一个完整的python大作业

由于能选择一个感兴趣的网站进行数据分析，所以这次选择爬取的网站是新华网，其网址为"http://www.xinhuanet.com/"，然后对其进行数据分析并生成词云

运行整个程序相关的代码包

import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime
import pandas
import sqlite3
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt

爬取网页信息

url = "http://www.xinhuanet.com/"

f=open("css.txt","w+")
res0 = requests.get(url)
res0.encoding="utf-8"
soup = BeautifulSoup(res0.text,"html.parser")
newsgroup=[]
for news in soup.select("li"):
    if len(news.select("a"))>0:
        print(news.select("a")[0].text)
        title=news.select("a")[0].text
        f.write(title)
f.close()

存入txt文件中，并进行字词统计

f0 = open('css.txt','r')
qz=[]
qz=f0.read()
f0.close()
print(qz)

words = list(jieba.cut(qz))

ul={':','的','"','、','”','“','。','！','：','？',' ','\u3000','，','\n'}
dic={}

keys = set(words)-ul
for i in keys:
    dic[i]=words.count(i)

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

f1 = open('diectory.txt','w')
for i in range(10):
    print(c[i])
    for words_count in range(c[i][1]):
        f1.write(c[i][0]+' ')
f1.close()

存入数据库

df = pandas.DataFrame(words)

print(df.head())

with sqlite3.connect('newsdb3.sqlite') as db:

    df.to_sql('newsdb3',con = db)

制作词云

f3 = open('diectory.txt','r')
cy_file = f3.read()
f3.close()
cy = WordCloud().generate(cy_file)
plt.imshow(cy)
plt.axis("off")
plt.show()

最终成果

 完整代码

import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime
import pandas
import sqlite3
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt


url = "http://www.xinhuanet.com/"

    

f=open("css.txt","w+")
res0 = requests.get(url)
res0.encoding="utf-8"
soup = BeautifulSoup(res0.text,"html.parser")
newsgroup=[]
for news in soup.select("li"):
    if len(news.select("a"))>0:
        print(news.select("a")[0].text)
        title=news.select("a")[0].text
        f.write(title)
f.close()

f0 = open('css.txt','r')
qz=[]
qz=f0.read()
f0.close()
print(qz)

words = list(jieba.cut(qz))

ul={':','的','"','、','”','“','。','！','：','？',' ','\u3000','，','\n'}
dic={}

keys = set(words)-ul
for i in keys:
    dic[i]=words.count(i)

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

f1 = open('diectory.txt','w')
for i in range(10):
    print(c[i])
    for words_count in range(c[i][1]):
        f1.write(c[i][0]+' ')
f1.close()

df = pandas.DataFrame(words)

print(df.head())

with sqlite3.connect('newsdb3.sqlite') as db:

    df.to_sql('newsdb3',con = db)


f3 = open('diectory.txt','r')
cy_file = f3.read()
f3.close()
cy = WordCloud().generate(cy_file)
plt.imshow(cy)
plt.axis("off")
plt.show()

 

转载于:https://www.cnblogs.com/murasame/p/7769198.html