Xuliqin Practice1127-3

%pip install requests beautifulsoup4

Requirement already satisfied: requests in d:\program files\python3.12.7\lib\site-packages (2.32.3)
Requirement already satisfied: beautifulsoup4 in d:\program files\python3.12.7\lib\site-packages (4.12.3)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\program files\python3.12.7\lib\site-packages (from requests) (3.4.0)
Requirement already satisfied: idna<4,>=2.5 in d:\program files\python3.12.7\lib\site-packages (from requests) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\program files\python3.12.7\lib\site-packages (from requests) (2.2.3)
Requirement already satisfied: certifi>=2017.4.17 in d:\program files\python3.12.7\lib\site-packages (from requests) (2024.8.30)
Requirement already satisfied: soupsieve>1.2 in d:\program files\python3.12.7\lib\site-packages (from beautifulsoup4) (2.6)
Note: you may need to restart the kernel to use updated packages.

[notice] A new release of pip is available: 24.2 -> 24.3.1
[notice] To update, run: pythonw.exe -m pip install --upgrade pip

import requests
 
# 定义请求的 URL 和 headers
url = "https://movie.douban.com/top250"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
 
# 发送 GET 请求
response = requests.get(url, headers=headers)
response.encoding = 'utf-8'  # 设置编码方式
html_content = response.text  # 获取网页的 HTML 内容
print("网页内容加载成功！")

网页内容加载成功！

from bs4 import BeautifulSoup
 
# 使用 Beautiful Soup 解析 HTML
soup = BeautifulSoup(html_content, 'html.parser')
 
# 提取电影名称、描述、评分和评价人数
movies = []
for item in soup.find_all('div', class_='item'):
    title = item.find('span', class_='title').get_text()  # 电影名称
    description = item.find('span', class_='inq')  # 电影描述
    rating = item.find('span', class_='rating_num').get_text()  # 评分
    votes = item.find('div', class_='star').find_all('span')[3].get_text()  # 评价人数
    
    # 如果没有描述，将其置为空字符串
    if description:
        description = description.get_text()
    else:
        description = ''
    
    movie = {
        "title": title,
        "description": description,
        "rating": rating,
        "votes": votes.replace('人评价', '').strip()
    }
    movies.append(movie)
 
print("数据提取成功！")

数据提取成功！

import csv
 
# 将数据保存到 CSV 文件
with open('./file/douban_top250.csv', 'w', newline='', encoding='utf-8') as csvfile:
    fieldnames = ['title', 'description', 'rating', 'votes']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
 
    writer.writeheader()  # 写入表头
    for movie in movies:
        writer.writerow(movie)  # 写入每一行数据
 
print("数据已成功保存到 douban_top250.csv")

数据已成功保存到 douban_top250.csv

import requests
from bs4 import BeautifulSoup
import csv
 
# 定义请求的 URL 和 headers
url = "https://movie.douban.com/top250"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
 
# 发送 GET 请求
response = requests.get(url, headers=headers)
response.encoding = 'utf-8'  # 设置编码方式
html_content = response.text  # 获取网页的 HTML 内容
 
# 使用 Beautiful Soup 解析 HTML
soup = BeautifulSoup(html_content, 'html.parser')
 
# 提取电影名称、描述、评分和评价人数
movies = []
for item in soup.find_all('div', class_='item'):
    title = item.find('span', class_='title').get_text()  # 电影名称
    description = item.find('span', class_='inq')  # 电影描述
    rating = item.find('span', class_='rating_num').get_text()  # 评分
    votes = item.find('div', class_='star').find_all('span')[3].get_text()  # 评价人数
    
    # 如果没有描述，将其置为空字符串
    if description:
        description = description.get_text()
    else:
        description = ''
    
    movie = {
        "title": title,
        "description": description,
        "rating": rating,
        "votes": votes.replace('人评价', '').strip()
    }
    movies.append(movie)
 
# 将数据保存到 CSV 文件
with open('./file/douban_top250.csv', 'w', newline='', encoding='utf-8') as csvfile:
    fieldnames = ['title', 'description', 'rating', 'votes']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
 
    writer.writeheader()  # 写入表头
    for movie in movies:
        writer.writerow(movie)  # 写入每一行数据
 
print("数据已成功保存到 douban_top250.csv")

数据已成功保存到 douban_top250.csv