Mango: Informações, Busca e Download de diversos títulos de Mangá.

mango.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""Mango: Informações, Busca e Download de diversos títulos de Mangá.

Através da string do titulo do mangá fornecida como parâmetro,
o script faz uma busca em serviços de leitura online de Mangá a procura
do titulo informado. Caso ache, providencia informações, e disponibiliza
para download.

Repositórios suportados até o momento:
* Mangahost
"""

import os
import sys
import re
import urllib2
import requests
from bs4 import BeautifulSoup

__author__ = "Cristina Silva"
__copyright__ = "Copyright 2014, mango"
__credits__ = "Cristina Silva"
__license__ = "MIT"
__version__ = "1.0"
__maintainer__ = "Cristina Silva"
__email__ = "cristina.silva@openmailbox.org"
__status__ = "Development"

directory = os.path.expanduser('~/mango')
if not os.path.exists(directory):
    os.makedirs(directory)

if len(sys.argv) == 2:
    if sys.argv[1] in ('-h', '-help', '--h', '--help', 'h', 'help'):
        print "mango 1.0"
        print "Usage: mango [options] \"title manga\""
        
    elif re.match('[A-Za-z0-9]+', sys.argv[1]):
        title = sys.argv[1].lower().replace(" ", "-")
        url = "http://br.mangahost.com/manga/" + title + "/"
        header = {'User-Agent': 'Mozilla/5.0'}
        req = urllib2.Request(url, headers=header)
        page = urllib2.urlopen(req)
        text = page.read().decode("utf-8")

        soup = BeautifulSoup(text)
        
        chapters = []
        for chapter in soup.find(attrs={'class':"list_chapters"}).findAll('a'):
            value = str(chapter['id'])
            chapters.append(url+value)

        chapters.reverse()
        
        print "Manga\'s Title:\t" + sys.argv[1]
        print "Availabe Chapters:\t" + str(len(chapters))
        chapter = input("Download Chapter:\t")

        directory = directory+"/"+sys.argv[1]
        if not os.path.exists(directory):
            os.makedirs(directory)
        directory = directory+"/"+"Chapter_"+str('{0:04}'.format(chapter))
        if not os.path.exists(directory):
            os.makedirs(directory)
        
        req = urllib2.Request(chapters[chapter-1], headers=header)
        page = urllib2.urlopen(req)
        text = page.read().decode("utf-8")

        soup = BeautifulSoup(text)

        pages = []
        number = []
        for page in soup.find(attrs={'name':"Pages"}).findAll('option'):
            number.append(int( page['value']))
            pages.append(sys.argv[1]+" - Capítulo "+str(chapter)+" - Página "+page['value'])

        links = []
        for num in number:            
            url_page = chapters[chapter-1]+"/"+str(num)
            req = urllib2.Request(url_page, headers=header)
            page = urllib2.urlopen(req)
            text = page.read().decode("utf-8")
            soup = BeautifulSoup(text)
            link = soup.find('img', attrs={'alt':pages[num-1]})
            links.append(str(link['src']))

        for num in number:
            url = links[num]
            req = urllib2.Request(url, headers=header)
            r = urllib2.urlopen(req)
            f = open(directory + '/' + "Page_"+str('{0:04}'.format(num))+".jpg", 'wb')
            f.write(r.read())
            f.close()
                
elif len(sys.argv) == 1:
    print "Try --help for more information."
    
else:
    print "Invalids parameters numbers."

Exemplo de uso:

cristinasilvaeng@home$ mango "20th Century Boys"
Manga's Title:  20th Century Boys
Availabe Chapters:  249
Download Chapter:   1

Meu eu do passado não garante o resto.