|
@@ 911-936 (lines=26) @@
|
| 908 |
|
} |
| 909 |
|
|
| 910 |
|
|
| 911 |
|
class MyExtraLife(GenericNavigableComic): |
| 912 |
|
"""Class to retrieve My Extra Life comics.""" |
| 913 |
|
name = 'extralife' |
| 914 |
|
long_name = 'My Extra Life' |
| 915 |
|
url = 'http://www.myextralife.com' |
| 916 |
|
get_navi_link = get_link_rel_next |
| 917 |
|
|
| 918 |
|
@classmethod |
| 919 |
|
def get_first_comic_link(cls): |
| 920 |
|
"""Get link to first comics.""" |
| 921 |
|
return get_soup_at_url(cls.url).find('a', class_='comic_nav_link first_comic_link') |
| 922 |
|
|
| 923 |
|
@classmethod |
| 924 |
|
def get_comic_info(cls, soup, link): |
| 925 |
|
"""Get information about a particular comics.""" |
| 926 |
|
title = soup.find("h1", class_="comic_title").string |
| 927 |
|
date_str = soup.find("span", class_="comic_date").string |
| 928 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 929 |
|
imgs = soup.find_all("img", class_="comic") |
| 930 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 931 |
|
return { |
| 932 |
|
'title': title, |
| 933 |
|
'img': [i['src'] for i in imgs if i["src"]], |
| 934 |
|
'day': day.day, |
| 935 |
|
'month': day.month, |
| 936 |
|
'year': day.year |
| 937 |
|
} |
| 938 |
|
|
| 939 |
|
|
|
@@ 2274-2298 (lines=25) @@
|
| 2271 |
|
} |
| 2272 |
|
|
| 2273 |
|
|
| 2274 |
|
class LinsEditions(GenericNavigableComic): |
| 2275 |
|
"""Class to retrieve L.I.N.S. Editions comics.""" |
| 2276 |
|
# Also on http://linscomics.tumblr.com |
| 2277 |
|
# Now on https://warandpeas.com |
| 2278 |
|
name = 'lins' |
| 2279 |
|
long_name = 'L.I.N.S. Editions' |
| 2280 |
|
url = 'https://linsedition.com' |
| 2281 |
|
_categories = ('LINS', ) |
| 2282 |
|
get_navi_link = get_link_rel_next |
| 2283 |
|
get_first_comic_link = simulate_first_link |
| 2284 |
|
first_url = 'https://linsedition.com/2011/09/07/l-i-n-s/' |
| 2285 |
|
|
| 2286 |
|
@classmethod |
| 2287 |
|
def get_comic_info(cls, soup, link): |
| 2288 |
|
"""Get information about a particular comics.""" |
| 2289 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2290 |
|
imgs = soup.find_all('meta', property='og:image') |
| 2291 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 2292 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2293 |
|
return { |
| 2294 |
|
'title': title, |
| 2295 |
|
'img': [i['content'] for i in imgs], |
| 2296 |
|
'month': day.month, |
| 2297 |
|
'year': day.year, |
| 2298 |
|
'day': day.day, |
| 2299 |
|
} |
| 2300 |
|
|
| 2301 |
|
|
|
@@ 341-363 (lines=23) @@
|
| 338 |
|
return [] |
| 339 |
|
|
| 340 |
|
|
| 341 |
|
class ExtraFabulousComics(GenericNavigableComic): |
| 342 |
|
"""Class to retrieve Extra Fabulous Comics.""" |
| 343 |
|
name = 'efc' |
| 344 |
|
long_name = 'Extra Fabulous Comics' |
| 345 |
|
url = 'http://extrafabulouscomics.com' |
| 346 |
|
get_first_comic_link = get_a_navi_navifirst |
| 347 |
|
get_navi_link = get_link_rel_next |
| 348 |
|
|
| 349 |
|
@classmethod |
| 350 |
|
def get_comic_info(cls, soup, link): |
| 351 |
|
"""Get information about a particular comics.""" |
| 352 |
|
img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url) |
| 353 |
|
imgs = soup.find_all('img', src=img_src_re) |
| 354 |
|
title = soup.find('meta', property='og:title')['content'] |
| 355 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 356 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 357 |
|
return { |
| 358 |
|
'title': title, |
| 359 |
|
'img': [i['src'] for i in imgs], |
| 360 |
|
'month': day.month, |
| 361 |
|
'year': day.year, |
| 362 |
|
'day': day.day, |
| 363 |
|
'prefix': title + '-' |
| 364 |
|
} |
| 365 |
|
|
| 366 |
|
|
|
@@ 367-388 (lines=22) @@
|
| 364 |
|
} |
| 365 |
|
|
| 366 |
|
|
| 367 |
|
class GenericLeMondeBlog(GenericNavigableComic): |
| 368 |
|
"""Generic class to retrieve comics from Le Monde blogs.""" |
| 369 |
|
_categories = ('LEMONDE', 'FRANCAIS') |
| 370 |
|
get_navi_link = get_link_rel_next |
| 371 |
|
get_first_comic_link = simulate_first_link |
| 372 |
|
first_url = NotImplemented |
| 373 |
|
|
| 374 |
|
@classmethod |
| 375 |
|
def get_comic_info(cls, soup, link): |
| 376 |
|
"""Get information about a particular comics.""" |
| 377 |
|
url2 = soup.find('link', rel='shortlink')['href'] |
| 378 |
|
title = soup.find('meta', property='og:title')['content'] |
| 379 |
|
date_str = soup.find("span", class_="entry-date").string |
| 380 |
|
day = string_to_date(date_str, "%d %B %Y", "fr_FR.utf8") |
| 381 |
|
imgs = soup.find_all('meta', property='og:image') |
| 382 |
|
return { |
| 383 |
|
'title': title, |
| 384 |
|
'url2': url2, |
| 385 |
|
'img': [convert_iri_to_plain_ascii_uri(i['content']) for i in imgs], |
| 386 |
|
'month': day.month, |
| 387 |
|
'year': day.year, |
| 388 |
|
'day': day.day, |
| 389 |
|
} |
| 390 |
|
|
| 391 |
|
|
|
@@ 1801-1826 (lines=26) @@
|
| 1798 |
|
} |
| 1799 |
|
|
| 1800 |
|
|
| 1801 |
|
class SafelyEndangered(GenericNavigableComic): |
| 1802 |
|
"""Class to retrieve Safely Endangered comics.""" |
| 1803 |
|
# Also on http://tumblr.safelyendangered.com |
| 1804 |
|
name = 'endangered' |
| 1805 |
|
long_name = 'Safely Endangered' |
| 1806 |
|
url = 'http://www.safelyendangered.com' |
| 1807 |
|
get_navi_link = get_link_rel_next |
| 1808 |
|
get_first_comic_link = simulate_first_link |
| 1809 |
|
first_url = 'http://www.safelyendangered.com/comic/ignored/' |
| 1810 |
|
|
| 1811 |
|
@classmethod |
| 1812 |
|
def get_comic_info(cls, soup, link): |
| 1813 |
|
"""Get information about a particular comics.""" |
| 1814 |
|
title = soup.find('h2', class_='post-title').string |
| 1815 |
|
date_str = soup.find('span', class_='post-date').string |
| 1816 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1817 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1818 |
|
alt = imgs[0]['alt'] |
| 1819 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 1820 |
|
return { |
| 1821 |
|
'day': day.day, |
| 1822 |
|
'month': day.month, |
| 1823 |
|
'year': day.year, |
| 1824 |
|
'img': [i['src'] for i in imgs], |
| 1825 |
|
'title': title, |
| 1826 |
|
'alt': alt, |
| 1827 |
|
} |
| 1828 |
|
|
| 1829 |
|
|
|
@@ 2545-2573 (lines=29) @@
|
| 2542 |
|
} |
| 2543 |
|
|
| 2544 |
|
|
| 2545 |
|
class TalesOfAbsurdity(GenericNavigableComic): |
| 2546 |
|
"""Class to retrieve Tales Of Absurdity comics.""" |
| 2547 |
|
# Also on http://tapastic.com/series/Tales-Of-Absurdity |
| 2548 |
|
# Also on http://talesofabsurdity.tumblr.com |
| 2549 |
|
name = 'absurdity' |
| 2550 |
|
long_name = 'Tales of Absurdity' |
| 2551 |
|
url = 'http://talesofabsurdity.com' |
| 2552 |
|
_categories = ('ABSURDITY', ) |
| 2553 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2554 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2555 |
|
|
| 2556 |
|
@classmethod |
| 2557 |
|
def get_comic_info(cls, soup, link): |
| 2558 |
|
"""Get information about a particular comics.""" |
| 2559 |
|
title = soup.find('h2', class_='post-title').string |
| 2560 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2561 |
|
date_str = soup.find("span", class_="post-date").string |
| 2562 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2563 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2564 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2565 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2566 |
|
return { |
| 2567 |
|
'img': [i['src'] for i in imgs], |
| 2568 |
|
'title': title, |
| 2569 |
|
'alt': alt, |
| 2570 |
|
'author': author, |
| 2571 |
|
'day': day.day, |
| 2572 |
|
'month': day.month, |
| 2573 |
|
'year': day.year |
| 2574 |
|
} |
| 2575 |
|
|
| 2576 |
|
|
|
@@ 2769-2795 (lines=27) @@
|
| 2766 |
|
} |
| 2767 |
|
|
| 2768 |
|
|
| 2769 |
|
class Optipess(GenericNavigableComic): |
