欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

基于python历史天气采集的分析

程序员文章站 2023-08-17 13:42:36
分析历史天气的趋势。 先采集 代码: #-*- coding:utf-8 -*- import requests import random...

分析历史天气的趋势。

先采集

基于python历史天气采集的分析

基于python历史天气采集的分析

基于python历史天气采集的分析

代码:

#-*- coding:utf-8 -*-
import requests
import random
import mysqldb
import xlwt
from bs4 import beautifulsoup
user_agent=['mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/54.0.2840.87 safari/537.36',
    'mozilla/5.0 (x11; u; linux x86_64; zh-cn; rv:1.9.2.10) gecko/20100922 ubuntu/10.10 (maverick) firefox/3.6.10',
    'mozilla/5.0 (x11; linux x86_64) applewebkit/537.11 (khtml, like gecko) chrome/23.0.1271.64 safari/537.11',
    'mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/30.0.1599.101 safari/537.36',
    'mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.1 (khtml, like gecko) chrome/21.0.1180.71 safari/537.1 lbbrowser',
    'mozilla/5.0 (compatible; msie 9.0; windows nt 6.1; wow64; trident/5.0; slcc2; .net clr 2.0.50727; .net clr 3.5.30729; .net clr 3.0.30729; media center pc 6.0; .net4.0c; .net4.0e; qqbrowser/7.0.3698.400)',
    ]
headers={
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, sdch',
'accept-language': 'zh-cn,zh;q=0.8',
'user-agent': user_agent[random.randint(0,5)]}
 
myfile=xlwt.workbook()
wtable=myfile.add_sheet(u"历史天气",cell_overwrite_ok=true)
wtable.write(0,0,u"日期")
wtable.write(0,1,u"最高温度")
wtable.write(0,2,u"最低温度")
wtable.write(0,3,u"天气")
wtable.write(0,4,u"风向")
wtable.write(0,5,u"风力")
 
db = mysqldb.connect('localhost','root','liao1234','liao',charset='utf8')
cursor = db.cursor()
 
index = requests.get("http://lishi.tianqi.com/binjianqu/index.html",headers=headers)
html_index = index.text
index_soup = beautifulsoup(html_index)
i = 1
for href in index_soup.find("div",class_="tqtongji1").find_all("a"):
  print href.attrs["href"]
 
 
  url = href.attrs["href"]
  r = requests.get(url,headers = headers)
  html = r.text
  #print html
  soup = beautifulsoup(html)
  ss = []
  s = []
  for tag in soup.find("div",class_="tqtongji2").find_all("li"):
    print tag.string
    s.append(tag.string)
    if len(s) == 6:
      ss.append(s)
      s = []
  flag = 0
  for s in ss:
    if flag == 0:
      flag = 1
      continue
    else:
      sql = "insert into weather(old_date,hight,low,weather,wind,wind_power) values('%s','%s','%s','%s','%s','%s')"%(s[0],s[1],s[2],s[3],s[4],s[5])
      cursor.execute(sql)
      wtable.write(i,0,s[0])
      wtable.write(i,1,s[1])
      wtable.write(i,2,s[2])
      wtable.write(i,3,s[3])
      wtable.write(i,4,s[4])
      wtable.write(i,5,s[5])
      i += 1
myfile.save("weather.xls")
db.close()

以上这篇基于python历史天气采集的分析就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。