import requests

from bs4 import BeautifulSoup

from selenium import webdriver

import os

class NovelSpider:

    def __init__(self):

        self.start_url = 'https://www.biqukan.com/1_1680/'

    def get_novel(self):

        # 访问起始URL

        response = requests.get(self.start_url)

        # 这里用lxml解析器会出问题，找了好久才发现。。。

        soup = BeautifulSoup(response.text, 'html.parser')

        # print(response.text)

        div_chapter = soup.find(class_="listmain")

        # print(div_chapter)
　　　　  # 选取所有的a标签，a标签包含所有章节名称和URL

        chapter_list = div_chapter.find_all('a')

        # 这里去除前12个重复的章节（具体看html代码）

        chapter_list = chapter_list[12:]

        #print(chapter_list)

        chapter = []

        # 记录总章节数，下载显示完成率

        chapter_num = len(chapter_list)

        # 设置计数器

        count = 0

        # 循环对每个章节进行访问和下载

        print('《凡人修仙传仙界篇》开始下载:')

        for cl in chapter_list:

            chapter_dict = {}

            chapter_name = cl.get_text()

            # 抓取章节名称

            chapter_dict['name'] = chapter_name

            chapter_url = cl.get('href')

            # 抓取章节URL地址

            chapter_dict['value'] = 'https://www.biqukan.com' + chapter_url

            if chapter_dict not in chapter:

                chapter.append(chapter_dict)

            print(f"已下载:{count}/{chapter_num}")

            # 调用download_novel（），按章节下载小说

            self.download_novel(chapter_dict)

            # 同时计数器加一

            count += 1

    def parse_novel(self, url):

        # 小说章节的具体内容是动态加载的，用Phantom访问

        browser = webdriver.PhantomJS(executable_path=r'F:\Spider\novelSpider\phantomjs.exe')

        browser.get(url)

        soup = BeautifulSoup(browser.page_source, 'html.parser')

        find_txt = soup.find(class_='showtxt')

        # print(type(find_txt.get_text()))

        return find_txt.get_text()

    def download_novel(self, data):  # data是{name：章节名，value：章节url地址}的字典

        filename = data['name']

        url = data['value']

        # 通过url访问小说章节的具体内容，返回小说内容，str

        txt = self.parse_novel(url)

        # 设置下载存储路径

        path = r"F:\Spider\novelSpider"

        # 检查路径是否存在，否则创建新的文件夹

        isExists = os.path.exists(path)

        if not isExists:

            # print('创建了新的文件夹')

            os.mkdir(path)

        else:

            # print('文件夹已存在')

            pass

        # 保存txt文件

        with open(path + f'\凡人修仙传仙界篇.txt', 'a', encoding='utf-8') as f:

            # print(f'正在下载--{filename}')

            f.write(f'{filename}\n\n')

            f.write(txt)

            # 章节分割线

            f.write('\n======\n\n')

            f.close()

if __name__ == '__main__':

    ns = NovelSpider()

    ns.get_novel()