pyppeteer爬虫例子

如果在centos上使用，需要安装下面的依赖

yum install pango.x86_64 libXcomposite.x86_64 libXcursor.x86_64 libXdamage.x86_64 libXext.x86_64 libXi.x86_64 libXtst.x86_64 cups-libs.x86_64 libXScrnSaver.x86_64 libXrandr.x86_64 GConf2.x86_64 alsa-lib.x86_64 atk.x86_64 gtk3.x86_64 -y

执行代码

import asyncio
import pyppeteer
from collections import namedtuple

Response = namedtuple("rs", "title url html cookies headers history status")


async def get_html(url, timeout=30):
    # 默认30s
    browser = await pyppeteer.launch(headless=True, args=['--no-sandbox'])
    page = await  browser.newPage()
    res = await page.goto(url, options={'timeout': int(timeout * 1000)})
    data = await page.content()
    title = await page.title()
    resp_cookies = await page.cookies()
    resp_headers = res.headers
    resp_history = None
    resp_status = res.status
    response = Response(title=title, url=url,
                        html=data,
                        cookies=resp_cookies,
                        headers=resp_headers,
                        history=resp_history,
                        status=resp_status)
    return response


if __name__ == '__main__':
    url_list = ["http://www.10086.cn/index/tj/index_220_220.html", "http://www.10010.com/net5/011/",
                "http://python.jobbole.com/87541/"]
    task = (get_html(url) for url in url_list)

    loop = asyncio.get_event_loop()
    results = loop.run_until_complete(asyncio.gather(*task))
    for res in results:
        print(res.title)