|
@@ 1861-1887 (lines=27) @@
|
| 1858 |
|
|
| 1859 |
|
class PicturesInBoxes(GenericNavigableComic): |
| 1860 |
|
"""Class to retrieve Pictures In Boxes comics.""" |
| 1861 |
|
# Also on https://picturesinboxescomic.tumblr.com |
| 1862 |
|
name = 'picturesinboxes' |
| 1863 |
|
long_name = 'Pictures in Boxes' |
| 1864 |
|
url = 'http://www.picturesinboxes.com' |
| 1865 |
|
get_navi_link = get_a_navi_navinext |
| 1866 |
|
get_first_comic_link = simulate_first_link |
| 1867 |
|
first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/' |
| 1868 |
|
|
| 1869 |
|
@classmethod |
| 1870 |
|
def get_comic_info(cls, soup, link): |
| 1871 |
|
"""Get information about a particular comics.""" |
| 1872 |
|
title = soup.find('h2', class_='post-title').string |
| 1873 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1874 |
|
date_str = soup.find('span', class_='post-date').string |
| 1875 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1876 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 1877 |
|
assert imgs |
| 1878 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 1879 |
|
return { |
| 1880 |
|
'day': day.day, |
| 1881 |
|
'month': day.month, |
| 1882 |
|
'year': day.year, |
| 1883 |
|
'img': [i['src'] for i in imgs], |
| 1884 |
|
'title': title, |
| 1885 |
|
'author': author, |
| 1886 |
|
} |
| 1887 |
|
|
| 1888 |
|
|
| 1889 |
|
class Penmen(GenericNavigableComic): |
| 1890 |
|
"""Class to retrieve Penmen comics.""" |
|
@@ 928-954 (lines=27) @@
|
| 925 |
|
|
| 926 |
|
class ImogenQuest(GenericNavigableComic): |
| 927 |
|
"""Class to retrieve Imogen Quest comics.""" |
| 928 |
|
# Also on http://imoquest.tumblr.com |
| 929 |
|
name = 'imogen' |
| 930 |
|
long_name = 'Imogen Quest' |
| 931 |
|
url = 'http://imogenquest.net' |
| 932 |
|
get_first_comic_link = get_div_navfirst_a |
| 933 |
|
get_navi_link = get_a_rel_next |
| 934 |
|
|
| 935 |
|
@classmethod |
| 936 |
|
def get_comic_info(cls, soup, link): |
| 937 |
|
"""Get information about a particular comics.""" |
| 938 |
|
title = soup.find('h2', class_='post-title').string |
| 939 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 940 |
|
date_str = soup.find('span', class_='post-date').string |
| 941 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 942 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 943 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 944 |
|
title2 = imgs[0]['title'] |
| 945 |
|
return { |
| 946 |
|
'day': day.day, |
| 947 |
|
'month': day.month, |
| 948 |
|
'year': day.year, |
| 949 |
|
'img': [i['src'] for i in imgs], |
| 950 |
|
'title': title, |
| 951 |
|
'title2': title2, |
| 952 |
|
'author': author, |
| 953 |
|
} |
| 954 |
|
|
| 955 |
|
|
| 956 |
|
class MyExtraLife(GenericNavigableComic): |
| 957 |
|
"""Class to retrieve My Extra Life comics.""" |
|
@@ 2534-2559 (lines=26) @@
|
| 2531 |
|
"""Class to retrieve Biter Comics.""" |
| 2532 |
|
name = "biter" |
| 2533 |
|
long_name = "Biter Comics" |
| 2534 |
|
url = "http://www.bitercomics.com" |
| 2535 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2536 |
|
get_navi_link = get_link_rel_next |
| 2537 |
|
|
| 2538 |
|
@classmethod |
| 2539 |
|
def get_comic_info(cls, soup, link): |
| 2540 |
|
"""Get information about a particular comics.""" |
| 2541 |
|
title = soup.find("h1", class_="entry-title").string |