| 2770 |
|
"""Class to retrieve Optipess comics.""" |
| 2771 |
|
name = 'optipess' |
| 2772 |
|
long_name = 'Optipess' |
| 2773 |
|
url = 'http://www.optipess.com' |
| 2774 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2775 |
|
get_navi_link = get_link_rel_next |
| 2776 |
|
|
| 2777 |
|
@classmethod |
| 2778 |
|
def get_comic_info(cls, soup, link): |
| 2779 |
|
"""Get information about a particular comics.""" |
| 2780 |
|
title = soup.find('h2', class_='post-title').string |
| 2781 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2782 |
|
comic = soup.find('div', id='comic') |
| 2783 |
|
imgs = comic.find_all('img') if comic else [] |
| 2784 |
|
alt = imgs[0]['title'] if imgs else "" |
| 2785 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2786 |
|
date_str = soup.find('span', class_='post-date').string |
| 2787 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2788 |
|
return { |
| 2789 |
|
'title': title, |
| 2790 |
|
'alt': alt, |
| 2791 |
|
'author': author, |
| 2792 |
|
'img': [i['src'] for i in imgs], |
| 2793 |
|
'month': day.month, |
| 2794 |
|
'year': day.year, |
| 2795 |
|
'day': day.day, |
| 2796 |
|
} |
| 2797 |
|
|
| 2798 |
|
|
|
@@ 2515-2541 (lines=27) @@
|
| 2512 |
|
} |
| 2513 |
|
|
| 2514 |
|
|
| 2515 |
|
class LastPlaceComics(GenericNavigableComic): |
| 2516 |
|
"""Class to retrieve Last Place Comics.""" |
| 2517 |
|
name = 'lastplace' |
| 2518 |
|
long_name = 'Last Place Comics' |
| 2519 |
|
url = "http://lastplacecomics.com" |
| 2520 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2521 |
|
get_navi_link = get_link_rel_next |
| 2522 |
|
|
| 2523 |
|
@classmethod |
| 2524 |
|
def get_comic_info(cls, soup, link): |
| 2525 |
|
"""Get information about a particular comics.""" |
| 2526 |
|
title = soup.find('h2', class_='post-title').string |
| 2527 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2528 |
|
date_str = soup.find("span", class_="post-date").string |
| 2529 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2530 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2531 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2532 |
|
assert len(imgs) <= 1 |
| 2533 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2534 |
|
return { |
| 2535 |
|
'img': [i['src'] for i in imgs], |
| 2536 |
|
'title': title, |
| 2537 |
|
'alt': alt, |
| 2538 |
|
'author': author, |
| 2539 |
|
'day': day.day, |
| 2540 |
|
'month': day.month, |
| 2541 |
|
'year': day.year |
| 2542 |
|
} |
| 2543 |
|
|
| 2544 |
|
|
|
@@ 2404-2430 (lines=27) @@
|
| 2401 |
|
} |
| 2402 |
|
|
| 2403 |
|
|
| 2404 |
|
class BiterComics(GenericNavigableComic): |
| 2405 |
|
"""Class to retrieve Biter Comics.""" |
| 2406 |
|
name = "biter" |
| 2407 |
|
long_name = "Biter Comics" |
| 2408 |
|
url = "http://www.bitercomics.com" |
| 2409 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2410 |
|
get_navi_link = get_link_rel_next |
| 2411 |
|
|
| 2412 |
|
@classmethod |
| 2413 |
|
def get_comic_info(cls, soup, link): |
| 2414 |
|
"""Get information about a particular comics.""" |
| 2415 |
|
title = soup.find("h1", class_="entry-title").string |
| 2416 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2417 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2418 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2419 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2420 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2421 |
|
assert len(imgs) == 1 |
| 2422 |
|
alt = imgs[0]['alt'] |
| 2423 |
|
return { |
| 2424 |
|
'img': [i['src'] for i in imgs], |
| 2425 |
|
'title': title, |
| 2426 |
|
'alt': alt, |
| 2427 |
|
'author': author, |
| 2428 |
|
'day': day.day, |
| 2429 |
|
'month': day.month, |
| 2430 |
|
'year': day.year |
| 2431 |
|
} |
| 2432 |
|
|
| 2433 |
|
|
|
@@ 1953-1979 (lines=27) @@
|
| 1950 |
|
_categories = ('TUNEYTOONS', ) |
| 1951 |
