mgkadl.py

#!/usr/bin/env python3
import requests
from lxml import html
import sys
import os
import glob
import zipfile

class MgkaDL:
    def __init__(self, url):
        self.session = requests.Session()
        self.saved_urls = []
        self.url = url
        self.load_known()
        if self.url == 'update':
            print("Updating all ...")
        else:
            if url not in self.saved_urls:
                print("Downloading new url")
                f = open("mgkadl_save.txt", "a")
                f.write("%s\n" % url)
                f.close()
            self.set_url(url)


    def set_url(self, url):
        self.url = url
        self.title = url.split('/')[-1]
        print('Downloading %s' % self.title)
        self.dlpath = 'mgkadl/%s' % self.title
        if not os.path.exists(self.dlpath):
            os.makedirs(self.dlpath)


    def load_known(self):
        try:
            f = open("mgkadl_save.txt", "r")
            for line in f:
                self.saved_urls.append(line[:-1])
            print("Loaded %d urls" % len(self.saved_urls))
        except FileNotFoundError:
            print("No saved urls found")


    def get_chapters(self):
        r = self.session.get(self.url)
        if r.status_code is not 200:
            print('Error retrieving page: %d' % r.status_code)
            print(self.url)
            sys.exit(1)
        tree = html.fromstring(r.content)
        self.urls = []
        l = tree.find_class('chapter-list')[0]
        for x in l:
            self.urls.append(x[0][0].get('href'))
        self.urls = self.urls[::-1]

    def get_image(self, url, zfile):
        r = self.session.get(url, stream=True)
        filename = url.split('/')[-1]
        print(filename, end='')
        if r.status_code is not 200:
            print('Error retrieving %s: %d' % (filename, r.status_code))
            print(url)
            sys.exit(1)
        zfile.writestr(filename, r.raw.read())

    def get_images(self, url):
        r = self.session.get(url)
        if r.status_code is not 200:
            print('Error retrieving page: %d' % r.status_code)
            print(url)
            sys.exit(1)
        tree = html.fromstring(r.content)
        l = tree.get_element_by_id('vungdoc')
        i = 1
        c = len(l)
        chapter = url.split('/')[-1]
        zfile = zipfile.ZipFile('%s/%s.cbz' % (self.dlpath, chapter), mode='w')
        for x in l:
            if x.tag == 'img':
                print("\r%3d / %3d : " % (i, c), end='')
                self.get_image(x.get('src'), zfile)
            i += 1
        print()

    def download(self):
        if self.url == 'update':
            for url in self.saved_urls:
                print("Updating from %s" % url)
                self.set_url(url)
                self.__download()
        else:
            self.__download()

    def __download(self):
        self.get_chapters()
        print("Available chapters: %d" % len(self.urls))
        downloaded = len(glob.glob('%s/*.cbz' % self.dlpath))
        print("Counted in downloaded: %d" % downloaded)
        for url in self.urls[downloaded:]:
            print("Chapter: %d" % (downloaded + 1))
            self.get_images(url)
            downloaded += 1

if len(sys.argv) != 2:
    print("Usage: %s [url|update]" % sys.argv[0])
    sys.exit(1)

dl = MgkaDL(sys.argv[1])
dl.download()