Code Duplication    Length = 22-26 lines in 5 locations

comics.py 5 locations

@@ 387-412 (lines=26) @@
384
    _categories = ('DELETED', )
385
386
387
class ExtraFabulousComics(GenericNavigableComic):
388
    """Class to retrieve Extra Fabulous Comics."""
389
    # Also on https://extrafabulouscomics.tumblr.com
390
    name = 'efc'
391
    long_name = 'Extra Fabulous Comics'
392
    url = 'http://extrafabulouscomics.com'
393
    _categories = ('EFC', )
394
    get_navi_link = get_link_rel_next
395
    get_first_comic_link = simulate_first_link
396
    first_url = 'http://extrafabulouscomics.com/comic/buttfly/'
397
398
    @classmethod
399
    def get_comic_info(cls, soup, link):
400
        """Get information about a particular comics."""
401
        img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url)
402
        imgs = soup.find_all('img', src=img_src_re)
403
        title = soup.find('meta', property='og:title')['content']
404
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
405
        day = string_to_date(date_str, "%Y-%m-%d")
406
        return {
407
            'title': title,
408
            'img': [i['src'] for i in imgs],
409
            'month': day.month,
410
            'year': day.year,
411
            'day': day.day,
412
            'prefix': title + '-'
413
        }
414
415
@@ 1074-1098 (lines=25) @@
1071
        }
1072
1073
1074
class Mercworks(GenericNavigableComic):
1075
    """Class to retrieve Mercworks comics."""
1076
    # Also on http://mercworks.tumblr.com
1077
    name = 'mercworks'
1078
    long_name = 'Mercworks'
1079
    url = 'http://mercworks.net'
1080
    get_first_comic_link = get_a_comicnavbase_comicnavfirst
1081
    get_navi_link = get_link_rel_next
1082
1083
    @classmethod
1084
    def get_comic_info(cls, soup, link):
1085
        """Get information about a particular comics."""
1086
        title = soup.find('meta', property='og:title')['content']
1087
        metadesc = soup.find('meta', property='og:description')
1088
        desc = metadesc['content'] if metadesc else ""
1089
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
1090
        day = string_to_date(date_str, "%Y-%m-%d")
1091
        imgs = soup.find_all('meta', property='og:image')
1092
        return {
1093
            'img': [i['content'] for i in imgs],
1094
            'title': title,
1095
            'desc': desc,
1096
            'day': day.day,
1097
            'month': day.month,
1098
            'year': day.year
1099
        }
1100
1101
@@ 416-437 (lines=22) @@
413
        }
414
415
416
class GenericLeMondeBlog(GenericNavigableComic):
417
    """Generic class to retrieve comics from Le Monde blogs."""
418
    _categories = ('LEMONDE', 'FRANCAIS')
419
    get_navi_link = get_link_rel_next
420
    get_first_comic_link = simulate_first_link
421
    first_url = NotImplemented
422
423
    @classmethod
424
    def get_comic_info(cls, soup, link):
425
        """Get information about a particular comics."""
426
        url2 = soup.find('link', rel='shortlink')['href']
427
        title = soup.find('meta', property='og:title')['content']
428
        date_str = soup.find("span", class_="entry-date").string
429
        day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8")
430
        imgs = soup.find_all('meta', property='og:image')
431
        return {
432
            'title': title,
433
            'url2': url2,
434
            'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs],
435
            'month': day.month,
436
            'year': day.year,
437
            'day': day.day,
438
        }
439
440
@@ 2393-2417 (lines=25) @@
2390
        }
2391
2392
2393
class LinsEditions(GenericNavigableComic):
2394
    """Class to retrieve L.I.N.S. Editions comics."""
2395
    # Also on https://linscomics.tumblr.com
2396
    # Now on https://warandpeas.com
2397
    name = 'lins'
2398
    long_name = 'L.I.N.S. Editions'
2399
    url = 'https://linsedition.com'
2400
    _categories = ('LINS', )
2401
    get_navi_link = get_link_rel_next
2402
    get_first_comic_link = simulate_first_link
2403
    first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/'
2404
2405
    @classmethod
2406
    def get_comic_info(cls, soup, link):
2407
        """Get information about a particular comics."""
2408
        title = soup.find('meta', property='og:title')['content']
2409
        imgs = soup.find_all('meta', property='og:image')
2410
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
2411
        day = string_to_date(date_str, "%Y-%m-%d")
2412
        return {
2413
            'title': title,
2414
            'img': [i['content'] for i in imgs],
2415
            'month': day.month,
2416
            'year': day.year,
2417
            'day': day.day,
2418
        }
2419
2420
@@ 3355-3376 (lines=22) @@
3352
        }
3353
3354
3355
class MarketoonistComics(GenericNavigableComic):
3356
    """Class to retrieve Marketoonist Comics."""
3357
    name = 'marketoonist'
3358
    long_name = 'Marketoonist'
3359
    url = 'https://marketoonist.com/cartoons'
3360
    get_first_comic_link = simulate_first_link
3361
    get_navi_link = get_link_rel_next
3362
    first_url = 'https://marketoonist.com/2002/10/the-8-types-of-brand-managers-2.html'
3363
3364
    @classmethod
3365
    def get_comic_info(cls, soup, link):
3366
        """Get information about a particular comics."""
3367
        imgs = soup.find_all('meta', property='og:image')
3368
        date_str = soup.find('meta', property='article:published_time')['content'][:10]
3369
        day = string_to_date(date_str, "%Y-%m-%d")
3370
        title = soup.find('meta', property='og:title')['content']
3371
        return {
3372
            'img': [i['content'] for i in imgs],
3373
            'day': day.day,
3374
            'month': day.month,
3375
            'year': day.year,
3376
            'title': title,
3377
        }
3378
3379