|
|
|
@ -6,3 +6,29 @@ _________________________
|
|
|
|
|
(安装包内置了所有需要用的python库,无需使用任何软件打开喔)
|
|
|
|
|
链接:https://pan.baidu.com/s/1GsrlLqSfbi5d3WM8D-duYA
|
|
|
|
|
提取码:bxgz
|
|
|
|
|
url="https://so.gushiwen.org/gushi/tangshi.aspx"
|
|
|
|
|
r = requests.get(url)
|
|
|
|
|
r.encoding = 'utf-8'
|
|
|
|
|
soup=BeautifulSoup(r.text,'html.parser')
|
|
|
|
|
bg=soup.find("div",class_='sons')
|
|
|
|
|
lb=[]
|
|
|
|
|
body = soup.find_all("div",class_="typecont")
|
|
|
|
|
for i in body:
|
|
|
|
|
juanci = i.text.split()[1::]
|
|
|
|
|
leix = i.find("div",class_="bookMl").text
|
|
|
|
|
for i in juanci:
|
|
|
|
|
try:
|
|
|
|
|
li=i.split('(')
|
|
|
|
|
ci = li[0]
|
|
|
|
|
zz = li[1][:-1]
|
|
|
|
|
lb.append([leix,ci,zz])
|
|
|
|
|
except:
|
|
|
|
|
pass
|
|
|
|
|
lb2=[]
|
|
|
|
|
for i in lb:
|
|
|
|
|
if i[2] == '白居易':
|
|
|
|
|
lb2.append(i)
|
|
|
|
|
for i in lb:
|
|
|
|
|
if i[2] == '李白':
|
|
|
|
|
lb2.append(i)
|
|
|
|
|
tsmc=lb2
|