Python3-爬取页面元素的几种方法

方法一：xpath

from lxml import etree
import requests
from requests import exceptions

def get_response(url, headers=None, timeout=None):

    """"
    当条件为假，断言失败
    assert response.status_code == 200'请求报错，请求状态码为: %s'%str(response.status_code)
    """
    try:
        response = requests.get(url, headers=headers, timeout=timeout)
    except exceptions.Timeout as e:
        response = None
        raise e
    except exceptions.HTTPError as e:
        response = None
        raise e
    except exceptions.ConnectTimeout as e:
        response = None
        raise e
    except exceptions.ReadTimeout as e:
        response = None
        raise e
    except exceptions.ProxyError as e:
        response = None
        raise e
    except Exception as e:
        response = None
        raise e
    finally:
        return response

de