第一题:

import requests
url = ‘http://www.ujxsw.com/modules/article/bookcase.php‘
# 添加cookie，记录用户信息
headers = {
‘user-agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36’,
‘cookie’: ‘Hmlvt_ffafa5ae2f1ca7e65cb521c271c680c5=1641654172; PHPSESSID=5lfpdjre05edk5fpon37r43ka4; username=User; Hm_lpvt_ffafa5ae2f1ca7e65cb521c271c680c5=1641654304’
}
# 发送一个请求
res = requests.get(url, headers=headers)
# 读取数据
html = res.content.decode(‘utf-8’)
# 写入数据
with open(‘书架.html’, ‘w’, encoding=’utf-8’) as f:
f.write(html)
print(“写入成功”)
# 2.打印出我们收藏的书籍名字
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, ‘lxml’)
result = soup.find(‘div’, class=’recrullist’).find_all(‘li’, class=’one’)
a = 1
for i in result:
print(f’第{a}本叫{list(i.strings)[0]}。’)
a += 1

第二题

_’https://images.dmzj.com/img/chapterpic/22608/73743/14981234628701.jpg‘
_import requests
headers = {
‘referer’: ‘https://www.dmzj.com/‘
}
res = requests.get(‘https://images.dmzj.com/img/chapterpic/22608/73743/14981234628701.jpg',headers=headers)
with open(‘漫画.jpg’, ‘wb’) as f:
f.write(res.content)