爬取所有校园新闻

Posted 2020-10-10 410陈锐锦

获取单条新闻的#标题#链接#时间#来源#内容 #点击次数，并包装成一个函数。

点击次数：

import requests
from bs4 import BeautifulSoup
from datetime import datetime


res = requests.get(\'http://news.gzcc.cn/html//xiaoyuanxinwen/\')
res.encoding = \'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')


for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        t = news.select(\'.news-list-title\')[0].text
        a = news.select(\'a\')[0][\'href\']
        d = news.select(\'.news-list-info\')[0].contents[0].text
        dt = datetime.strptime(d,\'%Y-%m-%d\')
        s = news.select(\'.news-list-info\')[0].contents[1].text
        #print(t,a,d,s)

        resl = requests.get(a)
        resl.encoding = \'utf-8\'
        soupl = BeautifulSoup(resl.text,\'html.parser\')
        ar = soupl.select(\'.show-content\')[0]
        click = requests.get(\'http://oa.gzcc.cn/api.php?op=count&id=8302&modelid=80\').text.split(\'.\')[-1].lstrip("html(\'").rstrip("\');")
        print(click)
        break

结果：

 

 

后面函数：

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re



def getclick(newsurl):
    id = re.match(\'http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html\',newsurl).groups()[0].split(\'/\')[1]
    clickurl = \'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(id)
    click = int(requests.get(clickurl).text.split(\'.\')[-1].lstrip("html(\'").rstrip("\');"))
    return(click)

def getonepage(listurl):
    res = requests.get(listurl)
    res.encoding = \'utf-8\'
    soup = BeautifulSoup(res.text,\'html.parser\')
    
    for news in soup.select(\'li\'):
        if len(news.select(\'.news-list-title\'))>0:
            t = news.select(\'.news-list-title\')[0].text
            a = news.select(\'a\')[0][\'href\']
            d = news.select(\'.news-list-info\')[0].contents[0].text
            dt = datetime.strptime(d,\'%Y-%m-%d\')
            s = news.select(\'.news-list-info\')[0].contents[1].text
            #print(t,a,d,s)

            resl = requests.get(a)
            resl.encoding = \'utf-8\'
            soupl = BeautifulSoup(resl.text,\'html.parser\')
            ar = soupl.select(\'.show-content\')[0].text
            click = getclick(a)
            print(click,t,dt,s,a,ar)
getonepage(\'http://news.gzcc.cn/html/xiaoyuanxinwen/index.html\')

res=requests.get(\'http://news.gzcc.cn/html/xiaoyuanxinwen\')
res.encoding = \'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
page = int(soup.select(\'.a1\')[0].text.rstrip(\'条\'))//10+1
for i in range(2,4):
    listurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html\'.format(i)
    getonepage(listurl)

 

 

 

 

 完成自己所选其他主题相应数据的爬取工作。