爬虫学习笔记：爬取笔趣阁小说

# -*- coding: utf-8 -*-
import requests
from lxml import etree

class BookSpider(object):
    def __init__(self):
        self.url = "http://www.jianlaixiaoshuo.com/"
        self.base_url = "http://www.jianlaixiaoshuo.com/"
        self.headers = {
            "Use_Agent": "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"}
    #请求网页内容
    def get_html(self,url):
        html = requests.get(url,headers = self.headers).content.decode()
        return html
    #封装xpath
    def get_xpath(self,html,pattern):
        p = etree.HTML(html)
        result = p.xpath(pattern)
        return result
    #保存数据
    def save_data(self, data):
        with open('剑来.txt','a',encoding='utf-8')as f:
            f.write(data)
    #下载数据
    def down_load(self,url):
        html = self.get_html(self.url)