Python笔记从html中提取字段

来源：互联网发布：三菱fx2n编程手册编辑：程序博客网时间：2024/06/07 10:36

def fun():    # url = 'http://quote.eastmoney.com/sh600010.html?from=BaiduAladdin'    url_total = 'http://api.map.baidu.com/place/v2/search?q=景区&page_size=20&page_num=1&region=白山市&scope=2&output=json&ak=秘钥'    response = requests.get(url_total)    url_total_html = response.text    # print(html)    # print(type(html),type(response),html[10:15])    # test1=html["total:[]"]    # print(test1)    # test2 ='total'    # print(html.find(test2))    total_0=r'[\d]+'   #提取所有数字，构成list    result=re.compile(total_0)    #将正则表达式编译成对象 其等价于result=re.compile(r'[\d]+')    total_1=re.findall(result,url_total_html)    # 匹配对象，其等价total_1=result.findall(url_total_html)    # print('\n',total_0,type(total_0),len(total_0))    # print(total_1[1],type(total_0[1]))    # print(int(total_1[1]),type(int(total_1[1])))    total_2=int(total_1[1])#提取后其为List,找到对应索引，将str转int    print(total_2)    #f = open('total—city', 'w')    #f.writelines(total_2)    #f.close()if __name__=='__main__':    fun()

阅读全文

1 0