import requests

def get_html(url):
    r = requests.get(url)
    html = r.content.decode()
    return html
def parse_data(data):
    lines = []
    url = ''
    for line in data.split('\n'):
        if '下一章' in line:
            url = line.split('"')[1] .strip() 
            break
        if line.startswith('<p>') and '=' not in line:
            line = line.strip()[3:-4]
            lines.append(line + '\n')
    return lines, url
def write_file(content):
    with open('平凡的世界.txt', 'a')  as f:
        f.writelines(content)
def main(url):
    while url:
        html = get_html(url)
        content, url = parse_data(html)
        write_file(content)
        if '06.html' in url:
            break
    
if __name__ == '__main__':
    data_url = 'http://www.pingfandeshijie.net/di-yi-bu-01.html'
    main(data_url)