爬虫练习-知乎热搜榜

代码

import requests
import json


def get_zhihu_hot_list():
    url = "https://api.zhihu.com/topstory/hot-list"  # 移动端获取热搜榜单数据api地址
    # 模拟请求头
    headers = {
        "User-Agent": "ZhihuHybrid com.zhihu.android/Futureve/6.59.0 Mozilla/5.0 (Linux; Android 10; SM-G9650 Build/QP1A.190711.020; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/83.0.4103.106 Mobile Safari/537.36",
    }
    try:
        # 获取api数据
        response = requests.get(url, headers=headers)
        # 检测https请求状态
        response.raise_for_status()
        # 最终接口数据
        data = response.json()

        if "data" in data:
            print(f"{'排名':<5}{'热度':<15}{'标题'}")
            print("-" * 80)
            # enumerate(list)：同时获取索引和值
            for index, item in enumerate(data["data"], 1):
                # 获取字典中的数据
                target = item.get("target", {})
                title = target.get("title", "No Title")

                # 容错
                hot_value = item.get("detail_text", "")
                if not hot_value:  # 找不到数据时
                    hot_value = "N/A"
                print(f"{index:<5}{hot_value:<15}{title}")
        else:
            print("Failed to retrieve data format expected.")

    except requests.exceptions.RequestException as e:
        print(f"Error fetching data: {e}")
    except json.JSONDecodeError:
        print("Error decoding JSON response")


if __name__ == "__main__":
    print("---------欢迎启动python爬虫程序✈️，将爬取的网站信息为：知乎热搜榜---------")
    get_zhihu_hot_list()

爬取效果

实际效果