【新人勿喷】实现某小说网小说全下载
初学python，果然，我对于编程一无所知，本以为相当简单的我不料竟一脚踩进这么大一个坑，不过不得不说，真香~
好了，不多说废话，源码奉上~~
import os
import requests
from lxml import etree
from docx import Document
from urllib import parse
from pyquery import PyQuery as pq
from bs4 import BeautifulSoup
import time
from tkinter import *
from tkinter import messagebox
# 代码
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'}
# 查询小说
def search_book():
url = 'http://www.xbiquge.la/modules/article/waps.php?searchkey='
book_name = entry1.get()
# 对输入的字符进行编码转换为gbk编码,再对其进行url编码操作
book_name = parse.quote(book_name.encode('utf-8'))
book_url = url + book_name
# print(book_url)
return book_url
# # 判断是否有书，并提示是否下载
def find_book(book_url):
# 调用查找search_book()函数 查找跳转至相应界面
url = book_url
# 请求页面
html = requests.get(url, headers)
root = etree.HTML(html.content.decode('UTF-8'))
# print(root)
if(root.xpath('//*[@id="checkform"]/table/tr/td/a/@href') == []):
text1.insert(END, '搜索的书不存在，请正确输入书名')
text1.see(END)
text1.update()
else:
# print('找到了作者为', root.xpath('//div[@class="search-list"]/ul/li/span[@class="s4"]/text()'),
# ',书名为《', root.xpath('//div[@class="search-list"]/ul/li/span/a/text()'), '》,请问是否下载'
# , end='')
text1.insert(END, '找到作品《' + str(root.xpath('//*[@id="checkform"]/table/tr/td/a/text()')) + '》，作者为 ' + str(root.xpath('//*[@id="checkform"]/table/tr/td/text()')) + ' ,仔细看一下哦!请问是否下载?')
text1.see(END)
text1.update()
text1.insert(END, )
text1.see(END)
text1.update()
def download(book_url):
# 调用查找search_book()函数 查找跳转至相应界面
url = book_url
# 请求页面
html = requests.get(url, headers)
root = etree.HTML(html.content.decode('UTF-8'))
# print(root)
if (root.xpath('//*[@id="checkform"]/table/tr/td/a/@href') != []):
text1.insert(END, '开始下载！')
text1.see(END)
text1.update()
path = "下载"
if not os.path.exists(path):
os.mkdir(path)
book_content_list(root.xpath('//*[@id="checkform"]/table/tr/td/a/@href'))
# 获取目录的URL 并调用download_book()函数下载内容
def book_content_list(url):
html = requests.get(url, headers)
root = etree.HTML(html.content)
# 获取目录的URL 并传入download_book()函数
s_list = root.xpath('//*[@id="list"]/dl/dd/a/@href')
for dd_url in s_list:
download_book('http://www.xbiquge.la' + str(dd_url))
# print('content_url:' + 'http://www.xbiquge.la' + str(dd_url))
def download_book(url):
try:
response = requests.get(url, headers=headers)# 提取目录
response.encoding = response.apparent_encoding# 解决乱码问题
# print(response.text) #输出
doc = pq(response.text)# 解决pyquer对象
title = doc('#wrapper > div.content_read > div > div.bookname > h1').text()
content = doc('#content').text()# 提取内容
global is_pause
is_pause = True
if is_pause:
text1.insert(END, title)
text1.see(END)
text1.update()
# print(content)
time.sleep(1)# 反爬3：隔1s爬取一章
else:
root.destroy()
with open('下载/{}.txt'.format(entry1.get()), 'a+', encoding='utf-8') as f:
f.write(title)
f.write("\n\n")# 使各章分隔开
f.write(content)
f.write("\n\n")# 使各章分隔开
except:
pass
def button2_even():
if entry1.get() != '':
book_url = search_book()
find_book(book_url)
def download1():
try:
global is_pause
is_pause = True
if is_pause:
book_url = search_book()
download(book_url)
else:
time.sleep(500)
except:
pass
# def is_pause():
# global is_pause
# is_pause = not is_pause
# if not is_pause:
# pauseBut["text"] = "继续"
# else:
# pauseBut["text"] = "暂停"
def is_quit():
ask_quit = messagebox.askquestion("退出程序", "您确定要退出程序并结束下载吗？")
if ask_quit == 'yes':
root.destroy()
exit()
#界面
root = Tk()
root.title('XX小说下载器')
root.geometry('550x400+400+200')
label1 = Label(root, text="搜 索：", font=('楷体', 15))
label1.place(x=65, y=30)
entry1 = Entry(root, font=('楷体', 15))
entry1.place(x=170, y=30)
# label2 = Label(root, text="确认下载：", font=('楷体',15))
# label2.place(x=60, y=40)
# entry2 = Entry(root, font=('楷体', 15))
# entry2.place(x=170, y=40)
# label3 = Label(root, text="（输入小说名称确认下载）", font=('楷体', 10), fg='red')
# label3.place(x=375, y=43)
text1 = Listbox(root, font=('楷体') ,background='#aaa')
text1.place(x=10, y=80, relwidth=0.95, relheight=0.65)
xscrollbar = Scrollbar(text1, command=text1.xview, orient=HORIZONTAL)
xscrollbar.pack(side=BOTTOM, fill=X)
yscrollbar = Scrollbar(text1, command=text1.yview)
yscrollbar.pack(side=RIGHT, fill=Y)
text1.config(yscrollcommand=yscrollbar.set)
text1.config(xscrollcommand=xscrollbar.set)
button1 = Button(root, text="确定", font=('楷体', 10), bd=4 ,activeforeground='#000', activebackground='#ace', highlightcolor="#ddd", command=button2_even)# relief,边框样式，设置控件3D效果，可选的有：FLAT、SUNKEN、RAISED、GROOVE、RIDGE。默认为 FLAT。
button1.place(x=400, y=28)
button2 = Button(root, text="下载", font=('楷体', 15), bd=4 ,activeforeground='#000', activebackground='#ace', highlightcolor="#ddd", command=download1)
button2.place(x=100, y=350)
# pauseBut = Button(root, text="暂停", font=('楷体', 15), bd=4 ,activeforeground='#000', activebackground='#ace', highlightcolor="#ddd",command=is_pause)
# pauseBut.place(x=250, y=350)
button4 = Button(root, text="退出", font=('楷体', 15), bd=4 ,activeforeground='#000', activebackground='#ace', highlightcolor="#ddd",command=is_quit)
button4.place(x=400, y=350)
root.mainloop()
大家有兴趣的看看就可以，本人小白一只，也写不出多复杂的东西。另外想问一句有哪位大佬可以指点一下怎么实现暂停功能呢{:1_919:}{:1_919:}{:1_919:} 支持发帖。 界面用的是什么模块？ 学习一下，感谢分享 不错啊，学以致用，就是强 青衫桑 发表于 2020-7-24 12:24
界面用的是什么模块？
tkinter，python内置GUI模块儿 shojnhv 发表于 2020-7-24 19:12
tkinter，python内置GUI模块儿
模块儿很精髓 这个可以有。我回去试试。。。 青衫桑 发表于 2020-7-24 12:24
界面用的是什么模块？
应该是TK 这个厉害，给你点个赞。谢谢分享
页:
[1]
2