import requests
from lxml import etree


class NeZha():

    def __init__(self):
        self.url = 'http://www.quanshuwan.com/book/702.aspx'
        self.url_tou = 'http://www.quanshuwan.com'
        self.header = {
            'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',
            'Referer': 'https: // movie.douban.com / subject / 26794435 / reviews?start = 480'
        }

    def get_url(self, reponse):
        html = etree.HTML(reponse.text)
        urls = html.xpath('//div[@id = "readlist"]//li/a/@href')
        link = []
        for i in urls:
            url = self.url_tou + i
            link.append(url)
        return link

    def parse_url(self, url):
        response = requests.get(url)
        html = etree.HTML(response.text)
        title = html.xpath('//div[@id="content"]/h1/text()')[0]
        contents = html.xpath('//div[@id="content"]/p/text()')
        with open(r'.\小说\%s.txt' % title, 'w', encoding='utf-8') as f:
            f.write(title)
            f.write('\n')
            for i in contents:
                f.write("    " + i)
                f.write("\n")
        f.close()

    def spider(self):
        url = self.url
        response = requests.get(url, headers=self.header)
        links = self.get_url(response)
        for i, link in enumerate(links):
            self.parse_url(link)
            print("\r第{}章下载完成，共{}章,剩余{:.2%}".format(i + 1, len(links), 1 - ((i + 1) / len(links))), end='', flush=True)


if __name__ == '__main__':
    start = NeZha()
    start.spider()