Created
July 26, 2020 05:34
-
-
Save arthur-tomsjj/5636d443680f75a7c093126367834a57 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib.request as req | |
import requests | |
from bs4 import BeautifulSoup | |
import os | |
file_path = input("輸入本子要存放的路徑:") | |
Header = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36'} | |
while(1): | |
print() | |
url = input("請輸入nhentai本子的網址:") | |
Nhentai = req.Request(url,headers = Header) | |
with req.urlopen(Nhentai) as response: | |
data = response.read().decode('utf-8') | |
page = BeautifulSoup(data,'html.parser') | |
title = page.find('div',id = 'info') | |
book_name = title.h2.text #本子名,N網經常改這裡的寫法,要注意...若程式出錯,先檢查這裡 | |
temp = '' | |
for _str in book_name: # 去除有?的字元 | |
if _str != '?': | |
temp += _str | |
book_name = temp | |
path = file_path+'\\'+book_name | |
if not os.path.isdir(path): | |
os.mkdir(path) | |
All_page = page.find_all('div',class_ = 'thumb-container') | |
pagenum = len(All_page) | |
print("下載項目: "+book_name) | |
print("總頁數: %d \n"%pagenum) | |
print("開始執行下載:") | |
for index in range(1,pagenum+1): | |
link = url+str(index)+'/' | |
Nhentai = req.Request(link,headers = Header) | |
with req.urlopen(Nhentai) as response: | |
data = response.read().decode('utf-8') | |
page = BeautifulSoup(data,'html.parser') | |
target = page.find('section',id = 'image-container') | |
if target.a.img['src'].find("http") == -1: | |
if url.find('nhentai.to') != -1: | |
img = "https://nhentai.to"+target.a.img['src'] | |
else: | |
img = "https://nhentai.net"+target.a.img['src'] | |
else : | |
img = target.a.img['src'] | |
download = requests.get(img) | |
fname = path+'\\'+img.split('/')[-1] | |
with open(fname,'wb') as f: | |
f.write(download.content) | |
f.close() | |
print("downloaded: "+img.split('/')[-1]) | |
del data | |
del download | |
del page | |
print("\n下載完成......") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment