读取新浪天气预报信息

周末就要考试职称英语了，这个星期就好好做几套真题，最近手头没甚要紧事就把抓取天气预报的代码重新整了整，刚刚梳理了一下，先记录下来，随后再整合到我的weapho项目中。

抓取信息脚本：

base_url = "http://php.weather.sina.com.cn/xml.php"
city = urlencode({"city":city_name.decode('utf-8').encode('gb2312')})
password = urlencode({"password":"DJOYnieT8234jlsK"})
for i in range(3):
day = urlencode({"day": i})
reader = urlopen(base_url + "?" + "&]

通过解析新浪提供的xml文件来获取信息，解析xml文件的脚本如下：

#coding=utf-8
#file:utility.py
#by: fatway#gmail.com

from xml2dict import XML2Dict

def _xml_2_dict(w_xml):
xml = XML2Dict()
w_dict = xml.fromstring(w_xml)
return w_dict

def _get_weather(w_xml):
w_info = _xml_2_dict(w_xml)
result = {}

if 'Weather' not in w_info.Profiles:
return result

weather = w_info.Profiles.Weather

city = weather.city  # 城市
status1 = weather.status1  # 白天天气
status2 = weather.status2  # 夜间天气
power = weather.power1  # 风力
temperature1 = weather.temperature1  # 白天温度
temperature2 = weather.temperature2  # 夜间温度

result["city"] = city
if status1 == status2:
result["status"] = status1
else:
result["status"] = status1 + u"\u8f6c" + status2
result["power"] = power
result["temperature"] = str(temperature2) \
+ "-" \
+ str(temperature1) \
+ u"\u2103"
result["chy"] = chy

return result

def weather(w_xml):
weather_info = _get_weather(w_xml)
temp = []
#    temp.append(weather_info["city"])
temp.append(weather_info["status"])
temp.append(weather_info["temperature"])
temp.append(weather_info["power"])

return ",".join(temp)

xml文件的解析我一直没有认真研究过，使用minidom就可以。为了省事我使用了开源项目xml2dict(http://code.google.com/p/xml2dict/)，将xml文件转换为dict字典再处理。

PS-1:

备注一个准备用来做选择目标城市用的脚本

#coding=utf-8
#file:place.py
#by: fatway#gmail.com

province = (
(0, "北京"),
(1, "天津"),
(2, "重庆"),
(3, "河北省"),
(4, "山西省"),
(5, "内蒙古"),
(6, "辽宁省"),
(7, "吉林省"),
(8, "黑龙江省"),
(9, "上海"),
(10, "江苏省"),
(11, "浙江省"),
(12, "安徽省"),
(13, "福建省"),
(14, "江西省"),
(15, "山东省"),
(16, "河南省"),
(17, "湖北省"),
(18, "湖南省"),
(19, "广东省"),
(20, "广西"),
(21, "海南省"),
(22, "四川省"),
(23, "贵州省"),
(24, "云南省"),
(25, "西藏"),
(26, "陕西省"),
(27, "甘肃省"),
(28, "青海省"),
(29, "宁夏"),
(30, "新xj疆"),
(31, "台湾省"),
(32, "香港"),
(33, "澳门")
)
province_dict = dict(province)

city = {
0: ((0, "北京"),),

1: ((0, "天津"),),

2: ((0, "重庆"),),

3: ((0, "石家庄"),
(1, "唐山"),
(2, "秦皇岛"),
(3, "张家口"),
(4, "承德"),
(5, "廊坊"),
(6, "邯郸"),
(7, "邢台"),
(8, "保定"),
(9, "沧州"),
(10, "衡水")
),

4: ((0, "太原"),
(1, "大同"),
(2, "阳泉"),
(3, "晋城"),
(4, "朔州"),
(5, "忻州"),
(6, "离石"),
(7, "榆次"),
(8, "临汾"),
(9, "运城"),
(10, "长治")
),

5: ((0, "呼和浩特"),
(1, "包头"),
(2, "乌海"),
(3, "集宁"),
(4, "巴彦浩特"),
(5, "临河"),
(6, "鄂尔多斯"),
(7, "赤峰"),
(8, "通辽"),
(9, "锡林浩特"),
(10, "海拉尔"),
(11, "乌兰浩特")
),

6: ((0, "沈阳"),
(1, "大连"),
(2, "鞍山"),
(3, "抚顺"),
(4, "本溪"),
(5, "锦州"),
(6, "营口"),
(7, "阜新"),
(8, "盘锦"),
(9, "铁岭"),
(10, "朝阳"),
(11, "丹东")
),

