#!/usr/bin/env python3

import os
import requests
import time
import sys
import re
import imghdr
import unicodedata
from bs4 import BeautifulSoup

class BadStatus(Exception):
    '''Exception for when http status is not 200. Takes the status as required input.'''
    def __init__(self, status):
        self.status = status

    def __str__(self):
        return repr(self.status)


def GetGallery(gallery_url): #Takes url string
    fail = 0
    while fail < 3:
        try:
            r = s.get(gallery_url, cookies=cookies, headers=headers)
            break
        except requests.exceptions.RequestException:
            fail += 1
            print("Failed to load page (attempt %d / 3). Retrying in 10s..." % fail)
            time.sleep(10)
    if fail == 3:
        sys.exit("Fatal error: Exceeded max retry attempts for page load")
        
    return r 

def PageInfo(gallery_url): #Takes url string
    if re.match('.*\/s\/.*', gallery_url):
        return "Page"
    elif re.match('.*\/g\/.*', gallery_url):
        return "Gallery"
    else:
        return "Overview"


def DownloadImage(image_url, image_name): #Takes strings
    '''Downloads an image. Takes a dictionary containing image name as key and URL as value.'''
    global directory
    global ovdirectory
    r = s.get(image_url, cookies=cookies, headers=headers, stream=True)
    size = int(r.headers['content-length'])
    fulldir = ovdirectory + directory
    if r.status_code == 200:
        with open(os.path.join(fulldir, image_name), 'wb') as f:
            for chunk in r.iter_content(1024):
                f.write(chunk)
    else:
        raise BadStatus(r.status_code)
        
    try: 
        if image_name[-3:] != imghdr.what(directory + '/' + image_name):
            os.rename(directory + '/' + image_name, directory + '/' + image_name[:-3] + imghdr.what(directory + '/' + image_name))
    except TypeError:
        print("OH SHIT")
        
def GetImageURL(gallery): #Takes Beautifulsoup object
    fullimg = gallery.findAll('a', href=re.compile('^http://exhentai.org/fullimg.php'))
    image_url = ""
    for links in fullimg:
            fimglink = links.get('href')
    try:
            fimglink
    except NameError:
        image_url = gallery.find(id="img")['src']
        print("Not high res - using H@H")
    else:
        if fimglink != []:
            image_url = fimglink
            print("High res - using ExH servers")
        else:
            image_url = gallery.find(id="img")['src']
            print("Not high res - using H@H")
    return image_url
    
    
def SetDirectory(gallery):
    global directory
    directory = gallery.find('title').string
    if not os.path.isdir(ovdirectory + directory):
        os.makedirs(ovdirectory + directory)

def PageLoop(gallery): #Takes Beautifulsoup object
    global stop
    imagenum = 0
    SetDirectory(gallery)
    
    while gallery:
        name = FindName(gallery)
        print(name)
        imgurl = GetImageURL(gallery)
        print(imgurl)
        
        try:
            DownloadImage(imgurl, name)
        except (requests.exceptions.RequestException, BadStatus):
            print("Error: Could not download image. Will try again later.")
            failnames.append(name)
            failurls.append(imgurl)
        
        gallery = NextGallery(gallery)
        imagenum += 1
        
        if imagenum == stop:
            gallery = False
    
    for i in range(0, len(failnames)):
        try:
            DownloadImage(failurls[i], failnames[i])
        except (requests.exceptions.RequestException, BadStatus):
            print("Error: Could not download image. Will try again later.")
            death.append(failnames[i] + " - " + failurls[i])
            
    print(death)

def NextGallery(page): #Takes a Beautifulsoup object
    '''Ensures a next page exists and if so returns the URL, else False'''
    new = page.find(id="next")['href']
    newpage = BeautifulSoup(GetGallery(new).text)
    if newpage != page:
        return newpage
    else:
        return False
    
    
def FindName(imagepage): #Takes Beautifulsoup object
    imgname = imagepage.findAll('div', {'id' : 'i4'})[0].find('div').string
    imgname = re.sub('\ ::\ .*', '', imgname)
    return imgname


def NextOverview(page): #Takes a Beautifulsoup object
    npitem = page.findAll('a', text=re.compile('>'))
    try:
        newpageurl = npitem[0].get('href')
        newpage = BeautifulSoup(GetGallery(newpageurl).text)
        return newpage
    except IndexError:
        return False

def GetGalleryURLs(overview):
    
    while overview:
        galinfos = overview.findAll('div', {'class' : 'it5'})
        urls = []
        for i in galinfos:
            a = i.find('a')
            urls.append(a['href'])
        overview = NextOverview(overview)
    
    print(urls)
    return urls

def DownloadGallery(gallery):
    first = gallery.find('a', href=re.compile('^http://exhentai.org/s/'))
    furl = first.get('href')
    PageLoop(BeautifulSoup(GetGallery(furl).text))



global directory
global ovdirectory
global stop
failnames = []
failurls = []
death = []
directory = ''
ovdirectory = ''
cmdurl = ""
gallery_url = ''
try:
    gallery_url = sys.argv[1]
except IndexError:
    print("Supply me a URL, come on")
    exit(0)

try:
    stop = sys.argv[2]
except IndexError:
    stop = 999999

try:
    ovdirectory = sys.argv[3]
except IndexError:
    ovdirectory = ""
s = requests.Session()
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0'}
cookies = dict(ipb_member_id='PUTYOUR THING HERE', ipb_pass_hash='PUT YOUR THING HERE', yay='louder')

PageID = PageInfo(gallery_url)
m_gallery = BeautifulSoup(GetGallery(gallery_url).text)

if PageID == "Overview":
    if ovdirectory == "":
        ovdirectory = "DownloadRun/"
    else:
        ovdirectory += "/DownloadRun/"
    gal_urls = GetGalleryURLs(m_gallery)
    for i in gal_urls:
        DownloadGallery(BeautifulSoup(GetGallery(i).text))
elif PageID == "Gallery":
    DownloadGallery(m_gallery)
elif PageID == "Page":
    PageLoop(m_gallery)