python爬虫小白升仙_2-----爬取天气预报信息

目的：从中国天气网爬取城市天气预报信息，得到7天的天气信息，并存入excel中

技术：requests、xpath的使用，openpyxl写入数据到excel（.xlsx），生成exe ： pyinstaller -F Weather_Spider.py

1. 分析网页，通过xpath获取相关数据，并对数据进行简单处理

area=xml.xpath('//div[@class="crumbs fl"]//a/text()')    # 地区
concrete_area=xml.xpath('//div[@class="crumbs fl"]//span/text()')
week=xml.xpath('//div[@class="con today clearfix"]//li//h1/text()')  # 7天
wea=xml.xpath('//div[@class="con today clearfix"]//li//p[@class="wea"]/text()')  # 天气
tem=xml.xpath('//div[@class="con today clearfix"]//li//p[@class="tem"]//i/text()')  # 温度

 

 

2. 使用openpyxl将数据写入excel中

3. 建立部分城市与代码的字典，提供查询

4. 测试并生成exe

5. 源码如下：

import time
import requests
import os
from lxml import etree
import openpyxl
from openpyxl.styles import Font,colors
import traceback

class Weather_Forecast(object):
    def __init__(self,url):
        self.__url=url

    # 获取网页信息
    def get_request(self):
        response=requests.get(self.__url)
        xml=etree.HTML(response.content)
        area=xml.xpath('//div[@class="crumbs fl"]//a/text()')    # 地区
        concrete_area=xml.xpath('//div[@class="crumbs fl"]//span/text()')
        self.week=xml.xpath('//div[@class="con today clearfix"]//li//h1/text()')  # 7天
        self.wea=xml.xpath('//div[@class="con today clearfix"]//li//p[@class="wea"]/text()')  # 天气
        self.tem=xml.xpath('//div[@class="con today clearfix"]//li//p[@class="tem"]//i/text()')  # 温度
        # print(self.week)
        # print(self.wea)
        # print(self.tem)
        for concrete_ar in concrete_area:
            if concrete_ar != '>':
                # print(concrete_ar)
                concrete_area_str=concrete_ar
        self.str=area[0]+">"+area[1]+">"+area[2]+">"+concrete_area_str    # 处理提取到的地区字符
        # print(self.str)

    # 写excel
    def write_excel(self):
        try:
            if os.path.exists("天气.xlsx"):
                wb = openpyxl.load_workbook("天气.xlsx")  # 打开已有文件
                # 创建一张新表
                # ws=wb.create_sheet()
                ws = wb["Sheet"]  # 通过名字选择表
            else:
                wb = openpyxl.Workbook()    # 新建Excel 实例化
                ws = wb.active   # 激活 worksheet
            # 设置字体为“宋体”，大小为11，bold为加粗，italic为斜体，strike为删除线，颜色为红色
            font = Font(u'宋体', size=21, bold=True, italic=True, strike=False, color=colors.RED)
            ws["A1"].font=font
            ws.column_dimensions['A'].width = 25  # 列宽
            ws.column_dimensions['B'].width = 25
            ws.column_dimensions['C'].width = 20
            ws.column_dimensions['D'].width = 20
            columnsHeader = ["地区", "当前时间", "星期", "天气", "温度"]
            for i in range(5):
                ws.cell(row=1, column=i + 1, value=columnsHeader[i])    # 写入列标题
            ws.cell(row=2, column=1, value=self.str)
            datetime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()));  # 获取当前时间，并格式化
            ws.cell(row=2, column=2, value=datetime)
            for i in range(7):
                ws.cell(row=i+2, column=3, value=self.week[i].encode("utf-8"))     # 写入单元格内容
            for i in range(7):
                ws.cell(row=i+2, column=4, value=self.wea[i].encode("utf-8"))
            for i in range(7):
                ws.cell(row=i+2, column=5, value=self.tem[i].encode("utf-8"))
            ws.merge_cells('F1:G1')  # 合并单元格
            wb.save("天气.xlsx")     # 保存表格
            print("已成功获取天气信息，并写入excel中！")
        except Exception:
            print(traceback.print_exc())


# 获取相应城市的url
def get_url():
    city = {
        "苏州": "101190401",
        "西安": "101110101",
        "北京": "101010100",
        "上海": "101020100",
        "南京": "101190101",
        "厦门": "101230201",
        "深圳": "101280601",
        "珠海": "101280701",
        "佛山": "101280800"
    }
    for k in city:
        print(k + " ", end="")
    print(" ")
    city_name = input("Please enter the city name for the query :")
    try:
        city_num = city[city_name]
        weather_url = "http://www.weather.com.cn/weather/%s.shtml" % city_num
    except Exception:            # 输入错误则默认为苏州
        print(traceback.print_exc())
        time.sleep(0.01)     # 加延迟 将异常信息输出完全再继续执行
        print("输入错误则默认为苏州！")
        weather_url = "http://www.weather.com.cn/weather/101190401.shtml"
    return weather_url

if __name__=="__main__":
    GetWeather=Weather_Forecast(get_url())
    GetWeather.get_request()
    GetWeather.write_excel()
    input("Press <enter>")

6.  运行结果：