python爬虫——新浪新闻网络爬虫
python爬虫——新浪新闻网络爬虫import requestsfrom bs4 import BeautifulSoupnewsurl = "http://news.sina.com.cn/china/"res = requests.get(newsurl)res.encoding = 'utf-8'#print(res.text)soup = BeautifulSoup(res.te
·
python爬虫——新浪新闻网络爬虫
import requests
from bs4 import BeautifulSoup
newsurl = "http://news.sina.com.cn/china/"
res = requests.get(newsurl)
res.encoding = 'utf-8'
#print(res.text)
soup = BeautifulSoup(res.text, 'html.parser')
for news in soup.select('.news-item'):
#print(news)
if len(news.select('h2')) > 0:
h2 = news.select('h2')[0].text
time = news.select('.time')[0].text
a = news.select('a')[0]['href']
print(time, h2, a)爬取效果：
加入社区！打开量化的大门，首批课程上线啦！
更多推荐
0
0- 0
已为社区贡献1条内容
所有评论(0)