python爬虫模块之HTML解析模块

from lxml import html
import json
class GetNodeList():
    def __init__(self):
        self.getdivxpath="//div[@class=‘demo‘]"
    def use_xpath(self,source):
        if len(source):
            root=html.fromstring(source) #html转换成dom对象
            nodelist=root.xpath(self.getdivxpath)#对dom对象进行xpath解析
            if len(nodelist):
                return nodelist
            return None
            
    def use_json(self, source,keyname):
        if len(source):
            jsonstr=json.loads(source)
            value=jsonstr.get(keyname) #根据具体的键值修改
            if len(value):
                return value
            return None