【爬虫】2.6 实践项目——爬取天气预报数据

1. 项目简介

在中国天气网(http://www.weather.com.cn)中输入一个城市的名称，例如输入深圳，那么会转到地址http://www.weather.com.cn/weather1d/101280601.shtml的网页显示深圳的天气预报，其中101280601是深圳的代码，每个城市或者地区都有一个代码。如下图：

在上图中可以看到，深圳今天，7天，8-15天等的天气数据，这里爬取7天的天气预报数据。

2. HTML 代码分析

分析这段代码：

7天的天气预报实际上在一个

元素中，每天是一个M
• 元素，7天的结构差不多是一样的(注意：今天没有最高温度与最低温度)。

  3. 爬取天气预报数据

  ---

  from bs4 import BeautifulSoup
  from bs4.dammit import UnicodeDammit  # BS内置库，用于推测文档编码
  import urllib.request  # 发起请求，获取响应
  
  url = "http://www.weather.com.cn/weather/101280601.shtml"
  
  try:
      headers = {
          "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
                        "(KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 Edg/109.0.1518.78"}
      req = urllib.request.Request(url, headers=headers)  # 创建请求对象
      data = urllib.request.urlopen(req)  # 发起请求
      data = data.read()  # 获得响应体
      dammit = UnicodeDammit(data, ["utf-8", "gbk"])
      data = dammit.unicode_markup  # 解码
      soup = BeautifulSoup(data, "lxml")
      lis = soup.select("ul[class='t clearfix'] li")
      x = 0
      for li in lis:
          try:
              date = li.select('h1')[0].text
              weather = li.select('p[class="wea"]')[0].text
              if x == 0:  # 为今天只有一个温度做判断 <i>14℃</i>
                  x += 1
                  temp = li.select('p[class="tem"] i')[0].text
              else:
                  temp = li.select('p[class="tem"] span')[0].text + "/" + li.select('p[class="tem"] i')[0].text
              print(date, weather, temp)
              # 22日（今天） 晴 14℃
              # 23日（明天） 晴 23℃/14℃
              # 24日（后天） 晴转多云 25℃/13℃
              # 25日（周六） 多云 21℃/13℃
              # 26日（周日） 多云转晴 22℃/12℃
              # 27日（周一） 晴 21℃/12℃
              # 28日（周二） 晴 24℃/14℃
          except Exception as err:
              print(err)
  except Exception as err:
      print(err)
  

  4. 爬取与存储天气预报数据

  ---

  获取北京、上海、广州、深圳等城市的代码，爬取这些城市的天气预报数据，并存储到sqllite数据库weathers.db中，存储的数据表weathers是：

  create table weathers (wCity varchar(16),wDate varchar(16),wWeather varchar(64),wTemp varchar(32),constraint pk_weather primary key (wCity,wDate))"

  编写程序依次爬取各个城市的天气预报数据存储在数据库中，程序如下：

  from bs4 import BeautifulSoup
  from bs4.dammit import UnicodeDammit
  import urllib.request
  import sqlite3
  
  # 天气数据库
  class WeatherDB:
      def __init__(self):
          self.cursor = None
          self.con = None
  
      def openDB(self):
          self.con = sqlite3.connect("weathers.db")
          self.cursor = self.con.cursor()
          try:
              self.cursor.execute(
                  "create table weathers (wCity varchar(16),"
                  "wDate varchar(16),"
                  "wWeather varchar(64),"
                  "wTemp varchar(32),"
                  "constraint pk_weather primary key (wCity,wDate))")
          except Exception as err:
              print(err)
              self.cursor.execute("delete from weathers")
  
      def closeDB(self):
          self.con.commit()
          self.con.close()
  
      def insert(self, city, date, weather, temp):
          try:
              self.cursor.execute("insert into weathers (wCity,wDate,wWeather,wTemp) values (?,?,?,?)",
                                  (city, date, weather, temp))
          except Exception as err:
              print(err)
  
      def show(self):
          self.cursor.execute("select * from weathers")
          rows = self.cursor.fetchall()
          print("%-16s%-16s%-32s%-16s" % ("city", "date", "weather", "temp"))
          for row in rows:
              print("%-16s%-16s%-32s%-16s" % (row[0], row[1], row[2], row[3]))
  
  # 天气预报
  class WeatherForecast:
      def __init__(self):
          self.headers = {
              "User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) "
                            "Gecko/2008072421 Minefield/3.0.2pre"}
          self.cityCode = {"北京": "101010100", "上海": "101020100", "广州": "101280101", "深圳": "101280601"}
  
      def forecastCity(self, city):
          if city not in self.cityCode.keys():
              print(city + " 找不到代码")
              return
          url = "http://www.weather.com.cn/weather/" + self.cityCode[city] + ".shtml"
          try:
              req = urllib.request.Request(url, headers=self.headers)
              data = urllib.request.urlopen(req)
              data = data.read()
              dammit = UnicodeDammit(data, ["utf-8", "gbk"])
              data = dammit.unicode_markup
              soup = BeautifulSoup(data, "lxml")
              lis = soup.select("ul[class='t clearfix'] li")
              x = 0
              for li in lis:
                  try:
                      date = li.select('h1')[0].text
                      weather = li.select('p[class="wea"]')[0].text
                      if x == 0:  # 为今天只有一个温度做判断 <i>14℃</i>
                          x += 1
                          temp = li.select('p[class="tem"] i')[0].text
                      else:
                          temp = li.select('p[class="tem"] span')[0].text + "/" + li.select('p[class="tem"] i')[0].text
                      print(city, date, weather, temp)
                      self.db.insert(city, date, weather, temp)
                  except Exception as err:
                      print(err)
          except Exception as err:
              print(err)
  
      def process(self, cities):
          self.db = WeatherDB()
          self.db.openDB()
  
          for city in cities:
              self.forecastCity(city)
  
          # self.db.show()
          self.db.closeDB()
  
  ws = WeatherForecast()
  ws.process(["北京", "上海", "广州", "深圳"])
  print("completed")
  

  程序执行结果如下：