如何爬取instagram相关帖子评论信息？

# Web Crawling# Instagram Release Date：Oct 30, 2025
ziome
ziome

在数据采集和分析工作中，Instagram 评论数据是一类非常有价值的内容。它可以反映用户的互动、情绪和热点话题。官方的 Graph API 需要认证和权限，而很多时候我们希望通过 不登录账号 的方式模拟请求来抓取评论。
Instagram使用GraphQL通过后端查询动态生成帖子浏览量。此端点返回不同的帖子数据，包括评论，点赞以及评论者信息等。因此我们可以利用此GraphQL端点来抓取Instagram帖子数据。本文将详细说明步骤及方法作为参考。
1. GraphQL 请求端点
以下是用于检索帖子数据的Graph端点

众所周知，每个GraphQL请求都是需要一个HTTP主体。对于帖子页面抓取，需要以下值：

Copy 
"csrftoken": "4OkRB9KIREX0imrqGS-3nn",
"__dyn":"7xeUjG1mxu1syUbFp41twpUnwgU7SbzEdF8aUco2qwJw5ux609vCwjE1EE2Cw8G11wBz81s8hwGxu786a3a1YwBgao6C0Mo2swtUd8-U2zxe2GewGw9a361qw8Xxm16wa-0oa2-azo7u3vwDwHg2ZwrUdUbGwmk0zU8oC1Iwqo5p0OwUQp1yUb8jxKi2qi7E5y4UrwHwcObBK4o16UswFwtF8",
"__csr":"g9YYrFmGt9AZfFv_VbuBl5KjGnvZSiQ-VpFdu9F3e8LAiGiEzyoa9u8F4ppCfX-EjKZFKmKuqidzFBAGbWxZ4Azox5zWplBBwAgGrxW5tS9ByQfggQuQqqm8zlgiggF4zVFUa6UDKq4XK8Cy8jxi6EB1i3eaxWaw05A1o3mwa21lwlUmgbWw73wio0wi0IdwdOkPxJ0Mw9a0eRw1Wi3lxqcw7Fwj87ut0d2q8ixd1rg6J09_g1eo3qe0hi5ohgKawaK1Xc00Cb80mMw1K2",
"__hsdp":"giMB0zOE8R2450clVE99qxi2m6opaE4C3Wdo56cwzw9FxG4A3m1vwiUgwi9E29iAecwXxy5obEao12E98sxauE98cU0w20esw4cwsEpwnU4y1wwDwYwa20xE3Ewcq0Syxe0hi6U5K2a5OGu1Twc-",
"__hblp":"0Pw8y1ey89axG2l7w4swJG0C8d8cU4CmdDAxC2qbAy98eFEaEeEfU8opxy54iq2a9xTwde3q2i78KquE98cUa8dE3VwtEb-bwkU3Qw60wci0L84-2e68dopwHy8aEcomwkU462-0E826wey0NEiwho5O2gEjwcm1exK2C26fx2cJ1sJ7x21Cx108i3y7Ueonw",
"shortcode":"DGLUo_6tKgY", # Post unique identifier
"doc_id": f"{INSTAGRAM_DOC_ID}", # Constant ID (identifier) used for Instagram posts

从以上细节我们可以得出结论，帖子 ID（短代码）是通过POST向 GraphQL 端点发送请求来抓取 Instagram 帖子页面所需的唯一变量。
2. 抓取帖子数据示例
让我们将此功能添加到我们的 Instagram 抓取工具中：

Python Copy 
import json
import requests
cookies = {
    "csrftoken": "4OkRB9KIREX0imrqGS-3nn",
    "datr": "nRmUaG1CyG0YIekOcKDNZ0UI",
    "ig_did": "F11F1FA5-C00E-4CF6-A249-2A917DD31183",
    "mid": "aJQZnQALAAG_bJTx2M9CiAw52Zr7",
    "ig_nrcb": "1",
    "wd": "163x848",
    "ps_l": "1",
    "ps_n": "1",
}
headers = {
    "accept": "*/*",
    "accept-language": "zh-CN,zh;q=0.9,en;q=0.8",
    "cache-control": "no-cache",
    "content-type": "application/x-www-form-urlencoded",
    "origin": "https://www.instagram.com",
    "pragma": "no-cache",
    "priority": "u=1, i",
    "referer": "https://www.instagram.com/p/DMzTPkHody0/",
    "sec-ch-prefers-color-scheme": "dark",
    "sec-ch-ua": '"Not)A;Brand";v="8", "Chromium";v="138", "Google Chrome";v="138"',
    "sec-ch-ua-full-version-list": '"Not)A;Brand";v="8.0.0.0", "Chromium";v="138.0.7204.184", "Google Chrome";v="138.0.7204.184"',
    "sec-ch-ua-mobile": "?0",
    "sec-ch-ua-platform": '"Windows"',
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36",
    "x-csrftoken": "4OkRB9KIREX0imrqGS-3nn",
    "x-fb-friendly-name": "PolarisPostActionLoadPostQueryQuery",
    "x-ig-app-id": "936619743392459",
}

data = {
    "variables": '{"shortcode":"DGLUo_6tKgY","fetch_tagged_user_count":null,"hoisted_comment_id":null,"hoisted_reply_id":null}',
    "doc_id": "29599222026389233",
}

response = requests.post(
    "https://www.instagram.com/graphql/query",
    cookies=cookies,
    headers=headers,
    data=data,
)
with open("./test.json", "w", encoding="utf-8") as f:
    json.dump(response.json(), f, ensure_ascii=False, indent=2)

