数据化结构与保存

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

#获取点击次数
def getClickCount(newsUrl):
    newsId = re.findall('\_(.*).html', newsUrl)[0].split('/')[1]
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
    clickStr = requests.get(clickUrl).text
    count = int(re.search("hits'\).html\('(.*)'\);",clickStr).group(1))
    return count

# def writeNewsContent(content):
#     f = open('getNewsDetail.txt','a',encoding='utf-8')
#     f.write(content)
#     f.close()


# 获取新闻详情
def getNewDetail(url):
    resd = requests.get(url)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')

    news = {}
    news['title'] = soupd.select('.show-title')[0].text
    info = soupd.select('.show-info')[0].text

    news['dt'] = datetime.strptime(info.lstrip('发布时间:')[0:19], '%Y-%m-%d %H:%M:%S')

    if info.find('来源:') > 0:
        news['source'] = info[info.find('来源:'):].split()[0].lstrip('来源:')
    else:
        news['source'] = 'none'
    # if info.find('作者:') > 0:
    #     author = info[info.find('作者:'):].split()[0].lstrip('作者:')
    # else:
    #     author = 'none'
    news['clickCount'] = getClickCount(url)
    return news

def getListPage(listPageUrl):
    res = requests.get(listPageUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    newsList = []
    for news in soup.select('li'):
        if len(news.select('.news-list-title')) > 0:
            # 获取新闻模块链接
            a = news.a.attrs['href']
            # 调用函数获取新闻正文
            newsList.append(getNewDetail(a))
    return newsList




# 首页列表新闻
newsTotal = []
firstPageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
newsTotal.extend(getListPage(firstPageUrl))


#计算总页数
def getPageNum():
    resn = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
    resn.encoding = 'utf-8'
    soupn = BeautifulSoup(resn.text, 'html.parser')
    n = int(soupn.select('.a1')[0].text.rstrip('条'))
    return (n // 10 + 1)

n = getPageNum()
for i in range(n,n+1):
    pageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    newsTotal.extend(getListPage(pageUrl))
    # print(newsTotal)

df = pandas.DataFrame(newsTotal)
df.to_excel('gzccnews.xlsx')

#提取包含点击次数、标题、来源的前6行数据
print(df.head(6))
#提取‘学校综合办’发布的,‘点击次数’超过3000的新闻。
print(df[(df['clickCount']>3000)&(df['source']=='学校综合办')])
#提取'国际学院'和'学生工作处'发布的全部新闻。
sour = ['国际学院','学生工作处']
print(df[df['source'].isin(sour)])

  

posted on 2018-04-12 20:29  阿丹丹酱  阅读(131)  评论(0编辑  收藏  举报

导航