python豆瓣图书top250+词云

# -*- coding: utf-8 -*-
"""
Created on Sun Dec 27 18:25:34 2020

@author: David
"""
#导入相关的包
from lxml import etree
import requests
import time 

#爬取数据写入文件
douban=open(r'C:\Users\David\Desktop\douban.txt','a+',encoding='utf-8')
for a in range(10):
    url = 'https://book.douban.com/top250?start={}'.format(a*25)
    header = {
    
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
    data = requests.get(url,headers=header).text

    s=etree.HTML(data)
    file=s.xpath('//*[@id="content"]/div/div[1]/div/table')

    for div in file:
        title =div.xpath("./tr/td[2]/div[1]/a/@title")[0]
        href=div.xpath("./tr/td[2]/div[1]/a/@href")[0]
        score=div.xpath("./tr/td[2]/div[2]/span[2]/text()")[0]
        num=div.xpath("./tr/td[2]/div[2]/span[3]/text()")[0].strip("(").strip(")").strip()
        author=div.xpath("./tr/td[2]/p[1]/text()")
        scrible=div.xpath("./tr/td[2]/p[2]/span/text()")
        if len(scrible)>0:
            print("{},{},{},{},{},{}\n".format(title,href,score,num,author,scrible[0]))
        else:
            print("{},{},{},{},{}\n".format(title,href,score,num,author))
        for i in author:
            b=str(i)
            c=b.split('/')[0]
            douban.write(c)     
 
    
#爬取短评数据写入文件
douban_dunanpin=open(r'C:\Users\David\Desktop\douban_dunanpin.txt','a+',encoding='utf-8')
for a in range(10):
    url = 'https://book.douban.com/top250?start={}'.format(a*25)
    header = {
    
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
    data = requests.get(url,headers=header).text

    s=etree.HTML(data)
    file=s.xpath('//*[@id="content"]/div/div[1]/div/table')

    for div in file:
        scrible=div.xpath("./tr/td[2]/p[2]/span/text()")
        douban_dunanpin.write(str(scrible))        
    
    
#导入词云想关的包                       
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np 

#将文件读取出来
with open(r'C:\Users\David\Desktop\douban.txt','r',encoding='utf-8') as f:
    authors=f.readlines()
    print(authors)

#分隔列表为字符串
a=' '.join(authors)

#运用jieba进行分词
douban_cut=jieba.cut(a)

#分词后的字符串
douban_text=" ".join(douban_cut)

#最高词频作者词云图绘制部分
x,y = np.ogrid[:300,:300]
mask = (x-150) ** 2 + (y-150) ** 2 > 130 ** 2
mask = 255 * mask.astype(int)
wc=WordCloud(font_path="C:/Windows/Fonts/simfang.ttf",background_color="white",repeat=True,mask=mask)
wordcloud=wc.generate(douban_text)
wordcloud.to_file(r'C:\Users\David\Desktop\豆瓣.png')



#评分和评价信息

# 导入相关的包
import pandas as pd

#用列表存入信息
sample=[]
for a in range(10):
    url = 'https://book.douban.com/top250?start={}'.format(a*25)
    header = {
    
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
    data = requests.get(url,headers=header).text

    s=etree.HTML(data)
    file=s.xpath('//*[@id="content"]/div/div[1]/div/table')

    for div in file:
        title =div.xpath("./tr/td[2]/div[1]/a/@title")[0]
        score=div.xpath("./tr/td[2]/div[2]/span[2]/text()")[0]
        num=div.xpath("./tr/td[2]/div[2]/span[3]/text()")[0].strip("(").strip(")").strip()
        sample.append([title,score,num[:-3]])

df = pd.DataFrame(sample,columns=['title','score','num'])




import matplotlib.pyplot as plt
import numpy as np
 
# 构建数据
x_data = list(df['title'][:10])
y_data = list(df['score'][:10])
# 绘图
plt.rcParams['font.sans-serif']=['SimHei']
plt.bar(x=x_data, height=y_data, color='steelblue', alpha=0.8)
plt.xticks(rotation=45)
# 设置标题
plt.title("排名前十的图书得分")
# 为两条坐标轴设置名称
plt.xlabel("书名")
plt.ylabel("评分")
# 显示图例
plt.legend()



import matplotlib.pyplot as plt
import numpy as np
 
# 构建数据
x_data = list(df['title'][:10])
y_data = list(df['num'][:10])
# 绘图
plt.rcParams['font.sans-serif']=['SimHei']
plt.bar(x=x_data, height=y_data, color='steelblue', alpha=0.8)
plt.xticks(rotation=45)
# 设置标题
plt.title("排名前十的图书评论数")
# 为两条坐标轴设置名称
plt.xlabel("书名")
plt.ylabel("评论数目")
# 显示图例
plt.legend()




#爬取短评数据写入文件
douban_dunanpin=open(r'C:\Users\David\Desktop\douban_dunanpin.txt','a+',encoding='utf-8')
for a in range(10):
    url = 'https://book.douban.com/top250?start={}'.format(a*25)
    header = {
    
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
    data = requests.get(url,headers=header).text

    s=etree.HTML(data)
    file=s.xpath('//*[@id="content"]/div/div[1]/div/table')

    for div in file:
        scrible=div.xpath("./tr/td[2]/p[2]/span/text()")
        douban_dunanpin.write(str(scrible))     
 
    
    
#导入词云想关的包                       
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np 

#将文件读取出来
with open(r'C:\Users\David\Desktop\douban_dunanpin.txt','r',encoding='utf-8') as f:
    duan=f.readlines()
    print(duan)

#分隔列表为字符串
a=' '.join(duan)

#运用jieba进行分词
duan_cut=jieba.cut(a)

#分词后的字符串
duan_text=" ".join(duan_cut)

#最高词频作者词云图绘制部分
x,y = np.ogrid[:300,:300]
mask = (x-150) ** 2 + (y-150) ** 2 > 130 ** 2
mask = 255 * mask.astype(int)
wc=WordCloud(font_path="C:/Windows/Fonts/simfang.ttf",background_color="white",repeat=True,mask=mask)
wordcloud=wc.generate(duan_text)
wordcloud.to_file(r'C:\Users\David\Desktop\豆瓣duan.png')