chaziyu.com网站域名爬取

爬取后可配合httpx进行探测
把爬取到的域名保存在3.txt文件中
常用命令：httpx -l 3.txt -status-code -tech-detect -web-server -title -cdn -mc 200

import asyncio
from pyppeteer import launch
import re

async def ziyu(uri):
    browser = await launch()
    page = await browser.newPage()
    await page.setUserAgent('Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/60.0')
    url = 'https://chaziyu.com/' + uri
    await page.goto(url)


    await page.evaluate('window.scrollBy(0, document.body.scrollHeight)')
    await asyncio.sleep(1)

    content = await page.content()
    ziyunming = re.findall('<a href="(.+?)"', content)

    for ziyu1 in ziyunming:
        if 'https://ipchaxun.com/' in ziyu1:
            new_ziyu1 = ziyu1.replace("https://ipchaxun.com/", "").rstrip("/")
            print('http://' + new_ziyu1)
    for ziyu2 in ziyunming:
        if 'https://chaolianjie.com/' in ziyu2:
            new_ziyu2 = ziyu2.replace("https://chaolianjie.com/#", "").rstrip("/")
            print('http://' + new_ziyu2)

    await browser.close()

if __name__ == '__main__':
    uri = input('+ \033[35m请输入要查询的子域名$:\033[0m')
    asyncio.run(ziyu(uri))