首页 / PYTHON / Python爬漫画(GUI)
Python爬漫画(GUI)
内容导读
互联网集市收集整理的这篇技术教程文章主要介绍了Python爬漫画(GUI),小编现在分享给大家,供广大互联网技能从业者学习和参考。文章包含7355字,纯文字阅读大概需要11分钟。
内容图文
![Python爬漫画(GUI)](/upload/InfoBanner/zyjiaocheng/645/3bfe81f818d14747a9fdfa9f733c10ca.jpg)
技术无罪,仅供学习
最近闲来无事看漫画,上网找了一堆漫画网站看漫画,懒得一个个找,就写了这个脚本(当然GUI版本花我4天时间。。),当然我自己也是在看正版漫画的bilibili和腾讯动漫的。
无GUI版本
#getComic.py
import requests,re,time,os,threading,sys
from bs4 import BeautifulSoup
header={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36 Edg/79.0.309.63'}
class bnComic:
def __init__(self):
self.comicDict={}
self.url='https://m.bnmanhua.com'
self.kw=input('请输入要下载的漫画:')
self.comicUrl=self.searchComic(self.kw)
self.pageList=self.returnPage(self.comicUrl)
def searchComic(self,kw):
r=requests.post(self.url+'/index.php?m=vod-search',{'wd':self.kw})
comic=re.search('<a class=\"vbox_t\" href=\"(.*)\" title=\"(.*)\">',r.text)
r.close()
self.filename=comic.group(2)
if not comic:
raise Exception('没有'+self.kw+'漫画,请检查漫画名称')
return self.url+comic.group(1)
def returnPage(self,u):
r=requests.get(u)
soup=BeautifulSoup(r.text,'html.parser')
r.close()
if soup.body.font:
raise Exception(self.kw+'漫画受版权限制,禁止下载')
return [self.url+x.attrs['href'] for x in soup.ul.find_all('a')]
def picDict(self,u):
r=requests.get(u,headers=header)
soup=BeautifulSoup(r.text,'html.parser')
b=re.findall(r'\[(.*)\]',soup.body.script.string.split(';')[1])
if 'https:' in re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(','):
self.comicDict[soup.title.text.split('-')[1]]=re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(',')
else:
self.comicDict[soup.title.text.split('-')[1]]=['https://img.yaoyaoliao.com/'+x for x in re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(',')]
r.close()
def saveComic(self,part):
c=0
os.mkdir('.\\'+self.kw+'\\'+part[0])
for pic in part[1]:
c+=1
r=requests.get(pic)
if pic[-1]=='0':
f=open('.\\'+self.kw+'\\'+part[0]+'\\'+str(c)+'.png','wb')
f.write(r.content)
r.close()
f.close()
else:
f=open('.\\'+self.kw+'\\'+part[0]+'\\'+str(c)+'.jpg','wb')
f.write(r.content)
r.close()
f.close()
return
def run(self):
try:
for page in self.pageList:
t=threading.Thread(target=self.picDict,args=(page,))
t.setDaemon(1)
t.start()
print('正在下载')
os.mkdir(self.filename)
for part in self.comicDict.items():
t=threading.Thread(target=self.saveComic,args=(part,))
t.setDaemon(1)
t.start()
print('下载完成')
except Exception as e:
print(e)
manhua=bnComic()
manhua.run()
有GUI版本
import requests,re,time,os,threading,sys,tkinter
from tkinter import ttk,messagebox,filedialog
from bs4 import BeautifulSoup
url='https://m.bnmanhua.com'
class bnComic(tkinter.Tk):
def __init__(self):
super().__init__()
self.comicDict={}
self.pageList=[]
self.urlData={}
self.title('漫画下载')
self.geometry('960x525')
self.resizable(0,0)
self.createUI()
def createUI(self):
self.topFrame=tkinter.Frame(self)
self.topFrame.pack(fill='x',side='top')
self.middleFrame=tkinter.Frame(self)
self.middleFrame.pack(fill='x')
self.scrollbar=tkinter.Scrollbar(self.middleFrame)
self.bottomFrame=tkinter.Frame(self)
self.bottomFrame.pack(fill='x',side='bottom')
self.pageBox=tkinter.Listbox(self.middleFrame,selectmode=tkinter.EXTENDED,height=26,width=65)
self.pageBox.pack(side=tkinter.LEFT)
self.scrollbar.pack(side='left',fill='y')
self.pageBox['yscrollcommand']=self.scrollbar.set
self.scrollbar['command']=self.pageBox.yview
self.kwEntry=tkinter.Entry(self.topFrame)
self.kwEntry.grid(row=0,column=1)
self.l1=tkinter.Label(self.topFrame,text='关键字:').grid(row=0,column=0)
self.l2=tkinter.Label(self.topFrame,text='搜索结果:').grid(row=0,column=3)
self.searchButton=tkinter.Button(self.topFrame,text='搜索',command=lambda:self.runthread(self.searchComic,self.kwEntry.get())).grid(row=0,column=2)
self.downButton=tkinter.Button(self.topFrame,text='下载所有',command=lambda:self.runthread(self.saveComic,self.comicDict)).grid(row=0,column=5)
