Created
July 22, 2020 08:19
-
-
Save arthur-tomsjj/5873fc9f311783682b1940ff89edb878 to your computer and use it in GitHub Desktop.
i am hentai senshi
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
####### e-hentai本子 爬蟲測試 ####### | |
import urllib.request as req | |
import requests | |
from bs4 import BeautifulSoup | |
import os | |
import time | |
url = 'https://e-hentai.org/s/42331c9fc6/1467036-1' | |
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'} | |
pagenum = 96 #本子總頁數 | |
count = 1 #計算目前存到第幾頁 | |
def crawl(url,count): | |
source = req.Request(url,headers = Header) | |
with req.urlopen(source) as response: | |
data = response.read().decode('utf-8') | |
page = BeautifulSoup(data,"html.parser") | |
div = page.find('div',id='i3') #找出div id為i3 | |
Next_link = div.a['href'] #抓div中的a標籤 提取裡面href的路徑 | |
img = div.a.img['src'] #抓div中的a中的img標籤 提取裡面src的路徑 | |
fname = '爬蟲img/'+str(count)+'.jpg' #檔案儲存路徑+名稱 | |
download = requests.get(img) | |
with open(fname,'wb') as f: | |
f.write(download.content) | |
f.close() | |
del download | |
print('downloaded: '+fname.split('/')[-1]) | |
if(count<pagenum): | |
count+=1 | |
del source | |
crawl(Next_link,count) | |
#開始抓爬 | |
crawl(url,count) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment