32 lines
1.3 KiB
Python
32 lines
1.3 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
import json
|
|
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"
|
|
}
|
|
movie_data = []
|
|
for start_offset in [0, 25]:
|
|
url = f"https://movie.douban.com/top250?start={start_offset}"
|
|
resp = requests.get(url, headers=headers)
|
|
soup = BeautifulSoup(resp.text, "html.parser")
|
|
item_list = soup.find_all("div", class_="item")
|
|
for index, item in enumerate(item_list):
|
|
rank = start_offset + index + 1
|
|
title = item.find("span", class_="title").get_text(strip=True)
|
|
info_str = item.find("div", class_="bd").p.get_text(strip=True)
|
|
if "主演:" in info_str:
|
|
actors = info_str.split("主演:")[-1].split("\n")[0].strip()
|
|
else:
|
|
actors = "无"
|
|
quote_tag = item.find("span", class_="inq")
|
|
quote = quote_tag.get_text(strip=True) if quote_tag else ""
|
|
movie_data.append({
|
|
"rank": rank,
|
|
"title": title,
|
|
"actors": actors,
|
|
"quote": quote
|
|
})
|
|
with open("movies.json", "w", encoding="utf-8") as f:
|
|
json.dump(movie_data, f, ensure_ascii=False, indent=2)
|
|
|
|
print(f"爬取完成，共{len(movie_data)}部电影，已生成 movies.json") |