用requests库和BeautifulSoup4库爬取新闻列表

Posted 2020-10-08 杨小宏

import requests
from bs4 import BeautifulSoup

url=\'http://news.gzcc.cn/html/xiaoyuanxinwen/\'

res=requests.get(url)
res.encoding=\'utf-8\'
   
soup=BeautifulSoup(res.text,\'html.parser\')

for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title=news.select(\'.news-list-title\')[0].text
        time=news.select(\'.news-list-info\')[0].contents[0].text
        url=news.select(\'a\')[0][\'href\']
        thumb=news.select(\'.news-list-thumb\')[0].contents[0]
        print(time)
        print(title)
        print(url)
        print(thumb)

import requests
from bs4 import BeautifulSoup
jq=\'http://www.gamersky.com/pcgame/\'
res = requests.get(jq)
res.encoding=\'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
 
for news in soup.select(\'li\'):
    if len(news.select(\'a\'))>0:
        title=news.select(\'a\')[0].text
        url=news.select(\'a\')[0][\'href\']
        #time=news.select(\'span\')[0].contents[0].text
        #print(time,title,url)
        print(title,url)