Python爬取实战-爬取菜鸟教程python100例

import requests
from lxml import etree

#获得详情页
def getDetailPage(page):
    url = 'https://www.runoob.com/python/python-exercise-example{}.html'.format(page)
    response = requests.get(url)
    html = etree.HTML(response.text)
    hs = html.xpath('//div[@class="article-intro"]')
    for h in hs:
        title = h.xpath('./h1/text()')[0]
        name = h.xpath('./p[2]/text()')[0]
        code = h.xpath('.//div[@class="hl-main"]//span/text()')
        code = ''.join(code)
        result = h.xpath('./pre/text()')
        result = ''.join(result)
        data = ''.join([title + '\n', '题目：'+ name + '\n', '代码：' + code + '\n', '输出：' + result])
        print(data)
        savedate(data)

#保存数据
def savedate(data):
    with open('菜鸟python编程100例.txt', 'a', encoding='utf-8') as f:
        f.write(data)

def main():
    for page in range(1,3):
        getDetailPage(page)

if __name__ == '__main__':
    main()

有问题请联系博主：
微信：hrvrap
qq:2580419087