一个完整的大作业

我选择主题是58同城二手汽车买卖网，爬取的网站是：http://gz.58.com/ershouche/?utm_source=market&spm=b-31580022738699-pe-f-829.hao360_101&PGTID=0d100000-0000-3ada-ba49-dc2ff301240a&ClickID=1

爬取网站的各个品牌的二手车品牌的链接

import requests
from bs4 import BeautifulSoup

url='http://gz.58.com/ershouche/?utm_source=market&spm=b-31580022738699-pe-f-829.hao360_101&PGTID=0d100000-0000-3ada-ba49-dc2ff301240a&ClickID=1'
res=requests.get(url)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
for esc in soup.select('li'):
    if len(esc.select('li'))>0:
        url=esc.select('a')[0]['href']
        title=esc.select('a')[0].text
        print(title,url)

分析爬取到的结果，统计词频

import jieba
fr=open("58.txt",'r',encoding='utf-8')
s=list(jieba.cut(fr.read()))
exp={'pve','
','.','_','”','“','：','http',' ','？','(',')','*',':','4917',';','ershouche','/','com'}
key=set(s)-exp
dic={}
for i in key:
    dic[i]=s.count(i)
wc=list(dic.items())
wc.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
    print(wc[i])
fr.close()

生成词云

#coding:utf-8
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator
  
text =open("58.txt",'r',encoding='utf-8').read()
print(text)
wordlist = jieba.cut(text,cut_all=True)
wl_split = "/".join(wordlist)

backgroud_Image = plt.imread('heart.jpg')  
mywc = WordCloud(
      background_color = 'white',    # 设置背景颜色
                mask = backgroud_Image,        # 设置背景图片
                max_words = 2000,            # 设置最大字数
                stopwords = STOPWORDS,        # 设置停用词
                font_path = 'C:/Users/Windows/fonts/msyh.ttf',# 设置字体格式
                max_font_size = 200,            # 设置字体值
                random_state = 30,            # 设置有多少种随机生成状态
 
    ).generate(text)
plt.imshow(mywc)
plt.axis("off")
plt.show()