35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
import requests
|
||
import json
|
||
from bs4 import BeautifulSoup
|
||
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
|
||
}
|
||
|
||
movies = []
|
||
# 豆瓣Top250每页25条，前50条需爬2页
|
||
for start in [0, 25]:
|
||
url = f"https://movie.douban.com/top250?start={start}"
|
||
res = requests.get(url, headers=headers)
|
||
soup = BeautifulSoup(res.text, "html.parser")
|
||
|
||
for item in soup.select(".item"):
|
||
rank = item.select_one(".pic em").text
|
||
title = item.select_one(".title").text
|
||
# 主演信息处理
|
||
info = item.select_one(".bd p").text.strip().split("\n")[0]
|
||
actors = info.split("主演:")[-1].split(" / ")[0].strip() if "主演:" in info else ""
|
||
# 短评（quote）处理
|
||
quote_tag = item.select_one(".quote .inq")
|
||
quote = quote_tag.text if quote_tag else ""
|
||
|
||
movies.append({
|
||
"rank": int(rank),
|
||
"title": title,
|
||
"actors": actors,
|
||
"quote": quote
|
||
})
|
||
|
||
# 保存为json文件
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(movies, f, ensure_ascii=False, indent=2) |