上面的 Instagram 抓取代码将返回整个帖子数据集，包括各种字段，例如帖子标题、评论、点赞和其他信息。但是，它也包含许多标志和不必要的字段，这些字段用处不大。
3.解析Instagram帖子数据
Instagram 帖子数据比用户个人资料数据更加复杂。因此，我们需要根据自己的需求进行简化处理，以减小其大小：

Python Copy 
def recombineVideoOrSidecarData(input_url, original_json):
    with open("./test.json", "w", encoding="utf-8") as f:
        json.dump(original_json, f, ensure_ascii=False, indent=4)
    try:
        print("  [Processor] Reconstructing video data in memory...")
        media=original_json.get("data",{}).get("xdt_shortcode_media")
        if not media:
            raise ValueError("Processing failed: 'data.xdt_shortcode_media' node not found in the incoming JSON object.")
        If "Video" in media.get("__typename") and media.get("video_duration"):
            print("--------------Process data into video posts-----------")
            caption_node = (
                media.get("edge_media_to_caption", {})
                .get("edges", [{}])[0]
                .get("node", {})
            )
            caption_text = caption_node.get("text", "")

            def extract_tags(text, prefix):
                if not text:
                    return []
                regex = re.compile(rf"\{prefix}[\w.]+")
                return regex.findall(text)

            comments_edges = media.get("edge_media_to_parent_comment", {}).get(
                "edges", []
            )
            latest_comments = []
            for edge in comments_edges:
                comment_node = edge.get("node")
                if not comment_node:
                    continue
                formatted_comment = _format_comment_node(comment_node)
                if formatted_comment:
                    latest_comments.append(formatted_comment)

            tagged_users_edges = media.get("edge_media_to_tagged_user", {}).get(
                "edges", []
            )
            tagged_users = []
            for edge in tagged_users_edges:
                user_node = edge.get("node", {}).get("user")
                if user_node:
                    tagged_users.append(user_node)

            music_info_raw = media.get("clips_music_attribution_info", {})
            image_data_edges = media.get("edge_sidecar_to_children", {}).get(
                "edges", []
            )
            transformed_post = {
                "inputUrl": input_url,
                "id": media.get("id"),
                "type": media.get("__typename", "").replace("XDTGraph", ""),
                "shortCode": media.get("shortcode"),
                "caption": caption_text,
                "hashtags": extract_tags(caption_text, "#"),
                "mentions": extract_tags(caption_text, "@"),
                "url": f"https://www.instagram.com/p/{media.get('shortcode')}/",
                "commentsCount": media.get("edge_media_to_parent_comment", {}).get(
                    "count", 0
                ),
                "firstComment": (
                    comments_edges[0].get("node", {}).get("text", "")
                    if comments_edges
                    else ""
                ),
                "latestComments": latest_comments,
                "dimensionsHeight": media.get("dimensions", {}).get("height"),
                "dimensionsWidth": media.get("dimensions", {}).get("width"),
                "displayUrl": media.get("display_url"),
                "images": [],
                "videoUrl": media.get("video_url"),
                "alt": media.get("accessibility_caption"),
                "likesCount": media.get("edge_media_preview_like", {}).get("count", 0),
                "videoViewCount": media.get("video_view_count"),
                "videoPlayCount": media.get("video_play_count"),
                "timestamp": datetime.fromtimestamp(
                    media.get("taken_at_timestamp", 0), tz=timezone.utc
                ).isoformat(),
                "childPosts": [],
                "locationName": "",
                "locationId": "",
                "ownerFullName": media.get("owner", {}).get("full_name"),
                "ownerUsername": media.get("owner", {}).get("username"),
                "ownerId": media.get("owner", {}).get("id"),
                "productType": media.get("product_type"),
                "videoDuration": media.get("video_duration"),
                "isSponsored": media.get("is_paid_partnership", False),
                "taggedUsers": tagged_users,
                "musicInfo": {
                    "artist_name": music_info_raw.get("artist_name", ""),
                    "song_name": music_info_raw.get("song_name", ""),
                    "uses_original_audio": music_info_raw.get(
                        "uses_original_audio", False
                    ),
                    "should_mute_audio": music_info_raw.get("should_mute_audio", False),
                    "should_mute_audio_reason": music_info_raw.get(
                        "should_mute_audio_reason", ""
                    ),
                    "audio_id": music_info_raw.get("audio_id", "0"),
                },
                "isCommentsDisabled": media.get("comments_disabled"),
            }

            def format_timestamps_recursively(obj):
                if isinstance(obj, dict):
                    for key, value in obj.items():
                        if key == "timestamp" and isinstance(value, str):
                            obj[key] = value.replace("+00:00", "Z")
                        else:
                            format_timestamps_recursively(value)
                elif isinstance(obj, list):
                    for item in obj:
                        format_timestamps_recursively(item)

            format_timestamps_recursively(transformed_post)
            print(f"  [Processor] ✅ Video data {media.get('shortcode')} reorganization successful.")
            return [transformed_post]

以上是处理视频帖子评论数据的代码样例，因为静态图片类处理方式不同，还需自己编写对应的处理函数。

Update Time：Feb 04, 2026

Comments

Tips: Support some markdown syntax: **bold**, [bold](xxxxxxxxx), `code`, - list, > reference