| 2542 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2543 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2544 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2545 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2546 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2547 |
|
assert len(imgs) == 1 |
| 2548 |
|
alt = imgs[0]['alt'] |
| 2549 |
|
return { |
| 2550 |
|
'img': [i['src'] for i in imgs], |
| 2551 |
|
'title': title, |
| 2552 |
|
'alt': alt, |
| 2553 |
|
'author': author, |
| 2554 |
|
'day': day.day, |
| 2555 |
|
'month': day.month, |
| 2556 |
|
'year': day.year |
| 2557 |
|
} |
| 2558 |
|
|
| 2559 |
|
|
| 2560 |
|
class TheAwkwardYeti(GenericNavigableComic): |
| 2561 |
|
"""Class to retrieve The Awkward Yeti comics.""" |
| 2562 |
|
# Also on http://www.gocomics.com/the-awkward-yeti |
|
@@ 2788-2812 (lines=25) @@
|
| 2785 |
|
desc = soup.find('meta', property='og:description')['content'] |
| 2786 |
|
title = soup.find('meta', property='og:title')['content'] |
| 2787 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 2788 |
|
title2 = ' '.join(i.get('title', '') for i in imgs) |
| 2789 |
|
return { |
| 2790 |
|
'title': title, |
| 2791 |
|
'title2': title2, |
| 2792 |
|
'description': desc, |
| 2793 |
|
'img': [urljoin_wrapper(cls.url, convert_iri_to_plain_ascii_uri(i['src'])) for i in imgs], |
| 2794 |
|
} |
| 2795 |
|
|
| 2796 |
|
|
| 2797 |
|
class CommitStripFr(GenericCommitStrip): |
| 2798 |
|
"""Class to retrieve Commit Strips in French.""" |
| 2799 |
|
name = 'commit_fr' |
| 2800 |
|
long_name = 'Commit Strip (Fr)' |
| 2801 |
|
url = 'http://www.commitstrip.com/fr' |
| 2802 |
|
_categories = ('FRANCAIS', ) |
| 2803 |
|
first_url = 'http://www.commitstrip.com/fr/2012/02/22/interview/' |
| 2804 |
|
|
| 2805 |
|
|
| 2806 |
|
class CommitStripEn(GenericCommitStrip): |
| 2807 |
|
"""Class to retrieve Commit Strips in English.""" |
| 2808 |
|
name = 'commit_en' |
| 2809 |
|
long_name = 'Commit Strip (En)' |
| 2810 |
|
url = 'http://www.commitstrip.com/en' |
| 2811 |
|
first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/' |
| 2812 |
|
|
| 2813 |
|
|
| 2814 |
|
class GenericBoumerie(GenericNavigableComic): |
| 2815 |
|
"""Generic class to retrieve Boumeries comics in different languages.""" |
|
@@ 2476-2500 (lines=25) @@
|
| 2473 |
|
class GerbilWithAJetpack(GenericNavigableComic): |
| 2474 |
|
"""Class to retrieve GerbilWithAJetpack comics.""" |
| 2475 |
|
name = 'gerbil' |
| 2476 |
|
long_name = 'Gerbil With A Jetpack' |
| 2477 |
|
url = 'http://gerbilwithajetpack.com' |
| 2478 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2479 |
|
get_navi_link = get_a_rel_next |
| 2480 |
|
|
| 2481 |
|
@classmethod |
| 2482 |
|
def get_comic_info(cls, soup, link): |
| 2483 |
|
"""Get information about a particular comics.""" |
| 2484 |
|
title = soup.find('h2', class_='post-title').string |
| 2485 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2486 |
|
date_str = soup.find("span", class_="post-date").string |
| 2487 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2488 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2489 |
|
alt = imgs[0]['alt'] |
| 2490 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2491 |
|
return { |
| 2492 |
|
'img': [i['src'] for i in imgs], |
| 2493 |
|
'title': title, |
| 2494 |
|
'alt': alt, |
| 2495 |
|
'author': author, |
| 2496 |
|
'day': day.day, |
| 2497 |
|
'month': day.month, |
| 2498 |
|
'year': day.year |
| 2499 |
|
} |
| 2500 |
|
|
| 2501 |
|
|
| 2502 |
|
