爬小说之笔趣阁

# 笔趣阁
import requests
import re
from lxml import etree

url = "https://www.biquga.com/33_33132/16700250.html"

def get_content(url):
    nodes = '';
    html_doc = requests.get(url).content.decode('gbk')
    # 网站地址编码
    tree = etree.HTML(html_doc)
    # 下一章地址
    url = tree.xpath('//*[@id="wrapper"]/div[4]/div/div[4]/a[4]//@href')[0]
    url = 'https://www.biquga.com/' + url
    # 章节标题
    node_title = tree.xpath('//*[@id="wrapper"]/div[4]/div/div[2]/h1//text()')[0]
    # 小说内容
    node_content = tree.xpath('//*[@id="content"]//text()')

    nodes += node_title
    nodes += '\n\n'
    for node in node_content:
        node = node.strip('\r')
        nodes += node
    nodes += '\n\n'
    print(node_title)
    filename = './全职妙手.txt'
    with open(filename,'a+', encoding='utf-8') as f:
        f.write(nodes)
    if re.search('.html', url) != None:
        get_content(url)
        
get_content(url)