数据结构化与保存

1. 将新闻的正文内容保存到文本文件。

soup = BeautifulSoup(res.text,'html.parser')
content =soup.select('.show-content')[0].text
f=open('news.txt','w',encoding='utf-8')
f.write(content)
f.close()

2. 将新闻数据结构化为字典的列表:

• 单条新闻的详情-->字典news
• 一个列表页所有单条新闻汇总-->列表newsls.append(news)
• 所有列表页的所有新闻汇总列表newstotal.extend(newsls)

 

3. 安装pandas，用pandas.DataFrame(newstotal)，创建一个DataFrame对象df.

4. 通过df将提取的数据保存到csv或excel 文件。

5. 用pandas提供的函数和方法进行数据分析：

• 提取包含点击次数、标题、来源的前6行数据
• 提取‘学校综合办’发布的，‘点击次数’超过3000的新闻。
• 提取'国际学院'和'学生工作处'发布的新闻。

import requests
import re
import pandas
import openpyxl
from bs4 import BeautifulSoup
from datetime import datetime
homepage='http://news.gzcc.cn/html/xiaoyuanxinwen/'
#newsurl='http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0411/9205.html'
res = requests.get(homepage) #返回response对象
res.encoding='utf-8'
soup = BeautifulSoup(res.text,'html.parser')
newscount=int(soup.select('.a1')[0].text.split('条')[0])
newspages = newscount // 10 + 1
allnews=[]
alllistnews=[]
def get_new_click_count(click_url):
    Res = requests.get(click_url)
    Res.encoding = 'utf-8'
    Soup = BeautifulSoup(Res.text, 'html.parser').text
    return Soup.split("('#hits').html")[1].lstrip("('").rstrip("');")


def get_all_news(newurl):
    dictionary={}
    Res = requests.get(newurl)
    Res.encoding = 'utf-8'
    Soup = BeautifulSoup(Res.text, 'html.parser')
    newlist=Soup.select('.news-list')[0].select('li')
    for newitem in newlist:
        title = newitem.select('.news-list-title')[0].text
        describe = newitem.select('.news-list-description')[0].text

        newurl=newitem.a.attrs['href']
        newcontenturl = re.search('(\d{1,}\.html)', newurl).group(1)
        newcontenturl2 = newcontenturl.rstrip('.html')
        click_url='http://oa.gzcc.cn/api.php?op=count&id='+newcontenturl2+'&modelid=80'
        newclicktimes=get_new_click_count(click_url)

        def get_new_click_content(newurl):
            Res = requests.get(newurl)
            Res.encoding = 'utf-8'
            Soup = BeautifulSoup(Res.text, 'html.parser')
            distributetime = Soup.select('.show-info')[0].text.split()[0].lstrip('发布时间:')
            author = Soup.select('.show-info')[0].text.split()[2].lstrip('作者：')
            trial = Soup.select('.show-info')[0].text.split()[3].lstrip('审核：')
            orgin = Soup.select('.show-info')[0].text.split()[4].lstrip('来源：')
            photograph = Soup.select('.show-info')[0].text.split()[5].lstrip('摄影：')
            return distributetime,author,trial,orgin,photograph
        dictionary['distributetime']=get_new_click_content(newurl)[0]
        dictionary['author'] = get_new_click_content(newurl)[1]
        dictionary['trial'] = get_new_click_content(newurl)[2]
        dictionary['orgin'] = get_new_click_content(newurl)[3]
        dictionary['photograph'] = get_new_click_content(newurl)[4]
        dictionary['title'] = title
        dictionary['describe'] = describe
        allnews.append(dictionary)
        return allnews


for i in range(2,6):
    page='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    alllistnews.extend(get_all_news(page))
df = pandas.DataFrame(alllistnews)
print(df)

df.to_excel('text.xlsx')
print(df.head(6))
super=df[(df['clickcount']>2000)&(df['source']=='学校综合办')]
print(super)

 

截图如下：