python 仿站_Python-定时爬取百度风云榜实时热点

import requests

import re

import xlrd

import xlwt

import time

from bs4 import BeautifulSoup

myfile=xlwt.Workbook(encoding='utf-8')

#定义excel中sheet,宽度等

table1=myfile.add_sheet(u"百度风云实时热点",cell_overwrite_ok=True)

table1.write(0,0,u"实时热点排行")

table1.col(0).width = 6666

table1.write(0,1,u"搜索指数")

user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'

headers = { 'User-Agent' : user_agent }

list = []

target='http://top.baidu.com/buzz?b=1&c=513&fr=topbuzz_b11_c513'

req=requests.get(url=target,headers=headers)

req.encoding='gb2312'

html=req.text

class sousuo():

def __init__(self,url,table):

self.url=url

self.table=table

def chaxun(self):

url = self.url

r=requests.get(url,headers=headers)

soup=BeautifulSoup(html)

#获取热搜名称

i=1

for tag in soup.find_all('a',class_='list-title'):

if tag.string is not None:

print (tag.string)

self.table.write(i,0,tag.string)

i+=1

#获取热搜关注数 百度有3中热搜表示方式

j=1

for tag in soup.find_all(class_="icon-rise"):#上升指数

if tag.string is not None:

list.append(tag.string) #使用list数组总结

j+=1

for tag in soup.find_all(class_="icon-fall"):#下降指数

if tag.string is not None:

list.append(tag.string) #使用list数组总结

j+=1

for tag in soup.find_all(class_="icon-fair"):#持平指数

if tag.string is not None:

list.append(tag.string) #使用list数组总结

j+=1

list.sort(reverse=True) #使用sort排序，reverse表示降序

j=1 #从第一行开始写入

k=0 #从数组的第一个元素开始取出数据

for paixu in list:

if list[k] is not None:

self.table.write(j,1,list[k])

j+=1

k+=1

s1=sousuo('http://top.baidu.com/buzz?b=1&fr=topindex',table1)

s1.chaxun()

#print(list[0])

print(list)

filename="baidu-hot-top"+str(time.strftime('%Y%m%d%H%M',time.localtime()))+".xls"

myfile.save(filename)