self.comicList=ttk.Combobox(self.topFrame,height=8,width=40)
self.comicList.grid(row=0,column=4)
self.comicList.bind("<<ComboboxSelected>>",lambda x:self.runthread(self.returnPage,self.urlData[self.comicList.get()]))
self.progress=ttk.Progressbar(self.bottomFrame,length=100,maximum=100.0)
self.progress.pack(side=tkinter.RIGHT)
self.l3=tkinter.Label(self.bottomFrame)
self.l3.pack(side=tkinter.RIGHT)
def searchComic(self,kw):
self.l3['text']='正在搜索关键字'
self.progress['value']=0.0
self.comicList.set('')
self.comicList['values']=''
self.urlData={}
r=requests.post(url+'/index.php?m=vod-search-pg-1-wd-'+kw+'.html')
soup=BeautifulSoup(r.text,'html.parser')
if not soup.find_all(name='li',attrs={'class':'vbox'}):
self.progress['value']=0.0
self.l3['text']=''
raise messagebox.showerror('ERROR','无此漫画,请检查漫画名称')
v=int(soup.body.find_all(name='em',attrs={'class':'num'})[0].string.split('/')[1])+1
for p in range(1,v):
r=requests.post(url+'/index.php?m=vod-search-pg-'+str(p)+'-wd-'+kw+'.html')
soup=BeautifulSoup(r.text,'html.parser')
pageNumList=soup.find_all(name='li',attrs={'class':'vbox'})
for x in pageNumList:
self.progress['value']+=100/(len(pageNumList)*(v-1))
self.urlData[x.a['title']]=url+x.a['href']
self.comicList['values']=[x[0] for x in dict(sorted(self.urlData.items(),key=lambda d:d[1],reverse=True)).items()]
time.sleep(0.1)
self.l3['text']=''
self.progress['value']=0.0
def returnPage(self,u):
global ff
self.comicDict={}
self.progress['value']=0.0
self.l3['text']='正在返回章节'
self.pageBox.delete(0,tkinter.END)
r=requests.get(u)
soup=BeautifulSoup(r.text,'html.parser')
r.close()
if soup.body.font:
self.progress['value']=0.0
self.l3['text']=''
raise messagebox.showerror('ERROR','漫画受版权限制,禁止下载')
self.pageList=[url+x.attrs['href']+'-'+x.string for x in soup.ul.find_all('a')]
ff=len(self.pageList)
for l in self.pageList:
self.pageBox.insert(tkinter.END,l)
t=threading.Thread(target=self.picDict,args=(l,))
self.progress['value']+=100/ff
t.start()
self.progress['value']=0.0
self.l3['text']=''
def picDict(self,u):
r=requests.get(u.split('-')[0])
soup=BeautifulSoup(r.text,'html.parser')
b=re.findall(r'\[(.*)\]',soup.body.script.string.split(';')[1])
if 'https:' in re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(','):
self.comicDict[soup.title.text.split('-')[1]]=re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(',')
else:
self.comicDict[soup.title.text.split('-')[1]]=['https://img.yaoyaoliao.com/'+x for x in re.sub('\"','',eval(re.sub(r'\\','',repr(b[0])))).split(',')]
r.close()
def saveComic(self,part):
self.l3['text']='正在下载漫画'
global ff,path
c=0
if path=='':
self.l3['text']=''
raise messagebox.showerror('ERROR','下载文件路径不能为空')
os.mkdir(path+'\\'+part[0])
for pic in part[1]:
self.progress['value']+=100/(len(part)*(ff))
c+=1
r=requests.get(pic)
if pic[-1]=='0':
f=open(path+'\\'+part[0]+'\\'+str(c)+'.png','wb')
f.write(r.content)
r.close()
f.close()
f=open(path+'\\'+part[0]+'\\'+str(c)+'.jpg','wb')
f.write(r.content)
r.close()
f.close()
@staticmethod
def runthread(func, args):
global ff,path
try:
if type(args)==type({}):
path=filedialog.askdirectory()
ff=len(args)
for arg in args.items():
t=threading.Thread(target=func,args=(arg,))
t.setDaemon(1)
t.start()
time.sleep(5)
self.l3['text']=''
self.progress['value']=0.0
elif type(args)==type([]):
ff=len(args)
for arg in args:
t=threading.Thread(target=func,args=(arg,))
t.setDaemon(1)
t.start()
self.l3['text']=''
self.progress['value']=0.0
else:
t=threading.Thread(target=func,args=(args,))
t.setDaemon(1)
t.start()
except:
pass
manhua=bnComic()
manhua.mainloop()
锁扣
发布了1 篇原创文章 · 获赞 0 · 访问量 13
私信
关注
内容总结
以上是互联网集市为您收集整理的Python爬漫画(GUI)全部内容,希望文章能够帮你解决Python爬漫画(GUI)所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错,欢迎将互联网集市网站推荐给程序员好友。
内容备注
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 gblab@vip.qq.com 举报,一经查实,本站将立刻删除。
内容手机端
扫描二维码推送至手机访问。