class EveryDayBlues(GenericEmptyComic, GenericNavigableComic): |
| 2503 |
|
"""Class to retrieve EveryDayBlues Comics.""" |
|
@@ 1749-1773 (lines=25) @@
|
| 1746 |
|
|
| 1747 |
|
class MouseBearComedy(GenericNavigableComic): |
| 1748 |
|
"""Class to retrieve Mouse Bear Comedy comics.""" |
| 1749 |
|
# Also on http://mousebearcomedy.tumblr.com |
| 1750 |
|
name = 'mousebear' |
| 1751 |
|
long_name = 'Mouse Bear Comedy' |
| 1752 |
|
url = 'http://www.mousebearcomedy.com' |
| 1753 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1754 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 1755 |
|
|
| 1756 |
|
@classmethod |
| 1757 |
|
def get_comic_info(cls, soup, link): |
| 1758 |
|
"""Get information about a particular comics.""" |
| 1759 |
|
title = soup.find('h2', class_='post-title').string |
| 1760 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1761 |
|
date_str = soup.find("span", class_="post-date").string |
| 1762 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1763 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 1764 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 1765 |
|
return { |
| 1766 |
|
'day': day.day, |
| 1767 |
|
'month': day.month, |
| 1768 |
|
'year': day.year, |
| 1769 |
|
'img': [i['src'] for i in imgs], |
| 1770 |
|
'title': title, |
| 1771 |
|
'author': author, |
| 1772 |
|
} |
| 1773 |
|
|
| 1774 |
|
|
| 1775 |
|
class BigFootJustice(GenericNavigableComic): |
| 1776 |
|
"""Class to retrieve Big Foot Justice comics.""" |
|
@@ 1157-1180 (lines=24) @@
|
| 1154 |
|
|
| 1155 |
|
class AmazingSuperPowers(GenericNavigableComic): |
| 1156 |
|
"""Class to retrieve Amazing Super Powers comics.""" |
| 1157 |
|
name = 'asp' |
| 1158 |
|
long_name = 'Amazing Super Powers' |
| 1159 |
|
url = 'http://www.amazingsuperpowers.com' |
| 1160 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1161 |
|
get_navi_link = get_a_navi_navinext |
| 1162 |
|
|
| 1163 |
|
@classmethod |
| 1164 |
|
def get_comic_info(cls, soup, link): |
| 1165 |
|
"""Get information about a particular comics.""" |
| 1166 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1167 |
|
date_str = soup.find('span', class_='post-date').string |
| 1168 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 1169 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1170 |
|
title = ' '.join(i['title'] for i in imgs) |
| 1171 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 1172 |
|
return { |
| 1173 |
|
'title': title, |
| 1174 |
|
'author': author, |
| 1175 |
|
'img': [img['src'] for img in imgs], |
| 1176 |
|
'day': day.day, |
| 1177 |
|
'month': day.month, |
| 1178 |
|
'year': day.year |
| 1179 |
|
} |
| 1180 |
|
|
| 1181 |
|
|
| 1182 |
|
class ToonHole(GenericNavigableComic): |
| 1183 |
|
"""Class to retrieve Toon Holes comics.""" |
|
@@ 674-697 (lines=24) @@
|
| 671 |
|
|
| 672 |
|
class OneOneOneOneComic(GenericEmptyComic, GenericNavigableComic): |
| 673 |
|
"""Class to retrieve 1111 Comics.""" |
| 674 |
|
# Also on http://comics1111.tumblr.com |
| 675 |
|
# Also on https://tapastic.com/series/1111-Comics |
| 676 |
|
name = '1111' |
| 677 |
|
long_name = '1111 Comics' |
| 678 |
|
url = 'http://www.1111comics.me' |
| 679 |
|
_categories = ('ONEONEONEONE', ) |
| 680 |
|
get_first_comic_link = get_div_navfirst_a |
| 681 |
|
get_navi_link = get_link_rel_next |
| 682 |
|
|
| 683 |
|
@classmethod |
| 684 |
|
def get_comic_info(cls, soup, link): |
| 685 |
|
