完成作业
This commit is contained in:
23
260324.33ljh.py
Normal file
23
260324.33ljh.py
Normal file
@@ -0,0 +1,23 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebkit/537.36 (KHTML, like Gecko) chrome/120.0.0.0 Safari/537.36',
|
||||
|
||||
}
|
||||
|
||||
ur1 = 'https://www.douban.com/doulist/3936288/?start=0&sort=time&playable=0&sub_type='
|
||||
|
||||
response = requests.get(ur1, headers=headers,timeout=10)
|
||||
response.encoding = 'utf-8'
|
||||
|
||||
soup = BeautifulSoup(response.txt, 'html.parser')
|
||||
|
||||
movies = []
|
||||
|
||||
for a in soup.find_all('a'):
|
||||
href = a.get('href','')
|
||||
if '/subject' in href:
|
||||
title - a.get_text(strip=True)
|
||||
print(title)
|
||||
movies.append(title)
|
||||
10
李佳豪.py
10
李佳豪.py
@@ -1,10 +0,0 @@
|
||||
from bs4 import BeautifulSoup
|
||||
soup = BeautifulSoup(html_content, 'lxmx')
|
||||
title = soup.find('title').string
|
||||
print("页面标题:", title)
|
||||
links = soup.find_all('a')
|
||||
for link in links:
|
||||
print("链接地址:", link.get('href'))
|
||||
div_elements = soup.select('div.class_name')
|
||||
for div in div_elements:
|
||||
print("div内容:", div.text)
|
||||
Reference in New Issue
Block a user