43 lines
1.5 KiB
Python
43 lines
1.5 KiB
Python
import requests
|
||
from bs4 import BeautifulSoup
|
||
import json
|
||
import time
|
||
|
||
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"
|
||
}
|
||
|
||
movies = []
|
||
# 豆瓣Top250每页25条，前50条需要爬取2页（start=0和start=25）
|
||
for page in range(2):
|
||
url = f"https://movie.douban.com/top250?start={page*25}"
|
||
response = requests.get(url, headers=headers)
|
||
soup = BeautifulSoup(response.text, "html.parser")
|
||
|
||
items = soup.find_all("div", class_="item")
|
||
for idx, item in enumerate(items):
|
||
rank = page * 25 + idx + 1
|
||
# 电影名称
|
||
title = item.find("span", class_="title").text.strip()
|
||
# 主演信息
|
||
info = item.find("div", class_="bd").find("p", class_="").text.strip()
|
||
actors = info.split("\n")[0].split("主演:")[-1].strip() if "主演:" in info else "未知"
|
||
# 短评
|
||
quote_tag = item.find("span", class_="inq")
|
||
quote = quote_tag.text.strip() if quote_tag else "无短评"
|
||
|
||
movies.append({
|
||
"rank": rank,
|
||
"title": title,
|
||
"actors": actors,
|
||
"quote": quote
|
||
})
|
||
|
||
# 礼貌间隔，避免被反爬
|
||
time.sleep(1)
|
||
|
||
# 保存为movies.json
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(movies, f, ensure_ascii=False, indent=2)
|
||
|
||
print("爬取完成，数据已保存到 movies.json") |