"""Get information about a particular comics.""" |
| 686 |
|
title = soup.find('h1', class_='comic-title').find('a').string |
| 687 |
|
date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string |
| 688 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 689 |
|
imgs = soup.find_all('meta', property='og:image') |
| 690 |
|
return { |
| 691 |
|
'title': title, |
| 692 |
|
'month': day.month, |
| 693 |
|
'year': day.year, |
| 694 |
|
'day': day.day, |
| 695 |
|
'img': [i['content'] for i in imgs], |
| 696 |
|
} |
| 697 |
|
|
| 698 |
|
|
| 699 |
|
class AngryAtNothing(GenericEmptyComic, GenericNavigableComic): |
| 700 |
|
"""Class to retrieve Angry at Nothing comics.""" |
|
@@ 902-924 (lines=23) @@
|
| 899 |
|
|
| 900 |
|
class TheGentlemanArmchair(GenericNavigableComic): |
| 901 |
|
"""Class to retrieve The Gentleman Armchair comics.""" |
| 902 |
|
name = 'gentlemanarmchair' |
| 903 |
|
long_name = 'The Gentleman Armchair' |
| 904 |
|
url = 'http://thegentlemansarmchair.com' |
| 905 |
|
get_first_comic_link = get_a_navi_navifirst |
| 906 |
|
get_navi_link = get_link_rel_next |
| 907 |
|
|
| 908 |
|
@classmethod |
| 909 |
|
def get_comic_info(cls, soup, link): |
| 910 |
|
"""Get information about a particular comics.""" |
| 911 |
|
title = soup.find('h2', class_='post-title').string |
| 912 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 913 |
|
date_str = soup.find('span', class_='post-date').string |
| 914 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 915 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 916 |
|
return { |
| 917 |
|
'img': [i['src'] for i in imgs], |
| 918 |
|
'title': title, |
| 919 |
|
'author': author, |
| 920 |
|
'month': day.month, |
| 921 |
|
'year': day.year, |
| 922 |
|
'day': day.day, |
| 923 |
|
} |
| 924 |
|
|
| 925 |
|
|
| 926 |
|
class ImogenQuest(GenericNavigableComic): |
| 927 |
|
"""Class to retrieve Imogen Quest comics.""" |
|
@@ 701-722 (lines=22) @@
|
| 698 |
|
|
| 699 |
|
class AngryAtNothing(GenericEmptyComic, GenericNavigableComic): |
| 700 |
|
"""Class to retrieve Angry at Nothing comics.""" |
| 701 |
|
# Also on http://tapastic.com/series/Comics-yeah-definitely-comics- |
| 702 |
|
# Also on http://angryatnothing.tumblr.com |
| 703 |
|
name = 'angry' |
| 704 |
|
long_name = 'Angry At Nothing' |
| 705 |
|
url = 'http://www.angryatnothing.net' |
| 706 |
|
get_first_comic_link = get_div_navfirst_a |
| 707 |
|
get_navi_link = get_a_rel_next |
| 708 |
|
|
| 709 |
|
@classmethod |
| 710 |
|
def get_comic_info(cls, soup, link): |
| 711 |
|
"""Get information about a particular comics.""" |
| 712 |
|
title = soup.find('h1', class_='comic-title').find('a').string |
| 713 |
|
date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string |
| 714 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 715 |
|
imgs = soup.find_all('meta', property='og:image') |
| 716 |
|
return { |
| 717 |
|
'title': title, |
| 718 |
|
'month': day.month, |
| 719 |
|
'year': day.year, |
| 720 |
|
'day': day.day, |
| 721 |
|
'img': [i['content'] for i in imgs], |
| 722 |
|
} |
| 723 |
|
|
| 724 |
|
|
| 725 |
|
class NeDroid(GenericNavigableComic): |
|
@@ 2645-2673 (lines=29) @@
|
| 2642 |
|
"""Class to retrieve Last Place Comics.""" |
| 2643 |
|
name = 'lastplace' |
| 2644 |
|
long_name = 'Last Place Comics' |
| 2645 |
|
url = "http://lastplacecomics.com" |
| 2646 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2647 |
|
get_navi_link = get_link_rel_next |
