获取全部校园新闻

Posted on 2018-04-11 20:43  170何强  阅读(147)  评论(0编辑  收藏  举报

1.取出一个新闻列表页的全部新闻 包装成函数。

2.获取总的新闻篇数,算出新闻总页数。

3.获取全部新闻列表页的全部新闻详情。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')


def getClick(newsUrl):
    newId = re.search('\_(.*).html', newsUrl).group(1).split('/')[1]
    click = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newId))
    return click.text.split('.html')[-1].lstrip("('").rstrip("');")


def getNews(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')
    title = soupd.select('.show-title')[0].text
    info = soupd.select('.show-info')[0].text
    dt = datetime.strptime(info.lstrip('发布时间:')[0:19], '%Y-%m-%d %H:%M:%S')
    if (info.find('作者:') > 0):
        author = re.search('作者:((.{2,4}\s|.{2,4}、){1,3})', info).group(1)
    if (info.find('审核:') > 0):
        check = re.search('审核:((.{2,4}\s){1,3})', info).group(1)
    if (info.find('来源:') > 0):
        sources = re.search('来源:((.{2,50}\s|.{2,50}、|.{2,50},){1,5})', info).group(1)
    content = soupd.select('.show-content')[0].text.strip()
    click = getClick(newsUrl)
    print(click,title,newsUrl,author,check,sources,dt)


def getListPage(listPageUrl):
    res=requests.get(listPageUrl)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    for news in soup.select('li'):
        if len(news.select('.news-list-title')) > 0:
            a = news.select('a')[0].attrs['href']
            getNews(a)

# listPageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
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(''))//10+1
for i in range(2,3):
    listPageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    getListPage(listPageUrl)

4.找一个自己感兴趣的主题,进行数据爬取,并进行分词分析。不能与其它同学雷同。

我选择的是我玩的手游官网公告,因为公告有图片而我爬的只有文字所以会有大片空白

import requests, re, jieba
from bs4 import BeautifulSoup
from datetime import datetime

# 获取新闻细节
def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'gb2312'
    soupd = BeautifulSoup(resd.text, 'html.parser')
    print(soupd.text)
    content = soupd.select('.artText')[0].text
    info = soupd.select('.artDate')[0].text
    title = soupd.select('h1')[0].text
    date = re.search('(\d{4}.\d{2}.\d{2})', info).group(1)  # 识别时间格式
    dateTime = datetime.strptime(date, '%Y-%m-%d')  # 用datetime将时间字符串转换为datetime类型
    keyWords = getKeyWords(content)
    print('标题:{}'.format(title))
    print('发布时间:{0}'.format(dateTime))
    print('关键词:{}、{}、{}'.format(keyWords[0], keyWords[1], keyWords[2]))
    print(content)

# 通过jieba分词,获取新闻关键词
def getKeyWords(content):
    content = ''.join(re.findall('[\u4e00-\u9fa5]', content))  # 通过正则表达式选取中文字符数组,拼接为无标点字符内容
    wordSet = set(jieba._lcut(content))
    wordDict = {}
    for i in wordSet:
        wordDict[i] = content.count(i)
    deleteList, keyWords = [], []
    for i in wordDict.keys():
        if len(i) < 2:
            deleteList.append(i)  # 去掉单字无意义字符
    for i in deleteList:
        del wordDict[i]
    dictList = list(wordDict.items())
    dictList.sort(key=lambda item: item[1], reverse=True)  # 排序,返回前三关键字
    for i in range(3):
        keyWords.append(dictList[i][0])
    return keyWords

# 获取一页的新闻
def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = 'gbk'
    soup = BeautifulSoup(res.text, 'html.parser')
    for new in soup.select('.txt-list'):
        newsUrl = new.select('a')[0]['href']
        t = 'http:'+newsUrl
        print(t)




        getNewsDetail(t)  # 调用getNewsDetail()获取新闻详情
        break  # z只获取单个新闻,若要获取整页则去掉break

for i in range(1, 31):
    listUrl = 'http://stzb.163.com/news/index_{}.html'.format(i)
    getListPage(listUrl)

Copyright © 2022 170何强
Powered by .NET 6 on Kubernetes