7: ((0, "长春"),
(1, "吉林"),
(2, "四平"),
(3, "辽源"),
(4, "松原"),
(5, "白城"),
(6, "延边"),
(7, "通化")
),

8: ((0, "哈尔滨"),
(1, "鸡西"),
(2, "鹤岗"),
(3, "双鸭山"),
(4, "伊春"),
(5, "佳木斯"),
(6, "七台河"),
(7, "牡丹江"),
(8, "绥化"),
(9, "齐齐哈尔"),
(10, "大庆"),
(11, "黑河"),
(12, "大兴安岭")
),

9: ((0, "上海"),),

10: ((0, "南京"),
(1, "无锡"),
(2, "徐州"),
(3, "常州"),
(4, "苏州"),
(5, "南通"),
(6, "连云港"),
(7, "淮阴"),
(8, "盐城"),
(9, "扬州"),
(10, "镇江"),
(11, "泰州"),
(12, "宿迁")
),

11: ((0, "杭州"),
(1, "宁波"),
(2, "温州"),
(3, "嘉兴"),
(4, "湖州"),
(5, "绍兴"),
(6, "金华"),
(7, "衢州"),
(8, "舟山"),
(9, "丽水"),
(10, "台州")
),

12: ((0, "合肥"),
(1, "芜湖"),
(2, "蚌埠"),
(3, "淮南"),
(4, "马鞍山"),
(5, "淮北"),
(6, "铜陵"),
(7, "安庆"),
(8, "黄山市"),
(9, "阜阳"),
(10, "宿州"),
(11, "滁州"),
(12, "六安"),
(13, "宣城"),
(14, "巢湖"),
(15, "池州")
),

13: ((0, "福州"),
(1, "厦门"),
(2, "莆田"),
(3, "三明"),
(4, "泉州"),
(5, "漳州"),
(6, "南平"),
(7, "宁德"),
(8, "龙岩")
),

14: ((0, "南昌"),
(1, "景德镇"),
(2, "赣州"),
(3, "萍乡"),
(4, "九江"),
(5, "新余"),
(6, "鹰潭"),
(7, "宜春"),
(8, "上饶"),
(9, "吉安")
),

15: ((0, "济南"),
(1, "青岛"),
(2, "淄博"),
(3, "枣庄"),
(4, "东营"),
(5, "烟台"),
(6, "潍坊"),
(7, "济宁"),
(8, "泰安"),
(9, "威海"),
(10, "日照"),
(11, "滨州"),
(12, "德州"),
(13, "聊城"),
(14, "临沂"),
(15, "菏泽"),
(16, "莱芜")
),

16: ((0, "郑州"),
(1, "开封"),
(2, "洛阳"),
(3, "平顶山"),
(4, "安阳"),
(5, "鹤壁"),
(6, "新乡"),
(7, "焦作"),
(8, "濮阳"),
(9, "许昌"),
(10, "漯河"),
(11, "三门峡"),
(12, "商丘"),
(13, "周口"),
(14, "驻马店"),
(15, "南阳"),
(16, "信阳")
),

17: ((0, "武汉"),
(1, "黄石"),
(2, "十堰"),
(3, "随州"),
(4, "宜昌"),
(5, "襄樊"),
(6, "鄂州"),
(7, "荆门"),
(8, "黄冈"),
(9, "孝感"),
(10, "咸宁"),
(11, "荆州"),
(12, "恩施")
),

18: ((0, "长沙"),
(1, "衡阳"),
(2, "邵阳"),
(3, "郴州"),
(4, "永州"),
(5, "韶山"),
(6, "张家界"),
(7, "怀化"),
(8, "吉首"),
(9, "株洲"),
(10, "湘潭"),
(11, "岳阳"),
(12, "常德"),
(13, "益阳"),
(14, "娄底")
),

19: ((0, "广州"),
(1, "佛山"),
(2, "深圳"),
(3, "汕尾"),
(4, "惠州"),
(5, "河源"),
(6, "清远"),
(7, "东莞"),
(8, "珠海"),
(9, "江门"),
(10, "肇庆"),
(11, "中山"),
(12, "湛江"),
(13, "茂名"),
(14, "韶关"),
(15, "汕头"),
(16, "梅州"),
(17, "阳江"),
(18, "潮州"),
(19, "顺德"),
(20, "揭阳"),
(21, "云浮")
),

20: ((0, "南宁"),
(1, "梧州"),
(2, "玉林"),
(3, "桂林"),
(4, "百色"),
(5, "河池"),
(6, "钦州"),
(7, "柳州"),
(8, "北海"),
(9, "防城港"),
(10, "贵港"),
(11, "贺州")
),