| 2648 |
|
|
| 2649 |
|
@classmethod |
| 2650 |
|
def get_comic_info(cls, soup, link): |
| 2651 |
|
"""Get information about a particular comics.""" |
| 2652 |
|
title = soup.find('h2', class_='post-title').string |
| 2653 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2654 |
|
date_str = soup.find("span", class_="post-date").string |
| 2655 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2656 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2657 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2658 |
|
assert len(imgs) <= 1 |
| 2659 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2660 |
|
return { |
| 2661 |
|
'img': [i['src'] for i in imgs], |
| 2662 |
|
'title': title, |
| 2663 |
|
'alt': alt, |
| 2664 |
|
'author': author, |
| 2665 |
|
'day': day.day, |
| 2666 |
|
'month': day.month, |
| 2667 |
|
'year': day.year |
| 2668 |
|
} |
| 2669 |
|
|
| 2670 |
|
|
| 2671 |
|
class TalesOfAbsurdity(GenericNavigableComic): |
| 2672 |
|
"""Class to retrieve Tales Of Absurdity comics.""" |
| 2673 |
|
# Also on http://tapastic.com/series/Tales-Of-Absurdity |
| 2674 |
|
# Also on http://talesofabsurdity.tumblr.com |
| 2675 |
|
name = 'absurdity' |
| 2676 |
|
long_name = 'Tales of Absurdity' |
|
@@ 2869-2895 (lines=27) @@
|
| 2866 |
|
long_name = 'Unearthed Comics' |
| 2867 |
|
url = 'http://unearthedcomics.com' |
| 2868 |
|
_categories = ('UNEARTHED', ) |
| 2869 |
|
get_navi_link = get_link_rel_next |
| 2870 |
|
get_first_comic_link = simulate_first_link |
| 2871 |
|
first_url = 'http://unearthedcomics.com/comics/world-with-turn-signals/' |
| 2872 |
|
|
| 2873 |
|
@classmethod |
| 2874 |
|
def get_comic_info(cls, soup, link): |
| 2875 |
|
"""Get information about a particular comics.""" |
| 2876 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 2877 |
|
title_elt = soup.find('h1') or soup.find('h2') |
| 2878 |
|
title = title_elt.string if title_elt else "" |
| 2879 |
|
desc = soup.find('meta', property='og:description') |
| 2880 |
|
date_str = soup.find('time', class_='published updated hidden')['datetime'] |
| 2881 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 2882 |
|
post = soup.find('div', class_="entry content entry-content type-portfolio") |
| 2883 |
|
imgs = post.find_all('img') |
| 2884 |
|
return { |
| 2885 |
|
'title': title, |
| 2886 |
|
'description': desc, |
| 2887 |
|
'url2': short_url, |
| 2888 |
|
'img': [i['src'] for i in imgs], |
| 2889 |
|
'month': day.month, |
| 2890 |
|
'year': day.year, |
| 2891 |
|
'day': day.day, |
| 2892 |
|
} |
| 2893 |
|
|
| 2894 |
|
|
| 2895 |
|
class Optipess(GenericNavigableComic): |
| 2896 |
|
"""Class to retrieve Optipess comics.""" |
| 2897 |
|
name = 'optipess' |
| 2898 |
|
long_name = 'Optipess' |
|
@@ 2504-2530 (lines=27) @@
|
| 2501 |
|
|
| 2502 |
|
class EveryDayBlues(GenericEmptyComic, GenericNavigableComic): |
| 2503 |
|
"""Class to retrieve EveryDayBlues Comics.""" |
| 2504 |
|
name = "blues" |
| 2505 |
|
long_name = "Every Day Blues" |
| 2506 |
|
url = "http://everydayblues.net" |
| 2507 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2508 |
|
get_navi_link = get_link_rel_next |
| 2509 |
|
|
| 2510 |
|
@classmethod |
| 2511 |
|
def get_comic_info(cls, soup, link): |
| 2512 |
|
"""Get information about a particular comics.""" |
| 2513 |
|
title = soup.find("h2", class_="post-title").string |
| 2514 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2515 |
|
date_str = soup.find("span", class_="post-date").string |
| 2516 |
|
day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8") |
| 2517 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2518 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 2519 |
|
assert len(imgs) <= 1 |
| 2520 |
|
return { |
| 2521 |
|
'img': [i['src'] for i in imgs], |
| 2522 |
|
'title': title, |
| 2523 |
|
'author': author, |
| 2524 |
|
'day': day.day, |
| 2525 |
|
'month': day.month, |
| 2526 |
|
'year': day.year |
| 2527 |
|
} |
| 2528 |
|
|
| 2529 |
|
|
| 2530 |
|
class BiterComics(GenericNavigableComic): |
| 2531 |
|
"""Class to retrieve Biter Comics.""" |
| 2532 |
|
name = "biter" |
| 2533 |
|
long_name = "Biter Comics" |
|
@@ 2006-2032 (lines=27) @@
|
| 2003 |
|
|
| 2004 |
|
class CompletelySeriousComics(GenericNavigableComic): |
| 2005 |
|
"""Class to retrieve Completely Serious comics.""" |
| 2006 |
|
name = 'completelyserious' |
| 2007 |
|
long_name = 'Completely Serious Comics' |
| 2008 |
|
url = 'http://completelyseriouscomics.com' |
| 2009 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2010 |
|
get_navi_link = get_a_navi_navinext |
| 2011 |
|
|
| 2012 |
|
@classmethod |
| 2013 |
|
def get_comic_info(cls, soup, link): |
| 2014 |
|
"""Get information about a particular comics.""" |
| 2015 |
|
title = soup.find('h2', class_='post-title').string |
| 2016 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 2017 |
|
date_str = soup.find('span', class_='post-date').string |
| 2018 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 2019 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 2020 |
|
assert imgs |
| 2021 |
|
alt = imgs[0]['title'] |
| 2022 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 2023 |
|
return { |
| 2024 |
|
'month': day.month, |
| 2025 |
|
'year': day.year, |
| 2026 |
|
'day': day.day, |
| 2027 |
|
'img': [i['src'] for i in imgs], |
| 2028 |
|
'title': title, |
| 2029 |
|
'alt': alt, |
| 2030 |
|
'author': author, |
| 2031 |
|
} |
| 2032 |
|
|
| 2033 |
|
|
| 2034 |
|
class PoorlyDrawnLines(GenericListableComic): |
| 2035 |
|
"""Class to retrieve Poorly Drawn Lines comics.""" |
|
@@ 2677-2702 (lines=26) @@
|
| 2674 |
|
# Also on http://talesofabsurdity.tumblr.com |
| 2675 |
|
name = 'absurdity' |
| 2676 |
|
long_name = 'Tales of Absurdity' |
| 2677 |
|
url = 'http://talesofabsurdity.com' |
| 2678 |
|
_categories = ('ABSURDITY', ) |
| 2679 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2680 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2681 |
|
|
| 2682 |
|
@classmethod |
| 2683 |
|
def get_comic_info(cls, soup, link): |
| 2684 |
|
"""Get information about a particular comics.""" |
| 2685 |
|
title = soup.find('h2', class_='post-title').string |
| 2686 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2687 |
|
date_str = soup.find("span", class_="post-date").string |
| 2688 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2689 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2690 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2691 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2692 |
|
return { |
| 2693 |
|
'img': [i['src'] for i in imgs], |
| 2694 |
|
'title': title, |
| 2695 |
|
'alt': alt, |
| 2696 |
|
'author': author, |
| 2697 |
|
'day': day.day, |
| 2698 |
|
'month': day.month, |
| 2699 |
|
'year': day.year |
| 2700 |
|
} |
| 2701 |
|
|
| 2702 |
|
|
| 2703 |
|
