第 0009 题: 一个HTML文件,找出里面的链接。
解答,这个问题的解答同上一题解答方式,使用soup获取所有的href链接
#encoding:utf-8
import requests
from bs4 import BeautifulSoup
import urllib.request
def get_page(url):
response = requests.get(url)
soup = BeautifulSoup(response.text, "lxml")
return soup
def get_page_urllib(url):
resp = urllib.request.urlopen(url)
soup = BeautifulSoup(resp.read(), "html.parser")
return soup
def get_page_links(soup):
links = []
page_links = soup.find_all("link")
for link in page_links:
links.append(link.get("href"))
return links
soup = get_page("https://github.com/Yixiaohan/show-me-the-code")
links = get_page_links(soup)
print(links)