废话不多说，完整代码如下：

import requests
import pandas as pd
import time
import re
import os
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry

# ====== 配置 ======
API_KEY = "你的apikey"
BASE_URL = "https://api.themoviedb.org/3"
OUTPUT_CSV = "tmdb_movies_boxoffice.csv"
OUTPUT_XLSX = "tmdb_movies_boxoffice.xlsx"
TOTAL_PAGES = 650  # 每页约20条
REQUEST_DELAY = 0.25  # 秒

# ====== 禁用代理 ======
os.environ.pop('HTTP_PROXY', None)
os.environ.pop('HTTPS_PROXY', None)

# ====== Session + 重试配置 ======
session = requests.Session()
retry = Retry(
    total=5,
    backoff_factor=1,
    status_forcelist=[500, 502, 503, 504]
)
adapter = HTTPAdapter(max_retries=retry)
session.mount("http://", adapter)
session.mount("https://", adapter)

# ====== 函数 ======
def fetch_movies(category="popular", page=1):
    url = f"{BASE_URL}/movie/{category}"
    params = {"api_key": API_KEY, "language": "zh-CN", "page": page}
    try:
        resp = session.get(url, params=params, timeout=10)
        resp.raise_for_status()
        return resp.json().get("results", [])
    except Exception as e:
        print(f"请求 {category} 页 {page} 失败: {e}")
        return []

def fetch_movie_details(movie_id):
    url = f"{BASE_URL}/movie/{movie_id}"
    params = {"api_key": API_KEY, "language": "zh-CN"}
    try:
        resp = session.get(url, params=params, timeout=10)
        resp.raise_for_status()
        return resp.json()
    except Exception as e:
        print(f"电影详情请求失败 (ID: {movie_id}): {e}")
        return {}

def is_valid_title(title: str) -> bool:
    if not title or title.strip() == "":
        return False
    if not re.match(r"^[\u4e00-\u9fa5a-zA-Z0-9\s:：\-—·,.!?()（）]+$", title):
        return False
    return True

def parse_movie(movie, details):
    revenue = details.get("revenue", 0)
    title = movie.get("title", "").strip()
    if revenue is None or revenue == 0:
        return None
    if not is_valid_title(title):
        return None
    return {
        "id": movie.get("id"),
        "title": title,
        "original_title": movie.get("original_title"),
        "release_date": movie.get("release_date"),
        "vote_average": movie.get("vote_average"),
        "vote_count": movie.get("vote_count"),
        "popularity": movie.get("popularity"),
        "original_language": movie.get("original_language"),
        "budget": details.get("budget"),
        "revenue": revenue
    }

# ====== 主流程 ======
all_movies = []
categories = ["popular", "top_rated", "now_playing", "upcoming"]

for cat in categories:
    print(f"\n开始抓取 /movie/{cat} ...")
    for page in range(1, TOTAL_PAGES + 1):
        print(f"抓取 {cat} 第 {page} 页...")
        movies = fetch_movies(cat, page)
        if not movies:
            break
        for m in movies:
            details = fetch_movie_details(m["id"])
            movie_data = parse_movie(m, details)
            if movie_data:
                all_movies.append(movie_data)
                print(f"✅ {movie_data['title']} | 票房: {movie_data['revenue']}")
            else:
                print(f"❌ 跳过无效电影: {m.get('title')}")
            time.sleep(REQUEST_DELAY)
        print(f"{cat} 第 {page} 页完成，当前累计有效电影: {len(all_movies)}")

# ====== 保存 ======
df = pd.DataFrame(all_movies)
df.to_csv(OUTPUT_CSV, index=False, encoding="utf-8-sig")
df.to_excel(OUTPUT_XLSX, index=False)

print(f"\n完成！共保存 {len(all_movies)} 条有效电影数据")
print(f"已写入 {OUTPUT_CSV} 和 {OUTPUT_XLSX}")

其中最关键的API_KEY = "你的apikey"上文中已经有详细的描述如何获取。

测试 API Key

        可以在浏览器访问，例如：https://api.themoviedb.org/3/movie/550?api_key=你的API_KEY

如果返回 JSON 数据，说明 Key 已可用。

爬取结果存到csv和excel两个文档中。