最近学习python 感觉这门脚本语言十分灵活 而且功能十分强大 尤其是他re库用于正则匹配十分强大
写了个例子解析中国天气网
例如 terminal中输入python weather.py http://www.weather.com.cn/weather/101010100.shtml 北京6天的天气数据 json格式
#coding=utf-8
#weather.py
import urllib
import re
import simplejson
import sys
if len(sys.argv) != 2:
print 'please enter: python ' + sys.argv[0] + ' <url>'
exit(0)
url = sys.argv[1];
def readurlPageContent(url):#获取页面的所有数据 逐行读取
webpage = urllib.urlopen(url);
line = webpage.readline();
data = ''
while line:
data = data + line.strip(); #去除每行两边的的空格
line = webpage.readline();
return data
def getDatabody(data):
reg = re.compile(r'(<div class=\"weatherYubaoBox\">(?:(?!<div)(?!</div).)*</div>)');
matchs = reg.findall(data,re.I);
if len(matchs) > 0:
return matchs[0]
return None
def getSixDayWeather(data):
regs = re.compile(r'>((?:(?!<)(?!>)(?!var).)+)<');
datas = regs.findall(data)
if len(datas) > 12:
datas = datas[12:len(datas)-7];#提取其中的78项 即后面6天的天气数据 每天相关的信息有13个
return datas
return None
data = readurlPageContent(url);
match_data = getDatabody(data)
if match_data == None :
print 'get weather data fail'
exit(0)
weathers_data = getSixDayWeather(match_data)
if weathers_data == None:
print 'get six day info fail'
exit(0)
count = len(weathers_data);
groups_item_count = count / 6;
weathers = {};
groups = [];
start = 0
for item in weathers_data :
if (start % groups_item_count) == 0:
groups = [];
weathers[('day'+str(start/groups_item_count + 1))] = groups;
groups.append(item)
start = start + 1
print simplejson.dumps(weathers, encoding='UTF-8', ensure_ascii=False)
其中会用到simplejson这个库 呵呵 如何安装 你懂的