Nhen*ai.net manga crawler

# I used it to crawl pics from a hentai reading site
# IDK why, but it might be usefull for someone
# as it was very useful for me (Lol)
# use it in moderation, perverts!


from urllib import request as req
import time
import json
import os
import struct
import gzip
import io
import re
import sys

#https://nhentai.net/g/92405/6/  <- this is a link to a random hentai manga gallery, you need to replace the value of gallery with "92405" to exactly download manga from this link

dl = True
session_name = ""
gallery   = "214024" #<- you just need to change this value
#getting title
if True:
                        pagelink = "http://nhentai.net/g/%s"% (gallery)
                        reque = req.Request(pagelink, headers={'Accept-encoding':'gzip','User-Agent': 'Mozilla/5.0'})
                        rawl = req.urlopen(reque)
                        encoding = rawl.headers.get('Content-Encoding')
                        print(encoding)
                        if encoding == None:
                            rawl = str(rawl.read())
                        else:
                            if encoding.upper() == "GZIP":
                                try:
                                    compressedstream = io.BytesIO(rawl.read())
                                    gzipper = gzip.GzipFile(fileobj=compressedstream)
                                    rawl = str(gzipper.read())
                                except Exception as exc:
                                    print(exc)
#                        rawl = str(req.urlopen(pagelink).read())
                        #print(rawl)
                        rawl2 = rawl.split("\n")
                        rawl_list = []
                        for li in rawl2:
                          x = li.split(">")
                          for xx in x:
                            rawl_list.append(xx)
                        #print(rawl_list)
                        title=rawl_list[5].split('content="')
                        title=title[1].split('" /')
                        series=title[0]
                        print(series)

destination = "pig/%s-%s/"%(series,gallery)

def downloop():
  while dl == True:
   try:
    session_name = "%s-%s"%(series,gallery)
    try:
        os.mkdir(destination)
    except:
        pass
    for page in range(1,500):
                checklist = os.listdir(destination)
                if len(str(page)) == 1:
                    pagenum = "00"+str(page)
                if len(str(page)) == 2:
                    pagenum = "0"+str(page)
                if pagenum+".jpg" in checklist:
                        print(pagenum+".jpg Checked.")

                        pass
                if pagenum+".jpg" not in checklist:
                        pagelink = "http://nhentai.net/g/%s/%s"% (gallery, page)
                        reque = req.Request(pagelink, headers={'Accept-encoding':'gzip','User-Agent': 'Mozilla/5.0'})
                        rawl = req.urlopen(reque)
                        encoding = rawl.headers.get('Content-Encoding')
                        print(encoding)
                        if encoding == None:
                            rawl = str(rawl.read())
                        else:
                            if encoding.upper() == "GZIP":
                                try:
                                    compressedstream = io.BytesIO(rawl.read())
                                    gzipper = gzip.GzipFile(fileobj=compressedstream)
                                    rawl = str(gzipper.read())
                                except Exception as exc:
                                    print(exc)
                        rawl2 = rawl.split("\\")
                        rawl_list = []
                        for li in rawl2:
                          x = li.split("t<img ")
                          for xx in x:
                            rawl_list.append(xx)
                        last_list = []
                        for i in rawl_list:
                            if 'src="https://i.nhentai.net/galleries/' in i:
                                last_list.append(i)
                        last_link = last_list[0].split('"')
                        last = last_link[1]
                        print(last)
                        req.urlretrieve(last, "%s%s.jpg"%(destination, pagenum))
                        print(pagenum+".jpg is done")
   except Exception as ex:
         print(ex)
         print(series)
         break
downloop()
print(session_name + " Done.")