小说爬取

# -*-conding:utf-8-*-
"""
    # File       : 获取西游记数据.py
    # Time       ：2022/4/24 17:38
    # Author     ：希维
    # version    ：python 3.8
    # Description：
"""
import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
from lxml import etree
import os

def getTitleLink(url):
    """
        ：获取目录页上各章节标题和链接
    """
    headers = {
        'user-Agent':UserAgent().random
    }
    resp = requests.get(url, headers=headers).content.decode('gbk', errors='ignore')  # 获取相应内容，改变内容编码格式
    e = etree.HTML(resp)
    chapters = e.xpath("/html/body/div[5]/div[2]/ul/li/a")
    print('chapters',chapters)

    titleLink = {}  # 创建一个字典，用于存放每一章节的标题与对应的链接
    for each in chapters:
        title = each.text
        # print('title:',title)
        link = ('https://www.gdwxcn.com/'+ str(each.get('href')))  # 构建完整链接
        # print('link:',link)
        titleLink[title] = link  #将新的标题和链接信息添加到字典
    return titleLink  # 返回目录页获取的章节与连接数据


def getText(url):
    """
        ：用于获取对应的文本信息
    """
    headers = {
        'user-Agent': UserAgent().random
    }
    resp = requests.get(url, headers=headers).content.decode('gbk', errors='ignore')  # 获取相应内容，改变内容编码格式
    # print(resp)
    e = etree.HTML(resp)
    text = e.xpath('/html/body/div[5]/div/div[1]/p/text()')
    print('text:',text)
    return text


def mkdir(path):
    """
        创建文件夹
    """
    folder = os.path.exists(path)
    if not folder:  # 判断是否存在文件夹如果不存在则创建为文件夹
        os.makedirs(path)  # makedirs 创建文件时如果路径不存在会创建这个路径
        print("---  new folder...  ---")
        print("---  OK  ---")
    else:
        print("---  There is this folder!  ---")

def main():
    """
        ：定义函数获取小说
    """
    url = 'https://www.gdwxcn.com/gdxs/xyj/'
    titleLink = getTitleLink(url)
    # print('titlelink', titleLink)

    mkdir("D:\\Users\\Donal\\Documents\\pythonProject\\爬虫\\西游记小说爬取/西游记")  # 创建文件夹
    i = 1
    for title, link in titleLink.items():
        with open('D:\\Users\\Donal\\Documents\\pythonProject\\爬虫\\西游记小说爬取/西游记/'+str(i)+str(title)+'.txt', 'w',encoding='utf-8') as f:
            for text in getText(link):
                f.write(text)
            f.close()
        i += 1
if __name__ == '__main__':
    main()