python学习系列3——爬取历史天气数据

根据输入的城市和年月，对该地区该时间段的历史天气数据进行爬取。其中用到了xpinyin库Pinyin类对输入的地名转换为拼音，用于获取信息时的地址输入。将获得的天气数据进行打印和保存

代码：

import urllib2
import urllib
import codecs
import random
import os
from xpinyin import Pinyin
from bs4 import BeautifulSoup
class Weather:
    #初始化方法
    def __init__(self):
        self.user_agent='Mozilla/5.0 (Windows NT 6.1; Win64; x64)'
        self.headers = {'User-Agent': self.user_agent}
        self.contens=[]
    # 先获取可查询的天气范围
    def weatherRange(self,Location):
        try:
            url_ = 'http://lishi.tianqi.com/' + Location + '/index.html'
            request_ = urllib2.Request(url_, headers=self.headers)
            response_ = urllib2.urlopen(request_)
            pageCode_ = response_.read()
            soup_ = BeautifulSoup(pageCode_)
            range_ = soup_.select('span.f_12')
            return range_
        except urllib2.HTTPError,e:
            if hasattr(e, "code"):
                print u"获取历史天气查询范围失败，错误原因：", e.code
                return None
            if hasattr(e, "reason"):
                print u"获取历史天气查询范围失败，错误原因：", e.reason
                return None
    #获取某月的页面代码
    def getPageCode(self,date_,Location):
            try:
                url = 'http://lishi.tianqi.com/' +Location + '/' + date_ + '.html'
                request = urllib2.Request(url, headers=self.headers)
                response = urllib2.urlopen(request)
                pageCode = response.read()
                return pageCode
            except urllib2.HTTPError, e:
                if hasattr(e, "code"):
                    print u"连接天气网失败，错误原因：", e.code
                    return None
                if hasattr(e, "reason"):
                    print u"连接天气网失败，错误原因：", e.reason
                    return None
    #获得某月的历史数据
    def getPageInfo(self,date_,Location):
        pageCode=self.getPageCode(date_,Location)
        if pageCode:
            soup=BeautifulSoup(pageCode)
            #天气详情
            soup = BeautifulSoup(pageCode)
            nodes = soup.select('div#tool_site')
            node1 = nodes[1]
            #标题
            xiangqingtitle = node1.select('div.box-hd')
            #天气详情
            xiangqing = node1.select('ul li')
            #风向统计
            node2=nodes[2]
            #标题
            fengxiangtitle=node2.select('div.box-hd')
            #风向详情
            fengxiang=node2.select('ul li')
            #风力统计
            node3=nodes[3]
            #标题
            fenglititle=node3.select('div.box-hd')
            #风向详情
            fengli=node3.select('ul li')
            return xiangqingtitle,xiangqing,fengxiangtitle,fengxiang,fenglititle,fengli
        else:
            print "页面加载失败..."
            return None
    # 加载该月的数据内容,并进行保存
    def loadInfo(self,date_,Location):
            xiangqingtitle, xiangqing, fengxiangtitle, fengxiang, fenglititle, fengli= self.getPageInfo(date_,Location)
            if xiangqing:
                print u"\n正在获取%s月的天气数据...\n" %date_
                print u"\n正在打印%s月的天气数据...\n"%date_
                # 随机创建txt文件，并向txt文件写入
                path_file_name = 'weather' + str(random.randint(1, 1000)) + '.txt'
                if not os.path.exists(path_file_name):
                   f = codecs.open(path_file_name, 'w', 'utf-8')
                #打印天气详情
                print xiangqingtitle[0].get_text().strip()
                f.write(xiangqingtitle[0].get_text().strip())
                f.write('\r\n')
                i=0
                for item in xiangqing:
                      i+=1
                      if i%6==0:
                        print item.get_text().strip(),
                        f.write(item.get_text().strip())
                        f.write('\r\n')
                        print '\n'
                      else:
                        print item.get_text().strip(),
                        f.write(item.get_text().strip())
                #打印风向
                print '\n'
                print fengxiangtitle[0].get_text().strip()
                i=0
                for item in fengxiang:
                    i+=1
                    if i%4==0:
                        print item.get_text().strip(),
                        print '\n'
                    else:
                        print item.get_text().strip(),
                #打印风力
                print '\n'
                print fenglititle[0].get_text().strip()
                for item in fengli:
                        print item.get_text().strip(),
            else:
                print "页面加载失败..."
                return
    #开始方法
    def start(self,date_,Location):
        #开始加载资源
        self.loadInfo(date_,Location)
        enable=True
        while enable:
            input_=raw_input("\n是否继续查询，是输入1，否输入0\n")
            if input_==str(1):
                Location_ = raw_input("\n请输入查询历史天气的城市名:\n")
                pin = Pinyin()
                Location = pin.get_pinyin(Location_.decode('utf-8'),"")
                range_ =self.weatherRange(str(Location))
                print u"\n%s可供查询历史天气的时间范围是%s\n" % (Location_.decode('utf-8'), range_[0].get_text().strip())
                date_ = raw_input("\n请输入查询年月（如201101）:\n")
                self.loadInfo(str(date_), str(Location))
            else:
                enable=False
Location_=raw_input("请输入查询历史天气的城市名:\n")
pin = Pinyin()
Location=pin.get_pinyin(Location_.decode('utf-8'),"")
spider=Weather()
range_=spider.weatherRange(str(Location))
print u"\n%s可供查询历史天气的时间范围是%s\n"%(Location_.decode('utf-8'),range_[0].get_text().strip())
date_=raw_input("\n请输入查询年月（如201101）:\n")
spider=Weather()
spider.start(str(date_),str(Location))