Xiaohongshu User Profile Scraper

XiaoHongShu User Profile Scraper

Scrape user profile data from XiaoHongShu.

Features

• Get data from user profile page like https://www.xiaohongshu.com/user/profile/5c9cb22d00000000110201ed.

Input parameters

• startUrls: The start urls to crawl.

Example

1{
2 "startUrls": [
3  {
4    "url": "https://www.xiaohongshu.com/user/profile/5c9cb22d00000000110201ed"
5  }
6 ]
7}

Output

Here's an example of scraped data from user profile https://www.xiaohongshu.com/user/profile/5c9cb22d00000000110201ed.

Example

1{
2    "basicInfo": {
3        "images": "https://sns-avatar-qc.xhscdn.com/avatar/6392d3e20b107a9b856db748.jpg?imageView2/2/w/360/format/webp",
4        "redId": "617284149",
5        "gender": 1,
6        "ipLocation": "意大利",
7        "desc": "“首先是自己” 真诚乃第一要义✨\n  模特 pickkstar@163.com",
8        "imageb": "https://sns-avatar-qc.xhscdn.com/avatar/6392d3e20b107a9b856db748.jpg?imageView2/2/w/540/format/webp",
9        "nickname": "耳朵仔子"
10    },
11    "interactions": [
12        {
13            "type": "follows",
14            "name": "关注",
15            "count": "10+"
16        },
17        {
18            "type": "fans",
19            "name": "粉丝",
20            "count": "50w+"
21        },
22        {
23            "type": "interaction",
24            "name": "获赞与收藏",
25            "count": "200w+"
26        }
27    ],
28    "tags": [
29        {
30            "icon": "http://ci.xiaohongshu.com/icons/user/gender-female-v1.png",
31            "tagType": "info"
32        },
33        {
34            "name": "时尚博主",
35            "tagType": "profession"
36        }
37    ],
38    "notes": [
39        {
40            "id": "655b22c00000000033005ac6",
41            "noteCard": {
42                "interactInfo": {
43                    "liked": false,
44                    "likedCount": "100+",
45                    "sticky": false
46                },
47                "cover": {
48                    "width": 1280,
49                    "url": "",
50                    "traceId": "",
51                    "infoList": [
52                        {
53                            "imageScene": "FD_PRV_JPG",
54                            "url": "http://sns-webpic-qc.xhscdn.com/202311211639/34454fff096ae407d93064707f753661/1040g2sg30rmm7af42i005n4sm8mkc0fdnvje2q0!nc_n_nwebp_prv_1"
55                        },
56                        {
57                            "imageScene": "FD_WM_JPG",
58                            "url": "http://sns-webpic-qc.xhscdn.com/202311211639/f096a28330858c88b9d33321b2371b2c/1040g2sg30rmm7af42i005n4sm8mkc0fdnvje2q0!nc_n_nwebp_mw_1"
59                        }
60                    ],
61                    "fileId": "",
62                    "height": 1707
63                },
64                "noteId": "655b22c00000000033005ac6",
65                "type": "normal",
66                "displayTitle": "“一些光影记录” ",
67                "user": {
68                    "nickname": "耳朵仔子",
69                    "nickName": "耳朵仔子",
70                    "avatar": "https://sns-avatar-qc.xhscdn.com/avatar/6392d3e20b107a9b856db748.jpg",
71                    "userId": "5c9cb22d00000000110201ed"
72                }
73            },
74            "index": 0,
75            "exposed": false
76        },
77        {
78            "id": "65587f23000000000f0242f4",
79            "noteCard": {
80                "type": "normal",
81                "displayTitle": "又长大了一岁诶🎂 ",
82                "user": {
83                    "nickName": "耳朵仔子",
84                    "avatar": "https://sns-avatar-qc.xhscdn.com/avatar/6392d3e20b107a9b856db748.jpg",
85                    "userId": "5c9cb22d00000000110201ed",
86                    "nickname": "耳朵仔子"
87                },
88                "interactInfo": {
89                    "liked": false,
90                    "likedCount": "1k+",
91                    "sticky": false
92                },
93                "cover": {
94                    "fileId": "",
95                    "height": 1920,
96                    "width": 1416,
97                    "url": "",
98                    "traceId": "",
99                    "infoList": [
100                        {
101                            "url": "http://sns-webpic-qc.xhscdn.com/202311211639/ba0bb56b51e31497439d179a31c59811/1040g00830rk3o5lb2i005n4sm8mkc0fd1ghf9p8!nc_n_nwebp_prv_1",
102                            "imageScene": "FD_PRV_JPG"
103                        },
104                        {
105                            "imageScene": "FD_WM_JPG",
106                            "url": "http://sns-webpic-qc.xhscdn.com/202311211639/0a9d3287845b2b6b7271b8a3229bab61/1040g00830rk3o5lb2i005n4sm8mkc0fd1ghf9p8!nc_n_nwebp_mw_1"
107                        }
108                    ]
109                },
110                "noteId": "65587f23000000000f0242f4"
111            },
112            "index": 1,
113            "exposed": false
114        },
115    ]
116}