Python获取小说数据分析

#%%
import requests
from lxml import etree
import pandas #数据分析模块
import matplotlib

url = 'https://www.qb5200.la/top/allvisit/'
hearders = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
'Cookie':'Hm_lvt_007bc30c1abb0ffb7a93b4f3c8e10c5e=1697951520; Hm_lpvt_007bc30c1abb0ffb7a93b4f3c8e10c5e=1697951595'
}

respond = requests.get(url,headers=hearders)
#print(respond.text)

resp = etree.HTML(respond.text)
types = resp.xpath('//div[@id="articlelist"]/ul[2]/li/span[1]/text()')
names = resp.xpath('//div[@id="articlelist"]/ul[2]/li/span[2]/a/text()')
autors = resp.xpath('//div[@id="articlelist"]/ul[2]/li/span[3]/text()')
word_count = resp.xpath('//div[@id="articlelist"]/ul[2]/li/span[5]/text()')
recommendations =resp.xpath('//div[@id="articlelist"]/ul[2]/li/span[6]/text()')

data = []

for type,name,autor,count,recommendation in zip(types,names,autors,word_count,recommendations):
    #print(f'{type}--{name}---{autor}----{count}----{recommendation}')
    data.append([type,name,autor,count[:-1],recommendation])

#%%


df = pandas.DataFrame(data,columns=['类型','书名','作者','字数','推荐票'])
df.to_excel('小说数据.xlsx',index=False)
print(df)

#%%
df.describe()

#%%
df.groupby('类型').count

#%%
df.类型.hist()

#%%