程序很简单
根据url找到网站截取相应的数据。
#!/usr/bin/env python import urllib2 import re provice=raw_input('input you provice') city=raw_input("input city:") url = "http://qq.ip138.com/weather/"+provice+"/"+city+".htm" #url = "http://qq.ip138.com/weather/anhui/HuoShan.htm" class Weather(): def __init__(self): pass def getHtml(self, url): req = urllib2.Request(url) res = urllib2.urlopen(req) html = res.read() res.close() return html def getWeather(self, html): patterndate = re.compile(">(\d{4}-\d{1,2}-\d{1,2} .+)<") date = patterndate.findall(html) patternweather = re.compile("<br/>(.+)</td>") weather = patternweather.findall(html) patterntemperature = re.compile("<td>([-]?\d{1,2}.+)</td>") temperature = patterntemperature.findall(html) if len(date) == 0: print "Cannot get city's weather you input" return for i in range(len(date)): print "%s" % date[i], "\t%s" % weather[i], "\t%s" % temperature[i] if __name__ == "__main__": weather = Weather() weather.getWeather(weather.getHtml(url))
后期准备存库
原文地址:http://blog.csdn.net/u010278923/article/details/43309923