import requests
from bs4 import BeautifulSoup
import os
import re
def get_Soup(Fiction_url):
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0',
        'Connection': 'keep - alive'
    }
    html_doc = requests.get(Fiction_url,headers=header)
    html_doc.encoding = 'utf-8'  # 笔趣阁网页编码为gbk 所以需要修改 防止中文乱码。
    soup = BeautifulSoup(html_doc.text, 'html.parser')
    return soup
    #返回soup
def get_FictionName(soup):
    fictionName = soup.find('h1').text
    fiction = {'名称':fictionName}
    return fiction

def mkdir(fiction):
    save_path = 'D:\\'+ fiction['名称']
    isExists = os.path.exists(save_path)   #判断目录是否存在
    if not isExists:
        os.makedirs(save_path)    #创建目录
        print('{}目录创建成功'.find(save_path))
        return save_path
    else:
        print("目录已经存在，请修改文件名")
        save_path = 'D:\\'+ input('请输入新的文件名：')
        os.makedirs(save_path)
        print('{}目录创建成功'.find(save_path))
        return save_path

def get_Fiction_AddAndName(soup):
    i = 1    #用来个章节计数用
    chapter_add = [] #章节地址 list
    chapter_name = [] #章节名 list
    rstr = r"[\=\(\)\,\/\\\:\*\?\"\<\>\|\' ']"  #为去掉章节名中的特殊字符做准备
    for chapter in soup.select('td'):
        href = chapter.select('a')[0]['href']
        chapter_add.append(href)
        name = re.sub(rstr, "", chapter.select('a')[0].text)   #去掉章节中的特殊字符
        text_name = '第' + str(i) + '章' + name
        chapter_name.append(text_name)
        i += 1
    return chapter_add,chapter_name
def get_Fiction(chapter_add,chapter_name,save_path):
    sum_chapter = len(chapter_add)
    i = 0
    for chapter in chapter_add:
        chapter_content = requests.get(chapter)
        chapter_content.encoding = 'utf-8'
        content_soup = BeautifulSoup(chapter_content.text,'html')
        try:
            text = content_soup.find('dd', id='contents').text
        except:
            print("第{}章节为空".format(i))
            text = '空'
        create_txt(text,save_path,chapter_name[i])
        i += 1
        print('共{}章,正在写入第{}章.....'.format(sum_chapter,i))
def create_txt(text,save_path,chapter_name):
    f = open(save_path+'\\'+ chapter_name+'.txt','w+',encoding='utf-8')  #创建txt文件 w 是写入 encoding 修改编码方式
    f.write(text)
    f.close()


Fiction_url = 'https://www.23us.so/files/article/html/15/15497/'

soup = get_Soup(Fiction_url)           #获取soup
fiction = get_FictionName(soup)        #获取小说名字
save_path = mkdir(fiction)             #创建目录
chapter_add,chapter_name = get_Fiction_AddAndName(soup)
get_Fiction(chapter_add,chapter_name,save_path)