首先需要下载浏览器对应版本的msedgedriver.exe,然后创建浏览器WebDriver实例
edge_driver_path = "msedgedriver.exe" # 此处需要填写自己的edgeDriver路径
s = Service(edge_driver_path)
my_driver = webdriver.Edge(service=s)
通过selenium实现动态加载页面并获取资源路径
def get_src(driver, a_url): # 通过selenium包获取动态页面的src
# 打开网页
driver.get(a_url)
# 等待一段时间确保页面加载完成
time.sleep(4)
# 获取完整页面内容
page_source = driver.page_source
# 使用BeautifulSoup解析HTML
a_soup = BeautifulSoup(page_source, 'html.parser')
# 找到id为"pdf"的iframe元素
pdf_iframe = a_soup.find('iframe', {'id': 'pdf'})
# 提取iframe的src属性
if pdf_iframe:
pdf_src = pdf_iframe.get('src')
if pdf_src[0]=='h':
return pdf_src
else:
pdf_src = "https:" + pdf_src
return pdf_src
else:
pdf_src = "fail"
return pdf_src
通过设置 User-Agent
标头,代码模拟浏览器向服务器发出请求,这有助于确保服务器以与浏览器相同的方式响应请求。
def download_pdf(load_path, url_path): # 先放下载路径,再放资源路径
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Referer': 'https://sci.bban.top/'
}
response = requests.get(url_path, headers=headers)
if response.status_code == 200:
with open(load_path, 'wb') as file:
file.write(response.content)
print(f"PDF文件已保存到: {load_path}")
else:
print('文件下载失败,状态码:', response.status_code)