1.选一个自己感兴趣的主题。

2.用python 编写爬虫程序,从网络上爬取相关主题的数据。

3.对爬了的数据进行文本分析,生成词云。

4.对文本分析结果进行解释说明。

说明:本文爬取的是中国日报网的教育模块,由文本分析结果可知中国教育已经开始跟人工智能有紧密联系了,科技即将是中国孩子教育的主题

5.写一篇完整的博客,描述上述实现过程、遇到的问题及解决办法、数据分析思想及结论。

6.最后提交爬取的全部数据、爬虫及数据分析源代码。

# -*- coding: UTF-8 -*-# -*-
import requests
import re
import jieba
import locale
locale=locale.setlocale(locale.LC_CTYPE, 'chinese')

from bs4 import BeautifulSoup
from datetime import datetime


url = "http://ent.chinadaily.com.cn/"
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')

def getKeyWords(text):
str = '''一!“”,。?、;’"',.、·《》()#\t:\n'''
for s in str:
text = text.replace(s, '')
newsList=list(jieba.lcut(text))

newsDict = {}
deleteList = []

for i in newsDict.keys():
if len(i) < 2:
deleteList.append(i) # 生成单字无意义字符列表
for i in deleteList:
del newsDict[i] # 在词云字典中删除无意义字符
newsSet = set(newsList) - set(deleteList)
for i in newsSet:
newsDict[i] = newsList.count(i) # 生成词云字典

dictList = list(newsDict.items())
dictList.sort(key=lambda x: x[1], reverse=True)

# 将所有词频写出到txt
for topWordTup in dictList:
print(topWordTup)
with open('news.txt', 'a+', encoding='UTF-8') as wordFile:
for i in range(0, topWordTup[1]):
wordFile.write(topWordTup[0] + '\n')

for i in range(20):

print('关键词:',dictList[i])

def getNewDetail(newsUrl):
resd = requests.get(newsUrl)
resd.encoding = 'utf-8'
soupd = BeautifulSoup(resd.text, 'html.parser')

title = soupd.select('h1')[0].text
info = soupd.select('.xinf-le')[0].text

t = soupd.select('#pubtime')[0].text
dt = datetime.strptime(t, ' %Y-%m-%d %H:%M:%S')
# source = soupd.select('#source')[0].text.lstrip(' 来源:')
biaoqian = soupd.select('.fenx-bq')[0].text.lstrip('标签:')

if info.find('作者:') > 0:
au = info[info.find('作者:'):].split()[0].lstrip('作者:')
else:
au = 'none'
if info.find('来源:') > 0:
source = info[info.find('来源:'):].split()[0].lstrip('来源:')
else:
source = 'none'

content = soupd.select('#Content')[0].text.strip()

print("标题:", title)
print("作者:",au)
print("来源:",source)
print("发布时间:", dt)
print("正文:",content)
print("标签:", biaoqian)
getKeyWords(content)


def getListPage(ListPageUrl):
res = requests.get(ListPageUrl)
res.encoding = 'utf-8'
soupd = BeautifulSoup(res.text, 'html.parser')
pagedetail = [] # 存储一页所有新闻的详情
for news in soupd.select('.busBox1'):
atail = news.a.attrs['href']
# a = 'http://ent.chinadaily.com.cn/' + atail
getNewDetail(atail)

pagedetail = getListPage('http://ent.chinadaily.com.cn/node_53008152.htm')
for i in range(2, 10):
listUrl='http://ent.chinadaily.com.cn/node_53008152_{}.htm'
pagedetail = getListPage(listUrl)

 

 

posted on 2018-04-30 21:44  189黄思慧  阅读(189)  评论(0编辑  收藏  举报