#获取起点小说的爬虫程序
#倒推法
import requests
from lxml import etree
url="https://book.qidian.com/info/1979049/#Catalog"#小说的网址
def getdata(url):
    html=requests.get(url).text
    # print(html)
    doc=etree.HTML(html)#构造xpath的解析对象
    contents=doc.xpath('//*[@class="cf"]/li')
    # print(contents)
    for content in contents:
        links=content.xpath('h2/a/@href')
        for link in links:
            hurl="https:"+link#小说某一章的网址
            html=requests.get(hurl).text#获取到源代码
            doc=etree.HTML(html)#构造xpath解析对象
            title=doc.xpath('//*[@class="text-wrap"]/div/div[1]/h3/span[1]/text()')
            content=doc.xpath('//*[@class="read-content j_readContent"]/p/text()')
            with open('novel/%s.txt'%title[0],mode='w',encoding='utf-8') as f:
                for abd in content:
                    f.write(abd)
a=getdata(url)