# my_first_scraper.py
# This is your first Xiaohongshu scraper script!

import asyncio
from xhs_scraper import XHSClient

async def main():
    # ⬇️ Replace these with your own Cookie values (see Cookie Setup above)
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies, rate_limit=2.0) as client:
        # Get your own user info to verify Cookie is working
        user = await client.users.get_self_info()
        print("🎉 Login successful!")
        print(f"Your nickname: {user.nickname}")

if __name__ == "__main__":
    asyncio.run(main())

from xhs_scraper.utils import extract_chrome_cookies

cookies = extract_chrome_cookies()
# The returned cookies can be passed directly to XHSClient

from xhs_scraper import qr_login

async def login():
    cookies = await qr_login()
    print(f"Obtained Cookies: {cookies}")

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        user = await client.users.get_self_info()
        print(f"✅ Login successful! Nickname: {user.nickname}")
        print(f"Followers: {user.followers}, Following: {user.following}")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # note_id and xsec_token can be obtained from note links or search results
        note = await client.notes.get_note(
            note_id="note_id_here",
            xsec_token="xsec_token_here"
        )
        print(f"Title: {note.title}")
        print(f"Content: {note.desc}")
        print(f"Likes: {note.liked_count}, Comments: {note.commented_count}")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # Scrape first 3 pages of notes
        result = await client.notes.get_user_notes(
            user_id="user_id_here",
            max_pages=3
        )
        print(f"Retrieved {len(result.items)} notes")
        for note in result.items:
            print(f"- {note.title}")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        user = await client.users.get_user_info(user_id="user_id_here")
        print(f"Nickname: {user.nickname}")
        print(f"Bio: {user.bio}")
        print(f"Followers: {user.followers}, Following: {user.following}")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # Get top-level comments
        comments = await client.comments.get_comments(
            note_id="note_id_here",
            max_pages=2
        )
        print(f"Retrieved {len(comments.items)} comments")
        
        for comment in comments.items:
            print(f"{comment.user.nickname}: {comment.content}")
            
            # Get sub-comments (replies)
            if comment.comment_id:
                sub_comments = await client.comments.get_sub_comments(
                    note_id="note_id_here",
                    root_comment_id=comment.comment_id
                )
                for sub in sub_comments.items:
                    print(f"  └─ {sub.user.nickname}: {sub.content}")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # Search notes
        # sort: "GENERAL" (default), "TIME_DESC" (latest), "POPULARITY" (popular)
        # note_type: "ALL" (default), "VIDEO", "IMAGE"
        result = await client.search.search_notes(
            keyword="camping gear",
            sort="POPULARITY",
            note_type="ALL",
            page=1,
            page_size=20
        )
        
        print(f"Found {len(result.items)} notes")
        for note in result.items:
            print(f"- {note.title} (Likes: {note.liked_count})")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient
from xhs_scraper.utils import export_to_json, export_to_csv

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # Search notes
        result = await client.search.search_notes("food recommendations")
        
        # Export to JSON
        export_to_json(result.items, "output/notes.json")
        print("✅ Exported to output/notes.json")
        
        # Export to CSV (can be opened directly in Excel)
        export_to_csv(result.items, "output/notes.csv")
        print("✅ Exported to output/notes.csv")

if __name__ == "__main__":
    asyncio.run(main())

import asyncio
from xhs_scraper import XHSClient
from xhs_scraper.utils import download_media

async def main():
    cookies = {
        "a1": "paste_your_a1_value_here",
        "web_session": "paste_your_web_session_value_here"
    }
    
    async with XHSClient(cookies=cookies) as client:
        # Get note details
        note = await client.notes.get_note(
            note_id="note_id_here",
            xsec_token="xsec_token_here"
        )
        
        # Download images
        if note.images:
            paths = await download_media(
                urls=note.images,
                output_dir="downloads/",
                filename_pattern="{note_id}_{index}.{ext}",
                note_id=note.note_id
            )
            print(f"✅ Downloaded {len(paths)} files to downloads/ directory")

if __name__ == "__main__":
    asyncio.run(main())

# ========== 配置区域 / Configuration ==========
COOKIES = {
    "a1": "Paste your a1 here",
    "web_session": "Paste your web_session here",
}
# ... other config options
# ========== 配置结束 / End Configuration ==========

from xhs_scraper.utils import export_to_json

# data can be a model list or PaginatedResponse object
export_to_json(notes, "output/notes.json")

from xhs_scraper.utils import export_to_csv

export_to_csv(notes, "output/notes.csv")

from xhs_scraper.media import download_media

# Automatically detect and download images or videos
await download_media(note, folder="downloads/")

import asyncio
from xhs_scraper import XHSClient
from xhs_scraper.utils import export_to_json

async def run():
    # Replace with your own cookies
    cookies = {"a1": "...", "web_session": "..."}
    async with XHSClient(cookies=cookies) as client:
        # Scrape first 3 pages of notes
        result = await client.notes.get_user_notes("user_id", max_pages=3)
        export_to_json(result.items, "user_notes.json")

if __name__ == "__main__":
    asyncio.run(run())

import asyncio
from xhs_scraper import XHSClient
from xhs_scraper.utils import export_to_csv

async def run():
    # Replace with your own cookies
    cookies = {"a1": "...", "web_session": "..."}
    async with XHSClient(cookies=cookies) as client:
        # Search "camping gear", sort by popularity
        search_res = await client.search.search_notes("camping gear", sort="POPULARITY")
        export_to_csv(search_res.items, "search_result.csv")

if __name__ == "__main__":
    asyncio.run(run())

import asyncio
from xhs_scraper import XHSClient

async def run():
    # Replace with your own cookies
    cookies = {"a1": "...", "web_session": "..."}
    async with XHSClient(cookies=cookies) as client:
        note_id = "65xxxxxxxxxxxxxxxx"
        comments = await client.comments.get_comments(note_id, max_pages=2)
        for comment in comments.items:
            print(f"{comment.user.nickname}: {comment.content}")

if __name__ == "__main__":
    asyncio.run(run())