爬取百度热搜榜并把数据可视化

import numpy as np

import matplotlib.pyplot as plt

import matplotlib as mpl

from scipy.optimize import leastsq 

import requests

from bs4 import BeautifulSoup

import pandas as pd

import csv

import jieba

import wordcloud

import requests

from lxml import etree

head = {}

url = "http://top.baidu.com/buzz?b=341&fr=topindex

head["User-Agent"] = "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:63.0) Gecko/20100101 Firefox/63.0"

head["Accept"]= "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"

head["Accept-Language"]= "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2"

head["Connection"] = "keep-alive"

def main():
print("百度热搜top： 

  res = requests.get(url , headers = head)

 with open("html.txt", "wb") as f:

 f.write(res.content)

html = etree.parse(‘html.txt‘ , etree.HTMLParser(encoding=‘gbk‘)

 top_list = html.xpath(‘//a[@class="list-title"]/text()‘

 num_search = html.xpath(‘//span[@class="icon-rise"]/text()‘

 for i  , j in zip(top_list[:10] , num_search[:10]):

 print(i ,"搜索指数为：" ,  j  )

if __name__ == ‘__main__‘

 main()

1 import pandas as pd
2 kugou=pd.DataFrame(pd.read_excel(‘data.xls‘))
3 kugou.head()
4 kugou.drop(1,axis=0,inplace=True)
5 kugou.head()