笔趣网小说试爬

import requests
from lxml import etree

url = "http://www.cits0871.com/booktxt/20768/"
file_name = '第一序列.txt'
res = requests.get(url).content.decode('gbk')
content = etree.HTML(res)
url = content.xpath("//div[@id='list']/dl/dd/a/@href")
k = 1
with open(file_name, 'w', encoding='utf-8') as f:
    f.write("")
for i in url:
    k += 1
    url = "http://www.cits0871.com" + i
    res = requests.get(url).content.decode('gbk')
    content = etree.HTML(res)
    name = content.xpath("//div[@class='bookname']/h1/text()")[0]
    ls = name.split('、')
    if len(ls) < 2:
        continue
    name = "第" + ls[0]+ "章  "+ls[1]
    text = content.xpath("//div[@id='content']/text()")

    with open(file_name,'a',encoding='utf-8') as f:
        f.write( name +"\n")
    for sr in text:
        with open(file_name, 'a', encoding='utf-8') as f:
            f.write(sr+"\n")
    with open(file_name, 'a', encoding='utf-8') as f:
        f.write("\n\n\n\n")
    print(name+"爬取成功")