Python 爬取携程景区评论数据实战

携程景区评论数据可通过 Python requests 库模拟接口请求获取。通过开发者工具定位 getCommentCollapseList 接口，构造包含 cookies 和 headers 的请求参数。解析返回的 JSON 数据提取评论内容、评分、用户信息等字段。支持分页爬取，单页最大 300 条。最终可将数据保存为 CSV 或 TXT 文件进行后续分析统计。

laoliangsh发布于 2026/3/150 浏览

爬虫

打开携程网，找到某个景区点击跳转到详情页面。
按 F12 打开开发者工具，然后点击下评论下一页来监听是否有网络请求更新。如果没有那就看页面地址栏是否发生变化，前者是动态更新（post 请求，通过调后端接口完成数据更新），后者是静态更新（get 请求，通过 html 页面更新数据）。

通过搜索评论内容定位到评论数据是通过调 getCommentCollapseList 接口返回的。

那么我们现在已经知道数据在哪个接口中，接下来就需要在本地模拟调用这个请求即可，这里我是用 Python 的 requests 库实现。可使用 curlconverter.com 将 curl 请求转换为代码。

import requests

def crawlComment():
    cookies = {
        'GUID': '09031069217559688465',
        'MKT_CKID': '1751274744072.9fx30.ncpi',
        '_RSG': 'Ce4EW5dni37P3spnPcTGtA',
        '_RDG': '281fac73a494fd20293dac96d16828aefe',
        '_RGUID': '70ecc671-6038-4a0c-add0-766671cf60d9',
        '_ga': 'GA1.1.1991158589.1751274745',
        'nfes_isSupportWebP': '1',
        'ibulocale': 'zh_cn',
        'cookiePricesDisplayed': 'CNY',
        '_abtest_userid': '1a3ec536-4b47-4de6-a67e-b8a48f5801d2',
        'Corp_ResLang': 'zh-cn',
        '_bfaStatusPVSend': '1',
        'UBT_VID': '1752483344037.225tvy',
        '_bfaStatus': 'success',
        '_RF1': '123.177.53.139',
        'intl_ht1': 'h4=2_77366892,1_125617009,1_1452207,1_37887757,1_1216725,1_451914',
        'Session': ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : 
    }
    headers = {
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : ,
        : 
    }
    params = {
        : ,
        : 
    }
    json_data = {
        : {
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : 
        },
        : {
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : ,
            : []
        }
    }
    response = requests.post(
        ,
        params=params,
        cookies=cookies,
        headers=headers,
        json=json_data
    )
     response.json()

相关免费在线工具

加密/解密文本

使用加密算法（如AES、TripleDES、Rabbit或RC4）加密和解密文本明文。在线工具，加密/解密文本在线工具，online

curl 转代码

解析常见 curl 参数并生成 fetch、axios、PHP curl 或 Python requests 示例代码。在线工具，curl 转代码在线工具，online

Base64 字符串编码/解码

将字符串编码和解码为其 Base64 格式表示形式即可。在线工具，Base64 字符串编码/解码在线工具，online

Base64 文件转换器

将字符串、文件或图像转换为其 Base64 表示形式。在线工具，Base64 文件转换器在线工具，online

Markdown转HTML

将 Markdown（GFM）转为 HTML 片段，浏览器内 marked 解析；与 HTML转Markdown 互为补充。在线工具，Markdown转HTML在线工具，online

HTML转Markdown

将 HTML 片段转为 GitHub Flavored Markdown，支持标题、列表、链接、代码块与表格等；浏览器内处理，可链接预填。在线工具，HTML转Markdown在线工具，online

