爬取校园新闻

def getNewsId(url):
    newsId = re.findall(r'\_(.*).html', newsUrl)[0][-4:]
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正则表达式获取新闻点击次数
    clickCount = int(re.search("hits'\).html\('(.*)'\);", clickRes.text).group(1))
    return clickCount


# 获取新闻细节
def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')

    content = soupd.select('#content')[0].text
    info = soupd.select('.show-info')[0].text
    # 调用getNewsId()获取点击次数
    count = getNewsId(newsUrl)
    print(info)
    # 识别时间格式
    date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1)
    # 识别一个至三个数据
    author = re.search('作者:((.{3}\s){1,3})', info).group(1)
    check = re.search('审核:((.{3}\s){1,3})', info).group(1)
    sources = re.search('来源:((.{3}\s){1,3})', info).group(1)
    # 用datetime将时间字符串转换为datetime类型
    dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
    # 利用format对字符串进行操作
    print('发布时间:{0}\n作者:{1}\n审核:{2}\n来源:{3}\n点击次数:{4}'.format(dateTime, author, check, sources, count))
    print(content)

  

str = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/') str.encoding = 'utf-8' from bs4 import BeautifulSoup soup=BeautifulSoup(str.text,'html.parser') #print(soup) d=soup.select('li') for news in d: if len(news.select('.news-list-title')) > 0: t=print(news.select('.news-list-title')[0].text) a=news.select('a')[0].attrs print(a['href']) strd = requests.get(a['href']) strd.encoding = 'utf-8' soupd = BeautifulSoup(strd.text, 'html.parser') cont=soupd.select('#content') timet=soupd.select('.show-info') print(timet[0].text[0:25]) print(timet[0].text[30:38]) print(timet[0].text[38:45]) print(timet[0].text[46:56]) print(timet[0].text[62:])

  

posted on 2018-04-03 14:36  阿丹丹酱  阅读(128)  评论(0编辑  收藏  举报

导航