class EndlessOrigami(GenericEmptyComic, GenericNavigableComic): |
| 2704 |
|
"""Class to retrieve Endless Origami Comics.""" |
| 2705 |
|
name = "origami" |
|
@@ 2218-2243 (lines=26) @@
|
| 2215 |
|
|
| 2216 |
|
class HappleTea(GenericNavigableComic): |
| 2217 |
|
"""Class to retrieve Happle Tea Comics.""" |
| 2218 |
|
name = 'happletea' |
| 2219 |
|
long_name = 'Happle Tea' |
| 2220 |
|
url = 'http://www.happletea.com' |
| 2221 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2222 |
|
get_navi_link = get_link_rel_next |
| 2223 |
|
|
| 2224 |
|
@classmethod |
| 2225 |
|
def get_comic_info(cls, soup, link): |
| 2226 |
|
"""Get information about a particular comics.""" |
| 2227 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2228 |
|
post = soup.find('div', class_='post-content') |
| 2229 |
|
title = post.find('h2', class_='post-title').string |
| 2230 |
|
author = post.find('a', rel='author').string |
| 2231 |
|
date_str = post.find('span', class_='post-date').string |
| 2232 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2233 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2234 |
|
return { |
| 2235 |
|
'title': title, |
| 2236 |
|
'img': [i['src'] for i in imgs], |
| 2237 |
|
'alt': ''.join(i['alt'] for i in imgs), |
| 2238 |
|
'month': day.month, |
| 2239 |
|
'year': day.year, |
| 2240 |
|
'day': day.day, |
| 2241 |
|
'author': author, |
| 2242 |
|
} |
| 2243 |
|
|
| 2244 |
|
|
| 2245 |
|
class RockPaperScissors(GenericNavigableComic): |
| 2246 |
|
"""Class to retrieve Rock Paper Scissors comics.""" |
|
@@ 1891-1916 (lines=26) @@
|
| 1888 |
|
|
| 1889 |
|
class Penmen(GenericNavigableComic): |
| 1890 |
|
"""Class to retrieve Penmen comics.""" |
| 1891 |
|
name = 'penmen' |
| 1892 |
|
long_name = 'Penmen' |
| 1893 |
|
url = 'http://penmen.com' |
| 1894 |
|
get_navi_link = get_link_rel_next |
| 1895 |
|
get_first_comic_link = simulate_first_link |
| 1896 |
|
first_url = 'http://penmen.com/index.php/2016/09/12/penmen-announces-grin-big-brand-clothing/' |
| 1897 |
|
|
| 1898 |
|
@classmethod |
| 1899 |
|
def get_comic_info(cls, soup, link): |
| 1900 |
|
"""Get information about a particular comics.""" |
| 1901 |
|
title = soup.find('title').string |
| 1902 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 1903 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 1904 |
|
tags = ' '.join(t.string for t in soup.find_all('a', rel='tag')) |
| 1905 |
|
date_str = soup.find('time')['datetime'][:10] |
| 1906 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 1907 |
|
return { |
| 1908 |
|
'title': title, |
| 1909 |
|
'short_url': short_url, |
| 1910 |
|
'img': [i['src'] for i in imgs], |
| 1911 |
|
'tags': tags, |
| 1912 |
|
'month': day.month, |
| 1913 |
|
'year': day.year, |
| 1914 |
|
'day': day.day, |
| 1915 |
|
} |
| 1916 |
|
|
| 1917 |
|
|
| 1918 |
|
class TheDoghouseDiaries(GenericNavigableComic): |
| 1919 |
|
"""Class to retrieve The Dog House Diaries comics.""" |
|
@@ 1832-1857 (lines=26) @@
|
| 1829 |
|
|
| 1830 |
|
class SafelyEndangered(GenericNavigableComic): |
| 1831 |
|
"""Class to retrieve Safely Endangered comics.""" |
| 1832 |
|
# Also on http://tumblr.safelyendangered.com |
| 1833 |
|
name = 'endangered' |
| 1834 |
|
long_name = 'Safely Endangered' |
| 1835 |
|
url = 'http://www.safelyendangered.com' |
| 1836 |
|
get_navi_link = get_link_rel_next |
| 1837 |
|
get_first_comic_link = simulate_first_link |
| 1838 |
|
first_url = 'http://www.safelyendangered.com/comic/ignored/' |
