Obtain administrative divisions in the latest China and administrative divisions in China

Obtain administrative divisions in the latest China and administrative divisions in China

To put it bluntly, go to the Code:

import urlparsefrom StringIO import StringIOimport datetimeimport requestsimport lxmlfrom lxml import etreedef get_latest_url(index_url):    response=requests.get(index_url)    parser=etree.HTMLParser()    tree   = etree.parse(StringIO(response.content ), parser)    r = tree.xpath('//ul[@class="center_list_contlist"]')    if len(r)==1:        div=r[0]        href = div.xpath('li/a/@href')[0]        return urlparse.urljoin(index_url,href)    else:        return Nonedef get_xingzhengquhua_text(latest_url, referer=None):    response=requests.get(latest_url)    parser= etree.HTMLParser()    tree   = etree.parse(StringIO(response.content ), parser)    r = tree.xpath('//div[@class="xilan_con"]')    print r    if len(r)==1:        div=r[0]        div2 = div.xpath('div/div')[0]        div3 = div2.xpath('.//p')        p=[]        for line in div3:            #line = line.replace(u'\xa0', u' ').strip()            #if not line:            #    continue            try:                code=line.xpath('span[1]/text()')[0]                name=line.xpath('span[2]/text()')[0].strip(u'\u3000')            except:                continue            if code.endswith('0000'):                parent=''            elif code.endswith('00'):                parent=code[:2]+'0000'            else:                parent=code[:4]+'00'            p.append((parent,code,name))        text='\n'.join(map(lambda x:','.join(x),p))        text=text.encode('utf-8')        print text        return text    else:        text=Noneif __name__ == '__main__':    index_url='http://www.stats.gov.cn/tjsj/tjbz/xzqhdm/'    #latest_url='http://www.stats.gov.cn/tjsj/tjbz/xzqhdm/201401/t20140116_501070.html'    latest_url=get_latest_url(index_url)    print latest_url    if latest_url:        text=get_xingzhengquhua_text(latest_url)        filename=latest_url.strip().split('/')[-1]        print filename        try:            filename=filename.split('_')[0][1:]        except:            now=datetime.datetime.now()            filename=now.strftime('%Y-%m-%d')        if text:            ff=open('latest-xingzhengquhua-%s.txt' % filename,'w')            ff.write(text)            ff.close()        else:            print 'Failed get xingzhengquehua data!'    else:        print 'Failed get latest data url'