爬虫笔记：爬取财经

小白学习爬虫：爬取财经
放码过来

import requests
from bs4 import BeautifulSoup
url='https://finance.sina.com.cn/'
html=requests.get(url)
html.encoding='utf8'
soup=BeautifulSoup(html.text,'lxml')
lis=soup.select('.m-p1-m-blk2 .m-p1-mb2-list.m-list-container ul li a ')
for li in lis:
    title=li.text
    innerUrl=li['href']
    if innerUrl.endswith('shtml') and len(title)>3:
        print(title,innerUrl)
        html = requests.get(innerUrl)
        html.encoding='utf8'
        soup = BeautifulSoup(html.text, 'lxml')
        result = soup.select('.article p')
        res = ''
        for r in result:
            res += r.text
        print('新闻内容', res)
        with open('caijing.txt','a',encoding='utf8')as f:
            f.write(res+'\n')