Hadoop綜合大做業&補交4次做業：獲取所有校園新聞，網絡爬蟲基礎練習，中文詞頻統計，熟悉經常使用的Linux操做

時間 2020-04-07

標籤 hadoop 綜合大做補交獲取所有網絡爬蟲基礎練習中文詞頻統計熟悉經常使用 linux 欄目 Hadoop 简体版

原文原文鏈接

1.用Hive對爬蟲大做業產生的文本文件（或者英文詞頻統計下載的英文長篇小說）進行詞頻統計。php

（1）開啓全部的服務，並建立文件夾wwchtml

(2)查看目錄下全部文件java

（3）把hdfs文件系統中文件夾裏的文本文件load進去。linux

（4）進入hive,並查看全部的表正則表達式

(5)建立表word,,寫hiveQL命令統計api

（6）運行結果bash

獲取所有校園新聞

1.取出一個新聞列表頁的所有新聞包裝成函數。網絡

2.獲取總的新聞篇數，算出新聞總頁數。app

3.獲取所有新聞列表頁的所有新聞詳情。jvm

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

# 獲取新聞點擊次數
def getNewsId(url):
    newsId = re.search(r'\_\d{4}\/((.*)).html', url).group(1)
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正則表達式獲取新聞點擊次數
    clickCount = int(re.search("hits'\).html\('(.*)'\);", clickRes.text).group(1))
    return clickCount


# 獲取新聞細節
def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')

    content = soupd.select('#content')[0].text
    info = soupd.select('.show-info')[0].text
    # 調用getNewsId()獲取點擊次數
    count = getNewsId(newsUrl)
    # 識別時間格式
    date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1)
    # 識別一個至三個數據
    if(info.find('做者：')>0):
        author = re.search('做者：((.{2,4}\s|.{2,4}、|\w*\s){1,3})', info).group(1)
    else:
        author = '無'
    if(info.find('審覈：')>0):
        check = re.search('審覈：((.{2,4}\s){1,3})', info).group(1)
    else:
        check = '無'
    if(info.find('來源：')>0):
        sources = re.search('來源：(.*)\s*攝|點', info).group(1)
    else:
        sources = '無'
    if (info.find('攝影：') > 0):
        photo = re.search('攝影：(.*)\s*點', info).group(1)
    else:
        photo = '無'
    # 用datetime將時間字符串轉換爲datetime類型
    dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
    # 利用format對字符串進行操做
    print('發佈時間：{0}\n做者：{1}\n審覈：{2}\n來源：{3}\n攝影：{4}\n點擊次數：{5}'.format(dateTime, author, check, sources, photo, count))
    print(content)


def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')

    for new in soup.select('li'):
        if len(new.select('.news-list-title')) > 0:
            title = new.select('.news-list-title')[0].text
            description = new.select('.news-list-description')[0].text
            newsUrl = new.select('a')[0]['href']

            print('標題:{0}\n內容:{1}\n連接:{2}'.format(title, description, newsUrl))
            # 調用getNewsDetail()獲取新聞詳情
            getNewsDetail(newsUrl)
            break


listUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
getListPage(listUrl)
res = requests.get(listUrl)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')
listCount = int(soup.select('.a1')[0].text.rstrip('條'))//10+1

for i in range(2,listCount):
    listUrl= 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    getListPage(listUrl)

4.找一個本身感興趣的主題，進行數據爬取，並進行分詞分析。不能與其它同窗雷同。

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


def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'gb2312'
    soupd = BeautifulSoup(resd.text, 'html.parser')

    content = soupd.select('#endText')[0].text
    info = soupd.select('.post_time_source')[0].text
    date = re.search('(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})', info).group(1)
    dateTime = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
    sources = re.search('來源:\s*(.*)', info).group(1)
    keyWords = getKeyWords(content)
    print('發佈時間：{0}\n來源：{1}'.format(dateTime, sources))
    print('關鍵詞：{}、{}、{}'.format(keyWords[0], keyWords[1], keyWords[2]))
    print(content)


def getKeyWords(content):
    content = ''.join(re.findall('[\u4e00-\u9fa5]', content))
    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)
    for i in deleteList:
        del wordDict[i]
    dictList = list(wordDict.items())
    dictList.sort(key=lambda item: item[1], reverse=True)
    for i in range(3):
        keyWords.append(dictList[i][0])
    return keyWords


def getListPage(listUrl):
    res = requests.get(listUrl)
    res.encoding = 'gbk'
    soup = BeautifulSoup(res.text, 'html.parser')
    for new in soup.select('.news_item'):
        newsUrl = new.select('a')[0]['href']
        title = new.select('a')[0].text
        print('標題：{0}\n連接：{1}'.format(title, newsUrl))
        getNewsDetail(newsUrl)
        break

listUrl = 'http://sports.163.com/zc/'
getListPage(listUrl)
for i in range(2, 20):
    listUrl = 'http://tech.163.com/special/it_2016_%02d/' % i
    getListPage(listUrl)

網絡爬蟲基礎練習

import requests
from bs4 import BeautifulSoup
res = requests.get('http://news.qq.com/')
res.encoding = 'UTF-8'
soup = BeautifulSoup(res.text, 'html.parser')

# 取出h1標籤的文本
for h1 in soup.find_all('h1'):
    print(h1.text)
# 取出a標籤的連接
for a in soup.find_all('a'):
    print(a.attrs.get('href'))
# 取出全部li標籤的全部內容
for li in soup.find_all('li'):
    print(li.contents)
# 取出第2個li標籤的a標籤的第3個div標籤的屬性
print(soup.find_all('li')[1].a.find_all('div')[2].attrs)

# 取出一條新聞的標題、連接、發佈時間、來源
print(soup.select('div .news-list-title')[0].text)
print(soup.select('div .news-list-thumb')[0].parent.attrs.get('href'))
print(soup.select('div .news-list-info > span')[0].text)
print(soup.select('div .news-list-info > span')[1].text)

中文詞頻統計

從文件讀取待分析文本。

news = open('gzccnews.txt','r',encoding = 'utf-8')

安裝與使用jieba進行中文分詞。

pip install jieba

import jieba

list(jieba.lcut(news))

生成詞頻統計

排序

排除語法型詞彙，代詞、冠詞、連詞

輸出詞頻最大TOP20

import jieba

fo=open('test.txt','r',encoding='utf-8')
text=fo.read()

textlist=list(jieba.lcut(text))

Dworlds=['，','也','。','若','亦','宜','、','之','於','「','」','：','曰','；','\u3000'
    ,'\n','了','與','中','有','而','人','不','我','在','來','！','遂','？','爲','又','被','皆','問','至','言','衆','吾','等','見','將']

textdic={}
for t in textlist:
    textdic[t]=textdic.get(t,0)+1


for i in Dworlds:
    if i in textdic:
        del textdic[i]

newtext=sorted(textdic.items(),key=lambda x:x[1],reverse=True)

for i in range(20):
   print(newtext[i])

運行截圖：