Python3 insloader库爬取博主视频粉丝量，点赞，互动率，国家等信息

写在题前：之前搞Java的，今天部门的人给了我一批视频链接，问问有没有办法爬出来这一批视频链接的博主的粉丝量，以及该视频的互动率等信息。经过一番探索之后了解了insloader库。真不不得不感叹python的强大。

 之前给代码把：

import instaloader
from urllib.parse import urlparse
import time
import csv
import os

# Instagram链接列表
INSTAGRAM_URLS = [
    "示例链接",
    "示例链接",

]


def extract_shortcode(url):
    """
    从Instagram链接中提取短代码（shortcode）
    :param url: Instagram帖子链接
    :return: 短代码或None
    """
    try:
        parsed_url = urlparse(url)
        path_parts = parsed_url.path.strip('/').split('/')
        if len(path_parts) >= 2:
            return path_parts[-1]
        elif len(path_parts) == 1:
            return path_parts[0]
        else:
            return None
    except Exception as e:
        print(f"URL: {url} - 短代码提取失败: {e}")
        return None


def fetch_post_data(shortcode, loader):
    """
    通过短代码获取帖子数据
    :param shortcode: 帖子短代码
    :param loader: Instaloader实例
    :return: 字典包含用户名、粉丝量、观看量、点赞数、评论数、互动率、发布时间 或 None
    """
    try:
        post = instaloader.Post.from_shortcode(loader.context, shortcode)
        username = post.owner_username
        followers = post.owner_profile.followers
        # 根据帖子类型获取观看量
        if post.is_video:
            view_count = post.video_view_count
        else:
            view_count = None  # 对于图片帖子，没有观看量
        likes = post.likes
        comments = post.comments
        # 计算互动率
        if followers > 0:
            interaction_rate = (likes + comments) / followers * 100
        else:
            interaction_rate = None
        # 获取发布时间
        post_date = post.date.strftime("%Y-%m-%d %H:%M:%S")

        return {
            "Username": username,
            "Followers": followers,
            "View Count": view_count,
            "Likes": likes,
            "Comments": comments,
            "Interaction Rate (%)": round(interaction_rate, 2) if interaction_rate is not None else None,
            "Post Date": post_date
        }
    except instaloader.exceptions.InstaloaderException as e:
        print(f"短代码: {shortcode} - 错误: {e}")
        return None


def main():
    # 初始化Instaloader
    loader = instaloader.Instaloader()

    # （可选）登录Instagram账号以提高成功率
    # 如果需要抓取私密帖子或提高抓取成功率，请取消下行注释并填写您的Instagram用户名和密码
    # 注意：频繁自动化登录可能违反Instagram的服务条款
    # loader.login('your_username', 'your_password')

    # 存储结果
    results = []

    for url in INSTAGRAM_URLS:
        shortcode = extract_shortcode(url)
        if shortcode:
            post_data = fetch_post_data(shortcode, loader)
            if post_data:
                results.append(post_data)
                print(
                    f"URL: {url} - Username: {post_data['Username']} - Followers: {post_data['Followers']} - Views: {post_data['View Count']} - Likes: {post_data['Likes']} - Comments: {post_data['Comments']} - Interaction Rate: {post_data['Interaction Rate (%)']}% - Post Date: {post_data['Post Date']}")
            else:
                results.append({
                    "Username": "Username not found",
                    "Followers": "N/A",
                    "View Count": "N/A",
                    "Likes": "N/A",
                    "Comments": "N/A",
                    "Interaction Rate (%)": "N/A",
                    "Post Date": "N/A"
                })
                print(f"URL: {url} - Username not found.")
        else:
            results.append({
                "Username": "Invalid URL or shortcode",
                "Followers": "N/A",
                "View Count": "N/A",
                "Likes": "N/A",
                "Comments": "N/A",
                "Interaction Rate (%)": "N/A",
                "Post Date": "N/A"
            })
            print(f"URL: {url} - 无法提取短代码。")

        # 为了避免被Instagram封锁，暂停一段时间
        time.sleep(2)  # 暂停2秒

    # 将结果保存到CSV文件
    csv_filename = "instagram_posts_data.csv"
    with open(csv_filename, mode='w', newline='', encoding='utf-8') as csvfile:
        fieldnames = ["URL", "Username", "Followers", "View Count", "Likes", "Comments", "Interaction Rate (%)",
                      "Post Date"]
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

        writer.writeheader()
        for idx, url in enumerate(INSTAGRAM_URLS):
            if idx < len(results):
                data = results[idx]
                writer.writerow({
                    "URL": url,
                    "Username": data["Username"],
                    "Followers": data["Followers"],
                    "View Count": data["View Count"],
                    "Likes": data["Likes"],
                    "Comments": data["Comments"],
                    "Interaction Rate (%)": data["Interaction Rate (%)"],
                    "Post Date": data["Post Date"]
                })
            else:
                writer.writerow({
                    "URL": url,
                    "Username": "Data not available",
                    "Followers": "N/A",
                    "View Count": "N/A",
                    "Likes": "N/A",
                    "Comments": "N/A",
                    "Interaction Rate (%)": "N/A",
                    "Post Date": "N/A"
                })

if __name__ == "__main__":
    main()

输出结果如下：