automatic_crawler/spider/crawler_search/baidu_search.py

"""
好看视频搜索爬虫
"""
import json

import requests
import urllib.parse
import time
import hashlib


def hksp_search(key):
    """
    好看视频搜索爬虫
    """
    timestamp_seconds = time.time()
    timestamp_milliseconds = int(timestamp_seconds * 1000)
    url = 'https://haokan.baidu.com/haokan/ui-search/pc/search/video'
    # 定义请求的参数
    strings = "{}_{}_{}_{}_{}".format(1, urllib.parse.quote(key), 10, timestamp_milliseconds, 1)
    sign = hashlib.md5(strings.encode()).hexdigest()
    params = {
        'pn': 1,
        'rn': 10,
        'type': 'video',
        'query': key,
        'sign': sign,
        'version': 1,
        'timestamp': timestamp_milliseconds
    }
    # 定义请求头
    headers = {
        'authority': 'haokan.baidu.com',
        'accept': '*/*',
        'accept-language': 'zh,en;q=0.9,zh-CN;q=0.8',
        'cookie': "BIDUPSID='",
        # 'referer': 'https://haokan.baidu.com/web/search/page?query=%E8%80%81%E4%BA%BA',
        'sec-ch-ua': '"Not A(Brand";v="99", "Google Chrome";v="121", "Chromium";v="121"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"macOS"',
        'sec-fetch-dest': 'empty',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36',
        'x-requested-with': 'xmlhttprequest',
    }
    # 发送GET请求
    response = requests.get(url, headers=headers, params=params).json()
    print(json.dumps(response, ensure_ascii=False, indent=4))


if __name__ == '__main__':
    hksp_search("人类首次从恐龙蛋化石中获得恐龙的遗传物质")