网络爬虫-通过百度百科查询行政区划代码

纯属练手

import  requests
import  re
from requests.exceptions import RequestException


def get_page(url):
    try:
        res=requests.get(url)
        res.encoding = 'utf-8'
        if res.status_code==200:
            return res.text
        else:
            return None
    except RequestException:
        return  None
def parse_page(html):
        pattern=re.compile('<h1 >(.*?)</h1>.*?(区码代码|行政代码).*?basicInfo-item value">\n(.*?)(<sup>|\n).*?</dd>',re.S)
        #pattern=re.compile('(.*?)<sup>',re.S)
        result=re.findall(pattern,html)
        print(result)
        #return result
        if result !=[]:
            return  {
                'Code':result[0][2]
                ,'Rname':result[0][0]
                }
        else:
            return {
                'Code':''
                ,'Rname':''
                }
def main():
    List=['龙门县','遂溪县','广州市','从化市','万山海洋开发试验区','aaa']
    codes=[]
    for c in List:
        html=get_page('http://baike.baidu.com/item/'+str(c))
        code=parse_page(html)
        code['Qname']=c
        codes.append(code)
    print(codes)
if __name__ == '__main__':
    main()