信息领域热词分类分析01

import requests
from bs4 import BeautifulSoup
import pymysql
import json
import lxml
import xlwt
def getTitle(url):
    response = requests.get(url, headers=headers)  # 发送网络请求
    content = response.content.decode(‘utf-8‘)
    soup = BeautifulSoup(content, ‘html.parser‘)
    list=soup.select(‘div:nth-child(2) > h2:nth-child(1) > a:nth-child(1)‘)
    for i in range(18):
        print(list[i].text)
    return list
url = "https://news.cnblogs.com/n/recommend?page={}"
headers = {‘user-agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36‘}#创建头部信息
f = xlwt.Workbook(encoding=‘utf-8‘)
sheet01 = f.add_sheet(u‘sheet1‘, cell_overwrite_ok=True)
sheet01.write(0, 0, ‘博客最热新闻‘)  # 第一行第一列
temp = 0
for i in range(1,100):
    newurl = url.format(i)
    title = getTitle(newurl)
    for j in range(len(title)):
        sheet01.write(temp + j + 1, 0, title[j].text)
    temp += len(title)
    print("第"+str(i)+"页打印完!")
print("全部打印完！！！")
f.save(‘Hotword02.xls‘)