某牛某客专栏文章爬虫

SingYi

发布于 2023-10-09 00:23:02

15400

代码可运行

文章被收录于专栏：Lan小站Lan小站

运行总次数：0

代码可运行

代码已脱敏，自行替换

# @Time    : 2023/10/8 14:43
# @Author  : Lan
# @File    : niukespider.py
# @Software: PyCharm
import time
import requests


def get_category(catalog='10klpm'):
    url = f'https://www.lanol.cn.com/content/zhuanlan/index/catalog/{catalog}'
    return requests.get(url).json()


c = """



    
    
    
    Document


{{content}}


"""


def get_content(catalog, entity):
    url = f'https://www.lanol.cn.com/content/zhuanlan/index/detail/{catalog}/{entity}?_={int(time.time() * 1000)}'
    return requests.get(url, headers={
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36'
    }).json()


if __name__ == '__main__':
    catalog = 'Gj5x2m'

    for i in get_category(catalog)['data']['catalog']:
        content = get_content(catalog, i['uuid'])['data']
        with open('./docs/' + i['title'].replace('/', '-') + '.html', 'w', encoding='utf-8') as f:
            f.write(c.replace('{{content}}', content['content']))