Building a Weibo Influencer Finder with LangChain and LLM

The author introduces LangChain as a mature AI application framework and outlines a plan to build a social‑network tool for locating suitable Weibo influencers (大V) to promote a dry‑goods store.

Project requirements : The marketing team wants to identify influential users on Weibo who are interested in food‑supplement topics, then contact them for collaborations.

Technical analysis : Use LangChain's search chain to find relevant UID numbers, write a crawler to fetch public profile data in JSON, and employ LLM prompts to generate invitation messages.

Environment setup and UID lookup code :

# 环境变量设置
import os
os.environ['OPENAI_API_KEY'] = ''
os.environ['SERPAPI_API_KEY'] = ''
# 正则模块
import re 
# 核心开发一个weibo_agent find_v方法
from agents.weibo_agent import find_V

if __name == "__main__":
    response_UID = find_v(food_type="助眠")
    print(response_UID)
    # 从返回结果中正则所有的UID数字
    UID = re.findall(r'\d+', response_UID)[0]
    print("这位大V的微博ID是", UID)

Custom agent implementation (find_V) :

# tools_search_tool后面会编写
from tools_search_tool import get_UID
# 模板
from langchain.prompts import PromptTemplate
from langchain.chat_models import ChatOpenAI
# 准备定制Agent
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType

def find_V(food_type: str):
    llm = ChatOpenAI(temperature=0,model_name="gpt-3.5-turbo")
    template = """given the {food} I want you to get a related 微博 UID.
    Your answer should contain only a UID.
    The URL always starts with https://weibo.com/u/<
    for example, if https://weibo.com/u/3659536733 is her 微博, then 3659536733 is him UID This is only the example don't give me this, but the actual UID
    """
    prompt_template = PromptTemplate(
        input_variables=["food"],
        template=template
    )
    tools = [
        Tool(
            name="Crawl Google for 微博 page",
            func=get_UID,
            description="useful for when you need get the 微博UID"
        )
    ]
    agent = initialize_agent(
        tools,
        llm,
        agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
        verbose=True
    )
    ID = agent.run(prompt_template.format_prompt(food=food_type))
    return ID

The agent uses langchain.agents.initialize_agent and Tool to call a SerpAPI‑based search for the Weibo page.

SerpAPI UID retrieval :

# langchain 集成了 SerpAIWrapper
from langchain.utilities import SerpAIWrapper
def get_UID(food: str):
    """Searches for Weibo Page."""
    search = SerpAPIWrapper()
    res = search.run(f"{food}")
    return res

Running the above returns a UID such as 3659536733 .

Web scraping for profile data :

import tools.scraping_tool import get_data

person_info=get_data(UID)
print(person_info)

The scraping_tool module contains:

import json     # json解析
import requests #发送请求
import time #时间

def scrape_weibo(url: str):
    '''爬取相关博主的资料'''
    headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36", "Referer": "https://weibo.com" }
    cookies = { "cookie": "..." }
    response = requests.get(url, headers=headers,cookies=cookies)
    time.sleep(2) # 加上2秒的延时 防止被反爬
    return response.text

def get_data(id):
    url = "https://weibo.com/ajax/profile/detail?uid={}".format(id)
    html = scrape_weibo(url)
    response = json.loads(html)
    return response

After fetching the JSON profile, non‑Chinese fields are removed to keep only Chinese content:

import re

def contains_chinese(s):
    return bool(re.search('[\u4e00-\u9fa5]', s))

def remove_non_chinese_fields(d):
    if isinstance(d, dict):
        to_remove = [key for key, value in d.items() if isinstance(value, (str, int, float, bool)) and (not contains_chinese(str(value)))]
        for key in to_remove:
            del d[key]
        for key, value in d.items():
            if isinstance(value, (dict, list)):
                remove_non_chinese_fields(value)
    elif isinstance(d, list):
        to_remove_indices = []
        for i, item in enumerate(d):
            if isinstance(item, (str, int, float, bool)) and (not contains_chinese(str(item))):
                to_remove_indices.append(i)
            else:
                remove_non_chinese_fields(item)
        for index in reversed(to_remove_indices):
            d.pop(index)

Summary : The article completes the workflow of locating a suitable Weibo influencer UID, scraping their profile, and preparing the data for downstream LLM‑generated invitation content.

Key LangChain components used: PromptTemplate, LLM, Chain, Agent, and custom Agent Tool.

Reference : Huang Jia’s LangChain course.