|
|
| 1952 |
|
|
| 1953 |
|
class CompletelySeriousComics(GenericNavigableComic): |
| 1954 |
|
"""Class to retrieve Completely Serious comics.""" |
| 1955 |
|
name = 'completelyserious' |
| 1956 |
|
long_name = 'Completely Serious Comics' |
| 1957 |
|
url = 'http://completelyseriouscomics.com' |
| 1958 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1959 |
|
get_navi_link = get_a_navi_navinext |
| 1960 |
|
|
| 1961 |
|
@classmethod |
| 1962 |
|
def get_comic_info(cls, soup, link): |
| 1963 |
|
"""Get information about a particular comics.""" |
| 1964 |
|
title = soup.find('h2', class_='post-title').string |
| 1965 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 1966 |
|
date_str = soup.find('span', class_='post-date').string |
| 1967 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1968 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 1969 |
|
assert imgs |
| 1970 |
|
alt = imgs[0]['title'] |
| 1971 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 1972 |
|
return { |
| 1973 |
|
'month': day.month, |
| 1974 |
|
'year': day.year, |
| 1975 |
|
'day': day.day, |
| 1976 |
|
'img': [i['src'] for i in imgs], |
| 1977 |
|
'title': title, |
| 1978 |
|
'alt': alt, |
| 1979 |
|
'author': author, |
| 1980 |
|
} |
| 1981 |
|
|
| 1982 |
|
|
|
@@ 2577-2602 (lines=26) @@
|
| 2574 |
|
} |
| 2575 |
|
|
| 2576 |
|
|
| 2577 |
|
class EndlessOrigami(GenericEmptyComic, GenericNavigableComic): |
| 2578 |
|
"""Class to retrieve Endless Origami Comics.""" |
| 2579 |
|
name = "origami" |
| 2580 |
|
long_name = "Endless Origami" |
| 2581 |
|
url = "http://endlessorigami.com" |
| 2582 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2583 |
|
get_navi_link = get_link_rel_next |
| 2584 |
|
|
| 2585 |
|
@classmethod |
| 2586 |
|
def get_comic_info(cls, soup, link): |
| 2587 |
|
"""Get information about a particular comics.""" |
| 2588 |
|
title = soup.find('h2', class_='post-title').string |
| 2589 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2590 |
|
date_str = soup.find("span", class_="post-date").string |
| 2591 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2592 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2593 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2594 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2595 |
|
return { |
| 2596 |
|
'img': [i['src'] for i in imgs], |
| 2597 |
|
'title': title, |
| 2598 |
|
'alt': alt, |
| 2599 |
|
'author': author, |
| 2600 |
|
'day': day.day, |
| 2601 |
|
'month': day.month, |
| 2602 |
|
'year': day.year |
| 2603 |
|
} |
| 2604 |
|
|
| 2605 |
|
|
|
@@ 2041-2065 (lines=25) @@
|
| 2038 |
|
} |
| 2039 |
|
|
| 2040 |
|
|
| 2041 |
|
class ChuckleADuck(GenericNavigableComic): |
| 2042 |
|
"""Class to retrieve Chuckle-A-Duck comics.""" |
| 2043 |
|
name = 'chuckleaduck' |
| 2044 |
|
long_name = 'Chuckle-A-duck' |
| 2045 |
|
url = 'http://chuckleaduck.com' |
| 2046 |
|
get_first_comic_link = get_div_navfirst_a |
| 2047 |
|
get_navi_link = get_link_rel_next |
| 2048 |
|
|
| 2049 |
|
@classmethod |
| 2050 |
|
def get_comic_info(cls, soup, link): |
| 2051 |
|
"""Get information about a particular comics.""" |
| 2052 |
|
date_str = soup.find('span', class_='post-date').string |
| 2053 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y") |
| 2054 |
|
author = soup.find('span', class_='post-author').string |
| 2055 |
|
div = soup.find('div', id='comic') |
| 2056 |
|
imgs = div.find_all('img') if div else [] |
| 2057 |
|
title = imgs[0]['title'] if imgs else "" |
| 2058 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 2059 |
|
return { |
| 2060 |
|
'month': day.month, |
| 2061 |
|
'year': day.year, |
| 2062 |
|
'day': day.day, |
| 2063 |
|
'img': [i['src'] for i in imgs], |
| 2064 |
|
'title': title, |
| 2065 |
|
'author': author, |
| 2066 |
|
} |
| 2067 |
|
|
| 2068 |
|
|
SylvainDe /
ComicBookMaker
