python 无法获取html_无法使用python从html内容获取链接

这不是小事。k参数值“隐藏”在嵌套iframes中的script元素的深处。下面是一个^{}+^{}获取k值的方法：import re

from urlparse import urljoin

# Python 3: from urllib.parse import urljoin

import requests

from bs4 import BeautifulSoup

base_url = "http://www.protect-stream.com"

with requests.Session() as session:

response = session.get("http://www.protect-stream.com/PS_DL_xODN4o5HjLuqzEX5fRNuhtobXnvL9SeiyYcPLcqaqqXayD8YaIvg9Qo80hvgj4vCQkY95XB7iqcL4aF1YC8HRg_i_i")

# get the top frame url

soup = BeautifulSoup(response.content, "html.parser")

src = soup.select_one('iframe[src^="frame.php"]')["src"]

frame_url = urljoin(base_url, src)

# get the nested frame url

response = session.get(frame_url)

soup = BeautifulSoup(response.content, "html.parser")

src = soup.select_one('iframe[src^="w.php"]')["src"]

frame_url = urljoin(base_url, src)

# get the frame HTML source and extract the "k" value

response = session.get(frame_url)

soup = BeautifulSoup(response.content, "html.parser")

script = soup.find("script", text=lambda text: text and "k=" in text).get_text(strip=True)

k_value = re.search(r'var k="(.*?)";', script).group(1)

print(k_value)

印刷品：

^{pr2}$