2509165016/task-2-1-data-collection
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

完成作业2：爬虫

Browse Source
This commit is contained in:
2509165016
2026-03-26 15:35:50 +08:00
parent 89df5438eb
commit 256d2cb21d
3 changed files with 31 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
2509165016 task-2-1-data-collection.py Normal file
View File

@@ -0,0 +1,31 @@
import requests
from bs4 import BeatifulSoup
a = 0
url = f'https://ww.douban.com/doulist/3936288/?start={a}&sort=time&piayable=0&sub_type='
headers = {'User-Agent':'Mozilla/5.0 (windows NT 6.1; Win64; x64) AppleWebkit/537.36 (KHTHL, like Gecko) Chrome/96.0.4664.110 Safari/537.36'}
# print(soup)
# print('---------------------------')
# print('---------------------------')
# print('---------------------------')
response = requests.get(ur1, headers=headers,timeout=10)
response.encoding = 'utf-8'
soup = BeatifulSoup(response.text, 'html.parser')
print(soup)
for b in soup.find_all('a'):
# print(a)
href - b.get('herf','')
if '/subject/'in href:
title = b.get_text(strip=True)
print(title)
//'('@id="17923343"j/div/div(2)/div(4)/a
c - soup.select('a')
print(c)

42
爬虫2.txt
View File

@@ -1,42 +0,0 @@
# 人工智能数据服务 - 作业二
# 学号：你的学号
# 姓名：你的姓名
print("=" * 40)
print("学号：2509165016")
print("姓名：郭宇涵")
print("Hello, Git!")
print("我已经学会使用 Git 提交作业啦！")
print("=" * 40)
import requests
from bs4 import BeautifulSoup as bs
print('-------------')
url = 'https://www.baidu.com'
params = {'key':'value'}
response = requests.get(url,params=params)
print(response.status_code)
print('-------------')
html_content = response.text
print(html__content)
print('-------------')
soup = bs(html_content,'lxml')
print(soup)
print('-------------')
title = soup.find('title').string
print(title)
print('-------------')
links = soup.find_all('a')
print(links)
print('-------------')
for link in links:
# print("11111111")
print("链接:",linl.get('href'))
div_elements = soup.select('div.di')
print(div_elements)
for div in div_elements:
print('div:',div.text)

26
爬虫3.py.txt
View File

@@ -1,26 +0,0 @@
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',
}
url = 'https://www.douban.com/doulist/3936288/?start=25&sort=time&playable=0&sub_type='
response = requests.get(url, headers=headers, timeout=10)
response.encoding = 'utf-8'
for page in range(10):
url = f'https://movie.douban.com/top250?start={page*25}'
print(f'正在爬取第 {page+1} 页：{url}')
# print(response.status_code)
soup = BeautifulSoup(response.text, 'html.parser')
movies = []
for a in soup.find_all('a'):
href = a.get('href', '')
if '?' in href:
title = a.get_text(strip=True)
print(title)
movies.append(title)