stoptazmo_downloader.py

#!/usr/bin/env python

import bs4
import re
import urllib2
import logging


class Resource(object):
    url = None
    request = None
    content = None

    def __init__(self, url, auto_get=True):
        self.url = url
        self.request = urllib2.Request(self.url)
        if auto_get:
            self.get()

    def get(self):
        self.content = urllib2.urlopen(self.request).read()

    def save(self, destination_path):
        if self.content is None:
            self.get()
        with open(destination_path, "wb") as output_file:
            output_file.write(self.content)


class Chapter(object):
    name = None
    url = None


class Manga(Resource):
    soup = None
    chapters = []

    def __init__(self, url):
        super(Manga, self).__init__(url)
        self.soup = bs4.BeautifulSoup(self.content)
        self.content = self.soup.prettify()
        for snippet in self.soup.find_all("tr", class_=re.compile("row")):
            chapter = Chapter()
            chapter.name = snippet.find("td").string
            chapter.url = snippet.find("a")["href"]
            self.chapters.append(chapter)


logging.basicConfig(level=logging.DEBUG)
logging.debug("Fetching manga page.")
home = Manga("http://stoptazmo.com/manga-series/chokotto_sister/")
logging.debug("Manga page fetched.")
for chapter in home.chapters:
    logging.debug("Fetching chapter %s" % chapter.name)
    download = Resource(chapter.url, auto_get=False)
    download.request.add_header("Referer", "http://stoptazmo.com/manga-series/chokotto_sister/")
    logging.debug("Saving chapter %s" % chapter.name)
    download.save("/Users/Albireo/Downloads/Chokotto Sister/" + chapter.name)
    logging.debug("Chapter %s fetched." % chapter.name)