# -*- coding: utf-8 -*-

"""

Created on Wed Nov  8 14:23:14 2017

@author: 123

"""

import requests

'''from bs4 import BeautifulSoup

import traceback'''

import re

import urllib

import random

'''用于获取HTML源代码'''

def getHTMLText(url):

    try:

        r = requests.get(url , timeout = 30)

        r.raise_for_status()

        r.encoding = r.apparent_encoding

        return r.text

    except:

        return "ERROR!"

'''通过去除标签获取HTML源代码中的正文信息'''

def getRealText(html):

    dre = re.compile(r'<[^>]+>',re.S)

    real_Text = dre.sub('',html)

    '''print(real_Text)'''

    return real_Text

def write_into(real_Title,real_Text):

    f = open(real_Title,'w')

    f.write(real_Text)

    f.close()

def test(real_Text):

    GDP = re.findall(".*地区生产总值(.*?)亿元.*",real_Text)

    for x in GDP:

        print(x)

    '''通过正则表达式匹配出地区生产总值和亿元之间的数字,即excel表格中的数值'''

    get = re.findall(".*地方公共财政预算收入(.*?)亿元.*",real_Text)

    for x in get:

        print(x)

def main():

    url = "http://xxgk.xiaogan.gov.cn/xxgk/jcms_files/jcms1/web30/site/art/2017/4/1/art_5130_17454.html"

    html = getHTMLText(url)

    Title = re.search('<title>.*</title>',html)

    '''获取html的title信息，即excel表格中的数据来源'''

    real_Title = Title.group().strip("</title>")

    real_Text = getRealText(html)

    write_into(real_Title,real_Text)

    test(real_Text)

main()