爬取校园新闻首页的新闻的详情，使用正则表达式，函数抽离

Posted 2020-10-30 193杨晓玲

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

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

def getNewDetail(newsUrl):
  for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        t=news.select(\'.news-list-title\')[0].text  #标题
        a=news.select(\'a\')[0].attrs[\'href\'] #链接
        res = requests.get(a)
        res.encoding = \'utf-8\'
        soupd = BeautifulSoup(res.text, \'html.parser\')
        content = soupd.select(\'#content\')[0].text
        description = news.select(\'.news-list-description\')[0].text
        resd=requests.get(a)
        resd.encoding=\'utf-8\'
        soupd=BeautifulSoup(resd.text,\'html.parser\')
        info=soupd.select(\'.show-info\')[0].text
        d=info.lstrip(\'发布时间:\')[:19]
        dt=datetime.strptime(d,\'%Y-%m-%d %H:%M:%S\')
        author=info[info.find(\'作者：\'):].split()[0].lstrip(\'作者：\')
        source=info[info.find(\'来源：\'):].split()[0].lstrip(\'来源：\')
        photo=info[info.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')
        print("新闻标题:",t)
        print("链接:",a)
        print("发布时间:",dt)
        print("作者:",author)
        print("来源:",source)
        print("摄影:",photo)
        print("描述:",description)
        getClickCount(a)
        print("正文:", content)
        break

    def getClickCount(newsUrl):
     clickUrl = \'http://oa.gzcc.cn/api.php?op=count&id=9183&modelid=80\'
     count = requests.get(clickUrl).text.split(\'.html\')[-1].lstrip("(\'").rstrip("\');")
     print("点击次数:", count)
     re.match(\'http://news.gzcc.cn/html/2018/xiaoyuanxinwen(.*).html\', newsUrl).group(1).split(\'/\')[1]
     print(\'新闻编号:\', re.search(\'\\_(.*).html\', newsUrl).group(1))

getNewDetail(newsurl)