数据结构化与保存

1. 将新闻的正文内容保存到文本文件。

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

news['content'] = soupd.select('.show-content')[0].text.strip()
writeNewsDetail(news['content'])

 

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)

def getNewsList(pageUrl):
    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(getNewDetail(newsUrl))
    return (newsList)

newsTotal = []
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
newsTotal.extend(getNewsList(url))

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

df = pandas.DataFrame(newsTotal)
print(df)

4. 通过df将提取的数据保存到csv或excel 文件。

df.to_excel('wxc.xlsx')

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。

  print(df[(df['clickCount']>3000) & (df['source'] == '学校综合办')])
  print(df[['clickCount', 'title', 'source']].head(6))
  sou = ['国际学院', '学生工作处']
  print(df[df['source'].isin(sou)])

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


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

def getClickCount(newsUrl):
    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 getNewDetail(newsUrl):
    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['clickCount'] = getClickCount(newsUrl)
    return (news)

def getNewsList(pageUrl):
    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(getNewDetail(newsUrl))
    return (newsList)

def getpageN():
    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 = []
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
newsTotal.extend(getNewsList(url))

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

df = pandas.DataFrame(newsTotal)
# print(df)
df.to_excel('wxc.xlsx')
# print(df[(df['clickCount']>3000) & (df['source'] == '学校综合办')])
#print(df[['clickCount', 'title', 'source']].head(6))
sou = ['国际学院', '学生工作处']
print(df[df['source'].isin(sou)])