豆瓣爬取排行榜电影

import requests
from bs4 import BeautifulSoup
import csv

# 豆瓣电影榜单的URL
url = 'https://movie.douban.com/chart'

# 设置请求头，伪装成浏览器访问
header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36 Edg/92.0.902.55',
    'Cookie': ''
}

# 发送GET请求
response = requests.get(url, headers=header)
print(response.status_code)
# 检查请求是否成功
if response.status_code == 200:
    # 使用BeautifulSoup解析HTML内容
    soup = BeautifulSoup(response.content, 'html.parser')

    # 选择电影标题的元素，这里假设电影标题在具有'pl2 a'类的<a>标签中
    movie_info = soup.select('.item')
    movices = []
    for each in movie_info:
        movie = {}
        title = each.select('.pl2 a')[0].text.split('/')[0].strip()
        try:
            rating = each.select_one('.rating_nums').text
        except AttributeError:
            rating = "暂无评分"
        try:
            count = int(each.select('.star .pl')[0].text[1:-4])
        except:
            pass
        print(title)
        print(rating)
        print(count)
        movie['title'] = title
        movie['rating'] = rating
        movie['count'] = count
        movices.append(movie)
else:
    print(f"请求失败，状态码：{response.status_code}")
print(movices)

# 数据写入
with open("movies.csv", "w", newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(["片名", "评分", "评价人数"])
    # 选择你要导出的讲师还是教授
    for member in movices:
        writer.writerow([member['title'], member['rating'], member['count']])