xpath学习

import requests
from lxml import etree

if __name__=='__main__':
    url = 'https://www.runoob.com/python3/python3-examples.html'
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36 Edg/94.0.992.38'
    }
    response = requests.get(url=url,headers=headers).text
    tree = etree.HTML(response)
    li_list = tree.xpath('//*[@id="content"]/ul/li')
    new_urls = []

    for li in li_list:

        new_url = li.xpath('./a/@href')
        new = ''
        ur = new.join(new_url)
        if '/python3/' not in ur:
            ur = '/python3/'+ur
        else:
            ur = ur
        new_url = 'https://www.runoob.com'+ ur
        new_urls.append(new_url)

    #     print(new_url)
    for p in new_urls:
        page_text = requests.get(url=p,headers=headers).text
        tr = etree.HTML(page_text)
        title = tr.xpath('//*[@id="content"]/h1/text()')[0]
        question = tr.xpath('//*[@id="content"]/p[2]/text()')[0]
        print(title +'\n'+question+'\n'+'\n')

numpy：(2条消息) Python之Numpy详细教程a373595475的博客-CSDN博客numpy

pandas：(2条消息) Pandas基础教程_Melo-CSDN博客

matplotlib：(2条消息) Python--Matplotlib（基本用法）苦作舟的人呐-CSDN博客matplotlib