python获取在线小说章节

以笔趣阁小说宋时归为例：

INPUT输入第一页网址：https://www.shengxu5w.com/4_4743/2041526.html

import requests, re
from lxml import etree


def get_text(url, novel):
    urls = url
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE'
    }

    req = requests.get(urls, headers=headers)
    req.encoding = req.apparent_encoding #获取源文件编码
    html = etree.HTML(req.text)

    title = html.xpath("//h1/text()")[0]  #获取文章标题
    contents = html.xpath('//*[@id="content"]/text()') #获取正文
    content = ""

    for j in contents:
        content += j
    content = re.sub("s+", "\r\t\n"