爬取校园新闻首页的新闻

Posted 2020-10-29 阿yuan

1. 用requests库和BeautifulSoup库，爬取校园新闻首页新闻的标题、链接、正文。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
newsurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(newsurl)
res.encoding = \'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
a=soup.select(\'li\')
for news in a:
    if len(news.select(\'.news-list-title\'))>0:
        # 获取标题
        b=news.select(\'.news-list-title\')[0].contents[0]
        # 获取链接接
        c = news.select(\'a\')[0].attrs[\'href\']
        # 获取正文
        res1 = requests.get(c)
        res1.encoding = \'utf-8\'
        soup1 = BeautifulSoup(res1.text, \'html.parser\')
        d=soup1.select(\'#content\')[0].text

2. 分析字符串，获取每篇新闻的发布时间，作者，来源，摄影等信息。

#发布时间
        info = soup1.select(".show-info")[0].text;
        e = info.lstrip(\'发布时间:\')[:19]
        #作者
        f=info[info.find(\'作者：\'):info.find(\'审核：\')].lstrip(\'作者：\').split()[0]
        #来源
        g = info[info.find(\'来源：\'):info.find(\'点击：\')].lstrip(\'来源：\').split()[0]
        #摄影
        h = info[info.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')

3. 将其中的发布时间由str转换成datetime类型。

# 获取当前的时间
        now_time = datetime.now();
        now_time.year
        # 将字符串转化为时间
        print(datetime.strptime(e, "%Y-%m-%d %H:%M:%S"))
        # 将时间转化为字符串
        print(now_time.strftime(\'%Y\\%m\\%d\'))

4. 将完整的代码及运行结果截图发布在作业上。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
newsurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(newsurl)
res.encoding = \'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
a=soup.select(\'li\')
for news in a:
    if len(news.select(\'.news-list-title\'))>0:
        # 获取标题
        b=news.select(\'.news-list-title\')[0].contents[0]
        # 获取链接接
        c = news.select(\'a\')[0].attrs[\'href\']
        # 获取正文
        res1 = requests.get(c)
        res1.encoding = \'utf-8\'
        soup1 = BeautifulSoup(res1.text, \'html.parser\')
        d=soup1.select(\'#content\')[0].text
        # print(b+" "+c+" "+d)
        #发布时间
        info = soup1.select(".show-info")[0].text;
        e = info.lstrip(\'发布时间:\')[:19]
        #作者
        f=info[info.find(\'作者：\'):info.find(\'审核：\')].lstrip(\'作者：\').split()[0]
        #来源
        g = info[info.find(\'来源：\'):info.find(\'点击：\')].lstrip(\'来源：\').split()[0]
        #摄影
        h = info[info.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')
        # 获取当前的时间
        now_time = datetime.now();
        now_time.year
        # 将字符串转化为时间
        # print(datetime.strptime(e, "%Y-%m-%d %H:%M:%S"))
        # 将时间转化为字符串
        print(b+" "+c+" "+e+" "+f+" "+g+" "+" "+h+" "+now_time.strftime(\'%Y\\%m\\%d\'));