好友 阅读权限 10
听众 最后登录 1970-1-1
本帖最后由 fff123123 于 2023-11-3 22:07 编辑 confirmation_search from bin.tk_ui import MyAppdef main ():if __name__ == '__main__' :from tkinter import *from tkinter import ttk, messageboximport tkinter.font as tffrom . import requestutilsclass MyApp(Tk):""" 继承 Tk ，创建自己的桌面应用程序类 """ def __init__ (self ):""" 构造函数 """ super ().__init__ ()self .title('Frame' )# self.iconbitmap('./bin/Tk.ico') self .geometry('800x500' )# self.resizable(width=False, height=False) # 阻止 Python GUI 的大小调整 # 底界面 self .frame = Frame(self , bg ='#90c0c0' )self .frame.pack(expand =True, fill =BOTH)self .frame2 = Frame(self .frame) # 界面 1 self .frame3 = Frame(self .frame) # 界面 2 self .frame4 = Frame(self .frame) # 界面 3 self .current_page = self .frame2self .init_ui()def init_ui (self ):""" 初始化界面 """ # 书籍存储搜索结果的二维列表 self .result = list ()# 章节存储搜索结果的二维列表 self .result2 = list ()# 章节内容存储搜索结果的二维列表 self .result3 = list ()# 设置字体 ft = tf.Font(family =" 微软雅黑 " , size =10 )# frame1 是 frame 的第 1 个子控件，从左向右布局 , 按钮所在的控件 frame1 = Frame(self .frame, bg ='#f0f0f0' )side =LEFT)# 3 个 Button 是 frame2 的子控件，自上而下布局 Button(frame1, text =' 书架 ' , width =10 , command =self .first_page).pack(padx =5 , pady =5 ) # 切换为界面 1 Button(frame1, text =' 搜索 ' , width =10 , command =self .second_page).pack(padx =5 , pady =5 ) # 切换为界面 2 Button(frame1, text =' 阅读 ' , width =10 , command =self .third_page).pack(padx =5 , pady =5 ) # 切换为界面 3 # 第一个界面 ui Label(self .frame2, text =' 界面 1' , bg ='#90c0c0' ).grid(row =1 , column =1 , padx =10 , pady =10 )# 第二个界面 ui # 顶部单独的一个 frame frame2_1 = Frame(self .frame3, bg ='#90c0c0' )side =TOP, fill ="x" )self .combo_source_book = ttk.Combobox(frame2_1, values =(" 全本免费小说 " , " 某点中文网 " ), state ='readonly' )self .combo_source_book.current(1 ) # 选择第一个 self .combo_source_book.grid(row =0 , column =1 , padx =2 , pady =2 , sticky ="nsew" )self .entry_book_name = Entry(frame2_1, width =30 )self .entry_book_name.grid(row =0 , column =2 , padx =2 , pady =2 , sticky ="nsew" ) # 书名获得 Button(frame2_1, text =' 确认 ' , width =12 , command =self .confirmation_search). \row =0 , column =3 , padx =2 , pady =2 , sticky ="nsew" ) # 搜索确认键 # 设置行和列的权重 frame2_1.grid_rowconfigure(0 , weight =1 )0 , weight =1 )1 , weight =2 )2 , weight =1 )# 搜索结果显示 self .lb_books_name = Listbox(self .frame3)self .lb_books_name.pack(expand =True, side =TOP, fill =BOTH, padx =5 , pady =5 )# 绑定双点击函数 获取具体章节 内容 self .lb_books_name.bind("<Double-Button-1>" , lambda event: self .get_book(self .lb_books_name.curselection()))# 绑定单击函数 提示具体信息 self .lb_books_name.bind("<<ListboxSelect>>" , lambda event: self .get_book_introduce(self .lb_books_name.curselection()))# 底部 书籍具体信息显示 # 创建文本框 self .book_introduce = Text(self .frame3, height =1 )self .book_introduce.pack(expand =True, side =TOP, fill =BOTH, padx =5 , pady =5 )# 第三个界面 ui frame3_1 = Frame(self .frame4, bg ='#90c0c0' )row =0 , column =0 , padx =2 , pady =2 , sticky ="nsew" )self .frame4, bg ='#90c0c0' )row =1 , column =0 , padx =2 , pady =2 , sticky ="nsew" )self .frame4.grid_columnconfigure(0 , weight =1 )self .frame4.grid_rowconfigure(0 , weight =1 )self .frame4.grid_rowconfigure(1 , weight =25 )# 第一个 frame self .frame3_1_name = StringVar() # 获取书名 Label(frame3_1, textvariable =self .frame3_1_name).grid(row =0 , column =0 , padx =2 , pady =2 , sticky ="nsew" ), text =" 上一章 " ).grid(row =0 , column =1 , padx =2 , pady =2 , sticky ="nsew" ), text =' 下一章 ' ).grid(row =0 , column =2 , padx =2 , pady =2 , sticky ="nsew" )# 设置行和列的权重 frame3_1.grid_rowconfigure(0 , weight =1 )0 , weight =3 )1 , weight =1 )2 , weight =1 )# 第二个 frame self .lb_chapter_name = Listbox(frame3_2)# 绑定双点击函数 获取具体章节 内容 self .lb_chapter_name.bind("<Double-Button-1>" , lambda event: self .get_chapter_content(self .lb_chapter_name.curselection()))# 多行文本 self .lb_chapter_info = Text(frame3_2, font =ft)self .lb_chapter_name.grid(row =0 , column =0 , padx =2 , sticky ="nsew" )self .lb_chapter_info.grid(row =0 , column =1 , padx =2 , sticky ="nsew" )# 设置行和列的权重 frame3_2.grid_rowconfigure(0 , weight =1 )0 , weight =1 )1 , weight =5 )# 默认显示界面 1 ，并记录当前界面 self .current_page.pack(expand =True, side =LEFT, fill =BOTH, padx =5 , pady =5 )# 书籍搜索确认键 def confirmation_search (self ):self .combo_source_book.current() # 书源 print (" 第 " + str (s1) + " 个书源 " )self .entry_book_name.get() # 书名 # 检查 清除 listbox 框内的内容 numble = self .lb_books_name.size()if numble != 0 :self .lb_books_name.delete(0 , END)if s2 != "" :# 根据书源搜索书 self .result = requestutils.requests_util(s2, s1, 0 )if self .result3 != '' :self .lb_books_name.insert(END, " 成功 " )else :self .lb_books_name.insert(END, " 失败 " )print (self .result)# 把搜索结果显示在 listbox 上 for item in self .result:self .lb_books_name.insert(END, item[0 ] + "----" + item[1 ] + " \n\n " )else :# 提示没有输入书名 messagebox.showinfo(' 提示 ' , ' 没有输入书名 ' )# 具体书籍 url 获取具体章节信息 章节内容 def get_book (self , index):# 设置阅读界面的书名 s = self .entry_book_name.get() # 书名 self .frame3_1_name.set(s)# 跳转到阅读界面 self .third_page()for i in index:# 获取书的 url # 获取书籍内容 / 获取章节内容 s = self .result[-1 ]# 网络请求获取章节信息 s1 = self .combo_source_book.current() # 书源 # 检查 清除 listbox 框内的内容 # 根据书源搜索具体书籍 self .result2 = requestutils.requests_util(s, s1, 1 )print (self .result2)# 清除阅读界面的章节数据 self .lb_chapter_name.delete(0 , END)# 设置阅读界面的章节数据 for item in self .result2:# 添加章节名 self .lb_chapter_name.insert(END, item[0 ])break # 获取章节内容 def get_chapter_content (self , index):for i in index:# 获取书的 url url = self .result2[-1 ]# 网络请求获取章节信息 s1 = self .combo_source_book.current() # 书源 # 检查 清除 listbox 框内的内容 # 根据书源搜索具体书籍 self .result3 = requestutils.requests_util(url, -1 , 2 )print (type (self .result3))self .lb_chapter_info.delete(1.0 , END)self .lb_chapter_info.insert(END, self .result3)# 获取书籍介绍 def get_book_introduce (self , index):print (index)for i in index:# 显示书籍具体信息 self .book_introduce.config(state =NORMAL)# 清除内容 self .book_introduce.delete("1.0" , END)self .book_introduce.insert("0.0" , self .result[0 ] + " " + self .result[1 ] + " \n\n " + self .result[2 ])self .book_introduce.config(state =DISABLED)break # 跳转到第一个 ui def first_page (self ):if self .current_page != self .frame2:self .current_page.pack_forget() # 取消显示当前界面，并不是销毁 self .current_page = self .frame2self .current_page.pack(expand =True, side =LEFT, fill =BOTH, padx =5 , pady =5 ) # 显示界面 1 # 跳转到第二个 ui def second_page (self ):if self .current_page != self .frame3:self .current_page.pack_forget() # 取消显示当前界面，并不是销毁 self .current_page = self .frame3self .current_page.pack(expand =True, side =LEFT, fill =BOTH, padx =5 , pady =5 ) # 显示界面 2 # 跳转到第三个 ui def third_page (self ):if self .current_page != self .frame4:self .current_page.pack_forget() # 取消显示当前界面，并不是销毁 self .current_page = self .frame4self .current_page.pack(expand =True, side =LEFT, fill =BOTH, padx =5 , pady =5 ) # 显示界面 3 import jsonimport randomimport timeimport requestsfrom bs4 import BeautifulSoupfrom lxml import etree# 随机返回请求头 user_agent def getheader ():"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 " "Safari/537.36 Edg/117.0.2045.47" , "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36" , "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" ]return random.choice(user_agent_list)# 读取 json 文件 def getMovieUrl ():with open ("./bin/yuan.json" , "r" , encoding ='utf-8' ) as file:return link# 普通网络请求 书名 / 完整书 url 书源选择 (0/1) 搜索书 (0)/ 搜索书的具体信息 (1) def requests_util (search, book_source_item, coeffcient):# ip 代{过}{滤}理 proxy = {"http" : "117.186.232.73:8080" }1 # 读取 json 文件 item = getMovieUrl()# 存储搜索结果的二维列表 result = list ()# 网络请求准备 name = item["bookSourceName" ]"bookSourceUrl" ]"search_url" ]"chapter_search_url" ]"headers" ]"rules" ]"rules_chapter" ]'User-Agent' ] = getheader()# 搜索书 if coeffcient == 0 :# 需要拼接 search_url += searchprint (" 书源名 " + name, " 书源网站 " + url, " 搜索网址 " + search_url)url =search_url, headers =headers, proxies =proxy, timeout =20 )# 搜索具体书籍 章节 elif coeffcient == 1 :print (" 书源名 " + name, " 书源网站 " + url, " 搜索网址 " + search)url =search, headers =headers, proxies =proxy, timeout =20 )# 搜索具体内容 elif coeffcient == 2 :print (name, " 搜索网址 " + search)url =search, headers =headers, proxies =proxy, timeout =20 )1 )# response.encoding = response.apparent_encoding # 设置编码，防止由于编码问题导致文字错乱 # print(response.text) # 查看请求到的内容 content = response.content.decode("utf-8" ), "html.parser" )# print(soup.text) if coeffcient == 0 :print (" 搜索书籍 " )# 打印筛选结果 t1 = rules["basics" ]"book_name" ]"book_author" ]"info" ]"url_part" ]# print(elements) for element in elements:# 基本信息 s = list ()print (" 具体文本信息：书名 作者 介绍 " )# url 信息 url_part = element.select_one(t5).get("href" )"book" )[-1 ]print (" 分割后字符串 " + spilt_after_url)# 设置只保持 10 个搜索的结果 if len (result) > 10 :break # print(result) return resultelif coeffcient == 1 :print (" 搜索章节 " )# 返回 章节名 章节 url t1 = rules_chapter["basics" ]"part1" ]# print(elements) for element in elements:for chapter in chapters:list ()"href" )# 找有没有前缀 没有 有前缀 删掉 com 之前的内容 if "com" in part_url:"com" , 1 )[-1 ]else :# print(name) # print(url) s.append(name)return resultelif coeffcient == 2 :print (" 搜索章节内容 " )# 创建一个 XPath 解析器 parser = etree.HTMLParser(), parser =parser)# search 为 url # 某点的规则 find(www.qidian.com) if "www.qidian.com" in search:# 使用 XPath 选择器筛选页面数据 # 创建一个 XPath 解析器 parser = etree.HTMLParser(), parser =parser)# 使用 XPath 选择器筛选页面数据 script_element = tree.xpath('//script[@id="vite-plugin-ssr_pageContext"]/text()' )0 ].strip()'pageContext' ]['pageProps' ]['pageData' ]['chapterInfo' ]['content' ].replace("<p>" , " \n " )print (value)return value# 全本的规则 elif "www.qbmfxs.com" in search:# 使用 XPath 选择器筛选页面数据 str value = tree.xpath("/html/body/div[4]/div/div[1]/div[3]//p/text()" )print (value)return value
发表于 2023-11-3 19:26
|
发表于 2023-11-3 19:27