import json import pandas as pd from datetime import datetime def extract_comments_from_json(json_data): comments = [] if 'result' in json_data and 'items' in json_data['result']: items = json_data['result']['items'] for item in items: comment_info = { 'comment_id': item.get('commentId'), 'user_nick': item.get('userInfo', {}).get('userNick', ''), 'user_member': item.get('userInfo', {}).get('userMember', ''), 'score': item.get('score', 0), 'content': item.get('content', ''), 'publish_time': format_timestamp(item.get('publishTime', '')), 'tourist_type': get_tourist_type_display(item.get('touristType', 0)), 'ip_location': item.get('ipLocatedName', ''), 'time_duration': item.get('timeDuration', ''), 'useful_count': item.get('usefulCount', 0), 'reply_count': item.get('replyCount', 0), 'image_count': len(item.get('images', [])), 'recommend_items': item.get('recommendItems', []), 'scores': get_detailed_scores(item.get('scores', [])) } comments.append(comment_info) return comments def format_timestamp(timestamp_str): if not timestamp_str: return '' try: if timestamp_str.startswith('/Date('): timestamp_str = timestamp_str.replace('/Date(', '').replace(')/', '') millis = int(timestamp_str.split('+')[0]) dt = datetime.fromtimestamp(millis / 1000) return dt.strftime('%Y-%m-%d %H:%M:%S') except: pass return timestamp_str def get_tourist_type_display(tourist_type): tourist_type_map = { 0: "个人游", 1: "情侣夫妻", 2: "家庭亲子", 3: "朋友出游", 4: "商务出差", 5: "独自旅行" } return tourist_type_map.get(tourist_type, "其他") def get_detailed_scores(scores_list): scores_detail = {} for score_item in scores_list: name = score_item.get('name', '') score = score_item.get('score', 0) if name: scores_detail[name] = score return scores_detail def analyze_comments_data(comments): if not comments: return {} total_comments = len(comments) avg_score = sum(comment['score'] for comment in comments) / total_comments score_distribution = {} for comment in comments: score = comment['score'] score_range = f"{int(score)}分" score_distribution[score_range] = score_distribution.get(score_range, 0) + 1 tourist_type_dist = {} for comment in comments: tourist_type = comment['tourist_type'] tourist_type_dist[tourist_type] = tourist_type_dist.get(tourist_type, 0) + 1 location_dist = {} for comment in comments: location = comment['ip_location'] or '未知' location_dist[location] = location_dist.get(location, 0) + 1 avg_content_length = sum(len(comment['content']) for comment in comments) / total_comments analysis = { 'total_comments': total_comments, 'average_score': round(avg_score, 2), 'score_distribution': score_distribution, 'tourist_type_distribution': tourist_type_dist, 'location_distribution': location_dist, 'average_content_length': round(avg_content_length, 2), 'total_images': sum(comment['image_count'] for comment in comments), 'total_useful_votes': sum(comment['useful_count'] for comment in comments) } return analysis def save_comments_to_files(comments, analysis, base_filename='harbin_ice_world_comments'): df = pd.DataFrame(comments) csv_filename = f"{base_filename}.csv" df.to_csv(csv_filename, index=False, encoding='utf-8-sig') txt_filename = f"{base_filename}.txt" with open(txt_filename, 'w', encoding='utf-8') as f: f.write("哈尔滨冰雪大世界用户评论分析\n") f.write("=" * 60 + "\n\n") f.write("数据统计:\n") f.write(f"总评论数：{analysis['total_comments']}\n") f.write(f"平均评分：{analysis['average_score']}\n") f.write(f"平均评论长度：{analysis['average_content_length']} 字符\n") f.write(f"总图片数：{analysis['total_images']}\n") f.write(f"总有用投票数：{analysis['total_useful_votes']}\n\n") f.write("评分分布:\n") for score_range, count in analysis['score_distribution'].items(): f.write(f" {score_range}: {count} 条\n") f.write("\n游客类型分布:\n") for tourist_type, count in analysis['tourist_type_distribution'].items(): f.write(f" {tourist_type}: {count} 条\n") f.write("\n地区分布:\n") for location, count in analysis['location_distribution'].items(): f.write(f" {location}: {count} 条\n") f.write("\n" + "=" * 60 + "\n") f.write("详细评论内容:\n\n") for i, comment in enumerate(comments, 1): f.write(f"评论 #{i}\n") f.write(f"用户：{comment['user_nick']} ({comment['user_member']})\n") f.write(f"评分：{comment['score']}分\n") f.write(f"时间：{comment['publish_time']}\n") f.write(f"游客类型：{comment['tourist_type']}\n") f.write(f"地点：{comment['ip_location']}\n") f.write(f"游玩时长：{comment['time_duration']}\n") f.write(f"有用投票：{comment['useful_count']} | 回复：{comment['reply_count']} | 图片：{comment['image_count']}\n") if comment['scores']: f.write("详细评分：") scores_str = ", ".join([f"{k}:{v}分" for k, v in comment['scores'].items()]) f.write(scores_str + "\n") if comment['recommend_items']: f.write(f"推荐项目：{', '.join(comment['recommend_items'])}\n") f.write(f"评论内容:\n{comment['content']}\n") f.write("-" * 80 + "\n\n") return csv_filename, txt_filename def extract_only_comments_content(comments, filename='comments_content_only.txt'): with open(filename, 'w', encoding='utf-8') as f: f.write("哈尔滨冰雪大世界评论内容汇总\n") f.write("=" * 50 + "\n\n") for i, comment in enumerate(comments, 1): f.write(f"【评论 {i}】\n") f.write(f"{comment['content']}\n") f.write("-" * 50 + "\n\n") return filename def process_ctrip_comments(json_data): print("开始处理携程评论数据...") comments = extract_comments_from_json(json_data) print(f"成功提取 {len(comments)} 条评论") if not comments: print("未找到评论数据") return analysis = analyze_comments_data(comments) print(f"\n数据统计:") print(f"总评论数：{analysis['total_comments']}") print(f"平均评分：{analysis['average_score']}") print(f"平均评论长度：{analysis['average_content_length']} 字符") print(f"\n评分分布:") for score_range, count in analysis['score_distribution'].items(): print(f" {score_range}: {count} 条") csv_file, txt_file = save_comments_to_files(comments, analysis) content_only_file = extract_only_comments_content(comments) print(f"\n文件保存完成:") print(f"- 完整数据 CSV: {csv_file}") print(f"- 详细分析报告：{txt_file}") print(f"- 纯评论内容：{content_only_file}") print(f"\n前 3 条评论内容预览:") for i, comment in enumerate(comments[:3], 1): print(f"{i}. {comment['content'][:100]}...") return comments, analysis if __name__ == "__main__": json_data = crawlComment() comments, analysis = process_ctrip_comments(json_data)

Python 爬取携程景区评论数据实战

爬虫

微信扫一扫，关注极客日志

更多推荐文章

相关免费在线工具