21: ((0, "海口"),
(1, "三亚"),
(2, "西沙")
),

22: ((0, "成都"),
(1, "眉山"),
(2, "雅安"),
(3, "峨嵋山"),
(4, "自贡")
),

23: ((0, "贵阳"),
(1, "六盘水"),
(2, "铜仁"),
(3, "安顺"),
(4, "凯里"),
(5, "都匀"),
(6, "兴义"),
(7, "毕节"),
(8, "遵义")
),

24: ((0, "昆明"),
(1, "德宏"),
(2, "曲靖"),
(3, "楚雄"),
(4, "玉溪"),
(5, "红河"),
(6, "文山"),
(7, "思茅"),
(8, "昭通"),
(9, "西双版纳"),
(10, "大理"),
(11, "保山"),
(12, "怒江"),
(13, "丽江"),
(14, "迪庆"),
(15, "临沧")
),

25: ((0, "拉萨"),
(1, "昌都"),
(2, "日喀则"),
(3, "那曲"),
(4, "阿里"),
(5, "林芝")
),

26: ((0, "西安"),
(1, "铜川"),
(2, "宝鸡"),
(3, "咸阳"),
(4, "渭南"),
(5, "汉中"),
(6, "安康"),
(7, "商洛"),
(8, "延安"),
(9, "榆林")
),

27: ((0, "兰州"),
(1, "白银"),
(2, "金昌"),
(3, "天水"),
(4, "张掖"),
(5, "武威"),
(6, "定西"),
(7, "平凉"),
(8, "临夏"),
(9, "嘉峪关"),
(10, "酒泉")
),

28: ((0, "西宁"),
(1, "果洛"),
(2, "海西"),
(3, "格尔木"),
(4, "海东"),
(5, "海北"),
(6, "玉树"),
(7, "黄南")
),

29: ((0, "银川"),
(1, "石嘴山"),
(2, "吴忠"),
(3, "固原")
),

30: ((0, "乌鲁木齐"),
(1, "克拉玛依"),
(2, "吐鲁番"),
(3, "哈密"),
(4, "昌吉"),
(5, "博乐"),
(6, "库尔勒"),
(7, "阿克苏"),
(8, "克州"),
(9, "喀什"),
(10, "伊犁"),
(11, "石河子"),
(12, "塔城"),
(13, "阿勒泰")
),

31: ((0, "台北"),),
32: ((0, "香港"),),
33: ((0, "澳门"),)

}

def get_all_province_name():
'''返回所有省份名称列表'''
return province_dict.values()

def get_province_name_by_id(prov_id):
'''根据省份代码获取名称'''
id = int(prov_id)
name = province_dict.get(id)
return name

def get_province_id_by_name(prov_name):
'''根据省份名称获取省份代码'''
for p_id,p_name in province:
if prov_name == p_name:
return p_id
return 99

def get_citys_by_province_id(prov_id):
'''根据省份代码获取所属城市清单'''
prov_id = int(prov_id)
return dict(city.get(prov_id, ()))

def get_citys_by_province_name(prov_name):
'''根据省份名称获取所属城市清单'''
prov_id = get_province_id_by_name(prov_name)
return get_citys_by_province_id(prov_id)

def get_city_name_by_provandcity_id(prov_id,city_id):
'''根据省、市代码获取城市名称'''
prov_id,city_id = int(prov_id),int(city_id)
citys_in_prov = get_citys_by_province_id(prov_id)
city_name = citys_in_prov.get(city_id, ())
return city_name

def get_id_by_city_name(city_name):
'''根据城市名称查询对应的省、市代码'''
for p_id,p_name in province:
citys = get_citys_by_province_id(p_id)
for c_id,c_name in citys.items():
if city_name == c_name:
return p_id,c_id
return 99,99

def city_viewer():
'''获取省份和城市的全景字典'''
result = {}
for prov_key,prov_name in province:
sub_result = {}
sub_result[prov_name] = dict(city.get(prov_key, ())).values()

result.update(sub_result)

return result

if __name__ == "__main__":
print get_province_name_by_id(19).decode('utf-8').encode('gbk')
print get_province_id_by_name("广东省")

print get_city_name_by_provandcity_id(19, 07).decode('utf-8').encode('gbk')
print get_id_by_city_name("东莞")

PS-2（废话）：

中午购网线30米、天线35米、转接头3个、网线直通一个、水晶头若干，花掉125大元。下午肯定要在困顿中度过了。

-End-