Python脚本

基于**阁网站写的一个Python爬虫
代码如下：

import requests
from bs4 import BeautifulSoup

def simple_crawel(url):
    html = requests.get(url).content.decode('utf-8')
    soup = BeautifulSoup(html, 'lxml')
    content = soup.find('div',id='content').get_text()
    f = open("./sancunrenjian.txt",'a',encoding='utf-8')
    f.write(content)

def get_all():
    html = requests.get(URL).content.decode('utf-8')
    html1 = html.replace("\n", "").replace('\t','')
    soup = BeautifulSoup(html1, 'lxml')
    list = soup.find('div',id='list').dl.children
    for dd in list:
        try:
            f = open("./sancunrenjian.txt", 'a', encoding='utf-8')
            f.write('\n\n\n'+dd.a.get_text()+'\n')
            print(dd.a.get_text())
            xr = base_url+dd.a.get('href')
            simple_crawel(xr)
        except:
            print("")

if __name__ == '__main__':
    get_all()

Python是真的强大，不到30行代码就完成了