数据结构化与保存

def writeNewsDetail(content):
    f=open(‘gzcc.txt‘,‘a‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()

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


def writeNewsDetail(content):
    f = open(‘gzccNews.txt‘, ‘a‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()


def getClickCount(newsUrl):  #一篇新闻的点击次数
    newId = re.search(‘\_(.*).html‘, newsUrl).group(1).split(‘/‘)[1]
    clickUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId)
    return (int(requests.get(clickUrl).text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);")))


def getNewsDetail(newsUrl):  #一篇新闻的全部信息
    resd = requests.get(newsUrl)
    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‘
    news[‘content‘] = soupd.select(‘.show-content‘)[0].text.strip()
    #writeNewsDetail(news[‘content‘])
    news[‘click‘] = getClickCount(newsUrl)
    news[‘newsUrl‘] = newsUrl
    return(news)


def getListPage(pageUrl):  #一个列表页的全部新闻
    res = requests.get(pageUrl)
    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:
            newsUrl = news.select(‘a‘)[0].attrs[‘href‘]  
            newsList.append(getNewsDetail(newsUrl))
    return(newsList)


def getPageN():  # 新闻列表页的总页数
    res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    n = int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
    return (n // 10 + 1)

newsTotal = []
firstPageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
newsTotal.extend(getListPage(firstPageUrl))

n = getPageN()
for i in range(n, n+1):
    listPageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    newsTotal.extend(getListPage(listPageUrl))

print(newsTotal)

 df = pandas.DataFrame(newsTotal)

df.to_excel("news.xlsx")

df.head(6)
df[[‘click‘,‘title‘,‘source‘]]
df[(df[‘click‘]>3000) | (df[‘source‘]==‘学校综合办‘)]
list=[‘学生工作处‘,‘国际学院‘]

 print(df[df[‘sources‘].isin(list)])