python学习之——爬取网页信息

爬取网页信息

说明：正则表达式有待学习，之后完善此功能

#encoding=utf-8

import urllib
import re
import os

#获取网络数据到指定文件
def getHtml(url,fname):
    #fname = ‘C:\\Users\cuiliting\\Desktop\\weather_forecast.txt‘
    data =[]
    page = urllib.urlopen(url)
    html = page.read()
    data.append(html)
    fobj = open(fname,‘w‘)
    fobj.writelines(‘%s‘ %x for x in data)
    fobj.close()
    page.close()  

#从文件获取得到所需数据
def getWeather(fname,weath_keyword):
    fobj = open(fname,‘r‘)
    for eachline in fobj:
        if weath_keyword in eachline:
            print eachline,

    fobj.close()  

if __name__ == ‘__main__‘:
    #url_input = raw_input("please enter url:")
    #fname_input = raw_input("please enter fname:")
    #weath_keyword_input = ‘raw_input("please enter keywords:")‘
    url_input = ‘http://www.weather.com.cn/weather/101010100.shtml‘
    fname_input = ‘C:\\Users\\Desktop\\weather_forecast.txt‘
    weath_keyword_input = ‘<h1>10日（明天）</h1>‘
    getHtml(url_input,fname_input)
    getWeather(fname_input,weath_keyword_input)