Python爬虫实现下载全本漫画

使用教程

1. 源码方式
   1). 打开Main.py，运行程序。
   2). 按照提示输入存储路径和漫画名称。路径用"/","","\" 做分隔符都行，代码中都将"“替换成”/"。

   

       path = input("请输入存储路径:\n").replace("\\","/")
   

   3). 选择要下载的漫画,然后等待下载就行。
   

   4). 下载结果显示，程序是从最新章节开始下载的，下载完成程序会自动关闭。
   

2. 可执行文件方式
   1). 打开Main.exe，按照提示操作。

注意事项

1. 本项目仅用于学习与交流，请勿用于其他用途。
2. 会出现单个章节下载不全的情况，这是下载源的问题。
3. 可执行文件在win7 x64和win10 x64上测试可以正常运行。
4. 项目没有使用多线程，所以下载速度较慢。

下载地址

1. 源码下载地址
   1). gitee: https://gitee.com/zy888888/spider
   2). 文末。
2. 可执行文件下载地址
   1). 百度云链接：https://pan.baidu.com/s/1rqTcuPrWem__Io0_pstjbQ 提取码：mp0u
   2). 在线下载: https://zhouyun.site/Main.exe

import requests
import lxml.html
import os
import re

class Api():
    # 搜索漫画
    # keywords: 漫画名字
    SEARCH_URL = "https://m.wuxiamh.com/search/?keywords={0}"

    # 下载路径
    FILE_PATH = "{0}/{1}/{2}"

class Book():
    def __init__(self, book_name, author, url):
        self._book_name = book_name
        self._author = author
        self._url = url

    @property
    def book_name(self):
        return self._book_name

    @book_name.setter
    def book_name(self, book_name):
        self._book_name = book_name

    @property
    def author(self):
        return self._author

    @author.setter
    def author(self, author):
        self._author = author

    @property
    def url(self):
        return self._url

    @url.setter
    def url(self, url):
        self._url = url

    @property
    def type(self):
        return self._type

    @type.setter
    def type(self, type):
        self._type = type

    @property
    def date(self):
        return self._date

    @date.setter
    def date(self, date):
        self._date = date

    @property
    def description(self):
        return self._description

    @description.setter
    def description(self, description):
        self._description = description

    def __str__(self) -> str:
        return "{书名: %s , 作者: %s , 链接: %s,  类型: %s, 日期: %s, 简介: %s}" % (
        self.book_name, self.author, self.url, self.type, self.date, self.description)

class Cartoon():
    def get_html(self, url):
        """
        获取html源码
        :param url: 需要获取的url
        :return:   html源码
        """
        if url != None and url != "":
            response = requests.get(url)
            if response.status_code == 200:
                html = response.text
            return html
        else:
            raise Exception("请输入正确的链接")

    def search(self, keywords):
        """
        搜索漫画
        :param keywords: 漫画名称
        :return:    html页面
        """
        url = Api.SEARCH_URL.format(keywords)
        html = self.get_html(url)
        return html

    def search_result(self, html):
        """
        搜索结果处理
        :param html: html页面
        :return: book对象
        """
        selector = lxml.html.fromstring(html)
        info = selector.xpath("//div[@class='Sub_H2 classify']/span/text()")
        result_num = int(re.findall("搜索结果，共(\\d*)条", info[0], flags=0)[0])
        print("搜索结果，共{0}条".format(result_num))
        if result_num == 0:
            raise Exception("搜索结果为0，请重新搜索")

        # 搜索结果url
        update_list = selector.xpath("//div[@id='update_list']/div/div/div[@class='itemTxt']")
        book_list = []
        for itemTxt in update_list:
            # 搜索结果
            book_name = itemTxt.xpath("a/text()")[0]
            author = itemTxt.xpath("p[1]/text()")[0]
            url = itemTxt.xpath("a/@href")[0]
            type = itemTxt.xpath("p[2]/span[2]/text()")[0]
            date = itemTxt.xpath("p[3]/span[2]/text()")[0]

            book = Book(book_name, author, url)
            book.type = type
            book.date = date
            book.description = ""
            book_list.append(book)
        i = 0
        while i < result_num:
            print("结果" , i + 1, ": ", book_list[i])
            i += 1
        # 10次输入机会，10次都错退出程序
        for i in range(10):
            result = int(input("请选择结果:\n"))
            # 越界检查
            if result > 0 and result <= result_num:
                # 返回选择的book对象

                return book_list[result - 1]
            else:
                print("请输入正确的结果")

    def chapeter(self, book):
        """
        获取所有章节
        :param book: book对象
        :return: 章节列表
        """
        html = self.get_html(book.url)
        selector = lxml.html.fromstring(html)
        book.description = selector.xpath("//div[@class='comic-view clearfix']/p/text()")[0]
        # 打印书名
        print(book)
        li = selector.xpath("//div[@class='list']/ul/li")
        chapter_dict = {}
        for i in li:
            # 章节名称
            links = "https://m.wuxiamh.com" + i.xpath("a/@href")[0]
            chapter_name = i.xpath("a/span/text()")[0]
            chapter_dict[chapter_name] = links
        new_chapter_dict = self.filter(book.book_name ,chapter_dict)
        return new_chapter_dict

    def filter(self, book_name, chapter_dict):
        """
        过滤无效链接
        :param book_name: 名称
        :param chapter_dict: 章节字典
        :return: 过滤后的新章节字典
        """
        new_chapter_dict = {}
        for chapter in chapter_dict.keys():
            html = self.get_html(chapter_dict[chapter])
            selector = lxml.html.fromstring(html)
            mip_img = selector.xpath("//div[@class='UnderPage']/div[@class='UnderPage']/mip-link/mip-img[1]/@src")
            if len(mip_img) > 0:
                webp = mip_img[0]
                response = requests.get(webp)
                if response.status_code == 200:
                    new_chapter_dict[chapter] = webp
                else:
                    print("异常链接: " + webp)
            else:
                print("尊敬的各位喜爱{0}漫画的用户，本站应《{0}》版权方要求现已屏蔽删除本漫画所有章节链接，只保留作品文字信息简介以及章节目录，请喜欢{0}的漫友购买杂志或到官网付费欣赏。为此给各位漫友带来的不便，敬请谅解！".format(book_name))
                raise Exception("没有版权，无法下载")
        return new_chapter_dict

    def download(self, book_name, chapter_dict):
        """
        下载
        :param book_name: 书名
        :param chapter_dict: 章节字典
        :return:
        """
        for chapter in chapter_dict.keys():
            file_name = Api.FILE_PATH.format(book_name, chapter)
            # 目录不存在就创建
            if os.path.exists(file_name) == False:
                os.makedirs(file_name)
            url = chapter_dict[chapter][0:-6]
            i = 0
            while True:
                print("download url: " + url + "{0}.webp".format(i))
                response = requests.get(url + "{0}.webp".format(i))
                status_code = response.status_code
                if status_code == 200:
                    with open(file_name + "/{0}.jpg".format(i), "wb") as f:
                        f.write(response.content)
                elif status_code == 404:
                    break
                i += 1



if __name__ == "__main__":
    cartoon = Cartoon()
    path = input("请输入存储路径:\n").replace("\\","/")
    Api.FILE_PATH = path + "/{0}/{1}"
    book_name = input("请输入要搜索的漫画名称:\n")
    try:
        html = cartoon.search(book_name)
        book = cartoon.search_result(html)
        chapter_dict = cartoon.chapeter(book)
        cartoon.download(book.book_name, chapter_dict)
    except Exception as e:
        print(e)