拒绝第三方依赖：用纯静态架构，把 900 条豆瓣记录搬进个人博客

pip3 install requests beautifulsoup4

import json
import re
import time
import requests
from bs4 import BeautifulSoup

# ==================== 配置项 ====================
USER_ID = "835"
# 注意：Cookie 字符串内部含有双引号，外层必须使用三引号包裹
COOKIE = '''bid=jRegckXI; dbcl2="83315:gefmOoc"; ck=rAfd; push_noty_num=0; push_doumail_num=0; frodotk_db="d07029fd94221507df8bc6666c6"'''
# ===============================================

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
    "Cookie": COOKIE,
    "Referer": "https://movie.douban.com/",
}

def extract_movie_id(url):
    match = re.search(r"subject/(\d+)/?", url)
    return match.group(1) if match else ""

def get_watched_movies(user_id):
    movies = []
    start = 0
    page = 1

    print(f"=== 开始抓取豆瓣用户 [{user_id}] 观影记录 ===")

    while True:
        url = f"https://movie.douban.com/people/{user_id}/collect?start={start}&sort=time&rating=all&filter=all&mode=grid"
        print(f"[*] 正在抓取第 {page} 页 (Offset: {start})...")

        try:
            resp = requests.get(url, headers=HEADERS, timeout=10)
            if resp.status_code == 403:
                print("[!] 触发豆瓣 403 防爬拦截，请检查 Cookie 是否有效或增大等待间隔。")
                break
            if resp.status_code != 200:
                print(f"[!] 请求异常，状态码: {resp.status_code}")
                break

            soup = BeautifulSoup(resp.text, "html.parser")
            items = soup.select(".grid-view .item")

            if not items:
                print("[✓] 没有更多数据，抓取完成。")
                break

            for item in items:
                # 1. 标题与详情页链接
                title_elem = item.select_one(".info .title a")
                raw_title = title_elem.text if title_elem else ""
                title = " ".join(raw_title.split())
                link = title_elem["href"] if title_elem else ""
                movie_id = extract_movie_id(link)

                # 2. 封面图 (替换为大图尺寸)
                pic_elem = item.select_one(".pic img")
                cover = pic_elem["src"] if pic_elem else ""
                if "/s_ratio_poster/" in cover:
                    cover = cover.replace("/s_ratio_poster/", "/l_ratio_poster/")

                # 3. 标记日期 (YYYY-MM-DD)
                date_elem = item.select_one(".info .date")
                date = date_elem.text.strip() if date_elem else ""

                # 4. 评分 (1-5 星)
                rating = None
                rating_elem = item.select_one('.info [class*="rating"]')
                if rating_elem:
                    for cls in rating_elem.get("class", []):
                        if cls.startswith("rating") and len(cls) >= 7 and cls[6].isdigit():
                            rating = int(cls[6])

                # 5. 标签
                tags_elem = item.select_one(".info .tags")
                tags = tags_elem.text.replace("标签:", "").strip() if tags_elem else ""

                # 6. 短评
                comment_elem = item.select_one(".info .comment")
                comment = comment_elem.text.strip() if comment_elem else ""

                movies.append({
                    "id": movie_id,
                    "title": title,
                    "rating": rating,
                    "date": date,
                    "comment": comment,
                    "tags": tags,
                    "cover": cover,
                    "link": link,
                })

            print(f"[+] 第 {page} 页解析成功，已累计获取 {len(movies)} 条记录。")
            start += 15
            page += 1
            time.sleep(3)

        except Exception as e:
            print(f"[!] 抓取出错: {e}")
            break

    return movies

if __name__ == "__main__":
    data = get_watched_movies(USER_ID)
    output_file = "movies.json"
    with open(output_file, "w", encoding="utf-8") as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

    print(f"\n=== 全部完成！共导出 {len(data)} 条观影数据，保存在 ./{output_file} ===")

python3 export_movies.py

/* 核心状态样式 */
.media-nav-btn {
  background: transparent;
  color: var(--mg-t-m);
  transition: color 0.2s ease;
}

.media-nav-btn.active {
  color: var(--mg-t-p);
}

/* 用 SVG 遮罩实现高级的勾选图标 */
.media-nav-btn.active::after {
  content: "";
  display: inline-block;
  width: 16px;
  height: 16px;
  background: var(--mg-t-p);
  -webkit-mask: url("data:image/svg+xml,...") no-repeat center / contain;
}

# 正确的片名提取姿势
info_div = item.find('div', class_='info')
if info_div:
    title_li = info_div.find('li', class_='title')
    if title_li and title_li.find('a'):
        raw_text = title_li.find('a').text.strip()
        # 用斜杠切割，只取第一部分的简体中文
        title = raw_text.split('/')[0].strip()