Python 爬取国家统计局的省市区数据

 说明：

1. 数据暂时不能爬取全，由于频繁请求会超时
2. 建议配置多个代理轮询调用爬去
3. 只爬取到区的信息，可以不用上代理

# -*-coding:utf-8 -*-
import urllib2
import sys

# 接上面代码
from bs4 import BeautifulSoup as bs

reload(sys)
sys.setdefaultencoding('GBK')


def get_url_content(url):
    i_headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5", \
                 "Referer": 'http://www.baidu.com'}
    req = urllib2.Request(url, headers=i_headers)
    # proxies = {"http": "114.244.112.220:8118"}  # 设置你想要使用的代理
    # proxy_s = urllib2.ProxyHandler(proxies)
    # opener = urllib2.build_opener(proxy_s)
    # urllib2.install_opener(opener)
    return urllib2.urlopen(req, timeout=10).read().decode('GBK')


html_data = get_url_conte