爬取17K小说网书架内的小说

最新推荐文章于 2024-03-25 11:38:18 发布

loveking001

最新推荐文章于 2024-03-25 11:38:18 发布

阅读量214

点赞数

文章标签： python 爬虫

本文链接：https://blog.csdn.net/loveking001/article/details/133826053

版权

import threading

import requests
from lxml import etree
import os


headers  = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
        }
session = requests.session()
accountNumber = input("请输入你的17K小说网账号：")
password = input("请输入你的登录密码：")
def login():
    session.post("https://passport.17k.com/ck/user/login",data={
                            "loginName": accountNumber,
                            "password": password
                    })


def get_shelf_books():
    '''

    :return:
    '''
    res = session.get("https://user.17k.com/ck/author2/shelf?page=1&appKey=2406394919")
    res.encoding="utf8"
    data = res.json().get("data")
    return data


def get_books(data):

    for bookDict in data:
        # print(bookDict)
        bookID = bookDict.get("bookId")
        bookName = bookDict.get("bookName")
        book_path = os.path.join(root_path,bookName)
        if not os.path.exists(book_path):
            os.mkdir(book_path)
        get_chapter(bookID,book_path,bookName)
def get_chapter(bookID,book_path,bookName):
    res = requests.get(f"https://www.17k.com/list/{bookID}.html")

    res.encoding = "utf8"

    selector = etree.HTML(res.text)
    items = selector.xpath('//dl[@class="Volume"]/dd/a')



    for item in items:
        chapter_href = item.xpath('./@href')[0]
        chapter_title = item.xpath('./span/text()')[0].strip()
        print("chapter_href", chapter_href)
        print("chapter_text", chapter_title)

        res = requests.get("https://www.17k.com" + chapter_href)
        res.encoding = "utf8"
        chapter_html = res.text
        print(chapter_html)
        selector = etree.HTML(res.text)
        chapter_text = selector.xpath('//div[contains(@class,"content")]/div[@class="p"]/p[position()<last()]/text()')
        # ret = selector.xpath('//div[contains(@class,"content")]/div[@class="p"]/p[position()<last()]/text()')
        print(chapter_text)
        download(book_path, chapter_title,chapter_text)

        print(f'{bookName}书籍的{chapter_title}章节已经下载完成')

def download(book_path, chapter_title,chapter_text):
    chapter_path = os.path.join(book_path, chapter_title)
    with open(chapter_path, "w", encoding="utf8") as f:
        for line in chapter_text:
            f.write(line + "\n")

login()
data = get_shelf_books()
root_path = "我的书架"
if  not os.path.exists(root_path):
    os.mkdir(root_path)

get_books(data)