Python BeautifulSoup解析HTML获取图片URL并下载到本地

一、Python BeautifulSoup解析HTML获取图片URL并下载到本地

#! python3
# downloadXkcd.py - Downloads every single JDLY comic.
import osimport bs4
import requestsurl = 'https://www.jdlingyu.com/145853.html'
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
}
os.makedirs('JDLY', exist_ok=True)
try:mainRequest = requests.get(url, headers)mainRequest.raise_for_status()# print(mainRequest.text)soup = bs4.BeautifulSoup(mainRequest.text, 'html.parser')  # html解析imgUrls = []imgUrls = soup.select('.entry-content img')  # 获取div class name为entry-content下的img图片# print(imgUrls)for imgUrl in imgUrls:url = imgUrl.get('data-src') # 获取data-src属性img = requests.get(url, headers=headers).content # 获取图片内容# 保存本地with open(os.path.join('JDLY//',os.path.basename(url)), mode='wb') as f:f.write(img)
except Exception as e:print(f"获取图片异常：" + str(e))