get xkcd comic

xkcd.py

import urllib,urllib2,json
import re
import os
import logging
from HTMLParser import HTMLParser

class HTMLStripper(HTMLParser):
    '''
        strip html tags
        Solution from: http://stackoverflow.com/questions/753052/strip-html-from-strings-in-python#answer-925630
    '''
    def __init__(self):
        self.reset()
        self.fed = []
    def handle_data(self, d):
        self.fed.append(d)
    def get_data(self):
        return ''.join(self.fed)


def strip_tags(html):
    '''
        deal with some title with html tags, such as comic 472
    '''
    s = HTMLStripper()
    s.feed(html)
    return s.get_data()



class Xkcd(object):
    '''
        get xkcd comic
    '''
    link = 'http://www.xkcd.com/{}/info.0.json'

    def __init__(self, index):
        if not isinstance(index, int):
            raise TypeError('Parameter "index" must be integer.')
        self.index = index
        self.link = Xkcd.link.format(index)

    def get(self):
        ret = {}
        # No.404 xkcd is not exist just like it's name.
        if self.index == 404:
            return -2,'The comic 404 is a joke.'
        try:
            resp = urllib2.urlopen(self.link).read()
            info = json.loads(resp)
            img = info['img']
            suffix_match = re.search(r'\.\w*?$',img)
            if suffix_match:
                suffix = suffix_match.group()
            else:
                suffix = '.jpg'
            ret['img'] = img
            # make the title with '/' a valid filename
            title = re.sub('/','_', strip_tags(info['title']))
            ret['title'] = "{index} - {title}{suffix}".format(index=self.index,title=title,suffix=suffix)
            return 0,ret
        except urllib2.HTTPError, error:
            if error.code == 404:
                return -2,'Comic {} does not exists.'.format(self.index)
            else:
                return -1,'Error at comic {} ,HTTPError {} happend.'.format(self.index,error.code)
        except:
            return -1,'Error at comic {}, unknown error happend.'.format(self.index)

    def save(self,src,path):
        try:
            with open(path,'wb') as f:
                f.write(urllib2.urlopen(src).read())
            return 0
        except urllib2.HTTPError, error:
            # some xkcd has no picture, such as comic 1608
            if error.code == 404:
                return -1
            else:
                return -2
        except:
            return -2


class Progress(object):
    '''
        save and load the progress to file.
    '''
    _instance = None
    def __new__(cls,*args,**kwargs):
        if not cls._instance:
            cls._instance = super(Progress,cls).__new__(cls,*args,**kwargs)
        return cls._instance

    def __init__(self,filename):
        self.filename = filename

    def load(self):
        if not os.path.isfile(self.filename):
            return 1
        else:
            with open(self.filename) as f:
                s = f.readline().strip()
                try:
                    return int(s)
                except ValueError,e:
                    return 1

    def save(self,index):
        if not isinstance(index,int):
            raise TypeError('Parameter "index" must be integer.')
        with open(self.filename,'w') as f:
            f.write(str(index))


if __name__ == '__main__':
    logging.basicConfig(
        level=logging.INFO,
        format= '%(asctime)s [%(levelname)s] %(message)s',
        datefmt='[%Y-%m-%d %H:%M:%S]',
        filename='xkcd.log'
    )
    progress = Progress('progress.data')
    index = progress.load()
    if not os.path.isdir('comic'):
        os.mkdir('comic')
    while True:
        comic = Xkcd(index)
        ret,info = comic.get()
        if ret == 0:
            saved = comic.save(info['img'],os.path.join('comic',info['title']))
            if saved == 0:
                logging.info('Comic {} saved successfully.'.format(index))
            elif saved == -1:
                logging.info('Comic {} has no image.'.format(index))
            else:
                logging.warn('Comic {} picture saved error.'.format(index))
        else:
            logging.warn(info)
            if ret == -2 and index != 404:
                progress.save(index)
                break
        index += 1