import requests # 请求，模拟在浏览器的操作
import bs4 # 解析
url = "https://www.gushiwen.cn/"
def get_gushiwen():
response = requests.get(url)
print(response.status_code)
data = response.text
# data2 = response.content
# data3 = data2.decode()
# print(type(data), type(data2),type(data3))
ret = bs4.BeautifulSoup(data, "html.parser")
all_a = ret.find_all("a", {"target":"_blank"})
for i in all_a:
# <a href="https://so.gushiwen.cn/authorv_b90660e3e492.aspx" target="_blank">李白</a>
# 根据href属性和authorv字符串，过滤出来所有的诗人
href = i["href"]
if href.count("authorv")>0:
print(i.text, end=" ")
get_gushiwen()
