python xpath text与attrib

废话不多说，直接开干！

说明

0.text获取标签包裹数据
或者解释用于html元素文本内容的存取
eg:element.text
1.attrib获取标签内的元素
eg:element.attrib['title'],element.attrib['href']

直接看代码

import asyncio
from pyppeteer import launch
from lxml import etree


async def main():
    browser = await launch()
    page = await browser.newPage()
    await page.goto('https://movie.douban.com/chart')
    await page.waitForXPath('//table//a[@title]')
    doc = etree.HTML(await page.content())
    # t = etree.tostring(doc, encoding="utf-8", pretty_print=True)
    # print(t.decode("utf-8"))
    for element in doc.xpath('//table//p[@class]'):
        print(element.attrib['text'])

    names = [element.attrib['title'] for element in doc.xpath('//table//a[@title]')]

    print('Names: ', names)
    await browser.close()


asyncio.get_event_loop().run_until_complete(main())