseid}'
        r = s.get(url)
        soup = BeautifulSoup(r.text, "html.parser")

        url = urljoin(url, soup.find('a', text='Text and Images Only')['href'])
        r = s.get(url)
        soup = BeautifulSoup(r.text, "html.parser")

        links = [urljoin(url, i['src']) for i in soup.select('img[src^="GetBinary.aspx"]')]

        count = 0
        for link in links:
            content = s.get(link).content
            with open("test_image" + str(count) + ".jpg", 'wb') as f:
                f.write(content)
            count += 1

Answer 1

尝试像这样使用format():

url = 'https://crashviewer.nhtsa.dot.gov/nass-CIREN/CaseForm.aspx?xsl=main.xsl&CaseID={}'.format(caseid)