| 1839 |
|
|
| 1840 |
|
@classmethod |
| 1841 |
|
def get_comic_info(cls, soup, link): |
| 1842 |
|
"""Get information about a particular comics.""" |
| 1843 |
|
title = soup.find('h2', class_='post-title').string |
| 1844 |
|
date_str = soup.find('span', class_='post-date').string |
| 1845 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1846 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1847 |
|
alt = imgs[0]['alt'] |
| 1848 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 1849 |
|
return { |
| 1850 |
|
'day': day.day, |
| 1851 |
|
'month': day.month, |
| 1852 |
|
'year': day.year, |
| 1853 |
|
'img': [i['src'] for i in imgs], |
| 1854 |
|
'title': title, |
| 1855 |
|
'alt': alt, |
| 1856 |
|
} |
| 1857 |
|
|
| 1858 |
|
|
| 1859 |
|
class PicturesInBoxes(GenericNavigableComic): |
| 1860 |
|
"""Class to retrieve Pictures In Boxes comics.""" |
|
@@ 2346-2370 (lines=25) @@
|
| 2343 |
|
def get_url_from_archive_element(cls, tr): |
| 2344 |
|
"""Get url corresponding to an archive element.""" |
| 2345 |
|
_, td_comic, td_date, _ = tr.find_all('td') |
| 2346 |
|
link = td_comic.find('a') |
| 2347 |
|
return urljoin_wrapper(cls.url, link['href']) |
| 2348 |
|
|
| 2349 |
|
@classmethod |
| 2350 |
|
def get_comic_info(cls, soup, tr): |
| 2351 |
|
"""Get information about a particular comics.""" |
| 2352 |
|
td_num, td_comic, td_date, _ = tr.find_all('td') |
| 2353 |
|
num = int(td_num.string) |
| 2354 |
|
link = td_comic.find('a') |
| 2355 |
|
title = link.string |
| 2356 |
|
imgs = soup.find_all('img', id='comic_image') |
| 2357 |
|
date_str = td_date.string |
| 2358 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y, %I:%M %p") |
| 2359 |
|
assert len(imgs) == 1 |
| 2360 |
|
assert all(i.get('alt') == i.get('title') for i in imgs) |
| 2361 |
|
return { |
| 2362 |
|
'num': num, |
| 2363 |
|
'title': title, |
| 2364 |
|
'alt': imgs[0].get('alt', ''), |
| 2365 |
|
'img': [i['src'] for i in imgs], |
| 2366 |
|
'month': day.month, |
| 2367 |
|
'year': day.year, |
| 2368 |
|
'day': day.day, |
| 2369 |
|
} |
| 2370 |
|
|
| 2371 |
|
|
| 2372 |
|
class LonnieMillsap(GenericNavigableComic): |
| 2373 |
|
"""Class to retrieve Lonnie Millsap's comics.""" |
|
@@ 2094-2118 (lines=25) @@
|
| 2091 |
|
|
| 2092 |
|
class ChuckleADuck(GenericNavigableComic): |
| 2093 |
|
"""Class to retrieve Chuckle-A-Duck comics.""" |
| 2094 |
|
name = 'chuckleaduck' |
| 2095 |
|
long_name = 'Chuckle-A-duck' |
| 2096 |
|
url = 'http://chuckleaduck.com' |
| 2097 |
|
get_first_comic_link = get_div_navfirst_a |
| 2098 |
|
get_navi_link = get_link_rel_next |
| 2099 |
|
|
| 2100 |
|
@classmethod |
| 2101 |
|
def get_comic_info(cls, soup, link): |
| 2102 |
|
"""Get information about a particular comics.""" |
| 2103 |
|
date_str = soup.find('span', class_='post-date').string |
| 2104 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y") |
| 2105 |
|
author = soup.find('span', class_='post-author').string |
| 2106 |
|
div = soup.find('div', id='comic') |
| 2107 |
|
imgs = div.find_all('img') if div else [] |
| 2108 |
|
title = imgs[0]['title'] if imgs else "" |
| 2109 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 2110 |
|
return { |
| 2111 |
|
'month': day.month, |
| 2112 |
|
'year': day.year, |
| 2113 |
|
'day': day.day, |
| 2114 |
|
'img': [i['src'] for i in imgs], |
| 2115 |
|
'title': title, |
| 2116 |
|
'author': author, |
| 2117 |
|
} |
| 2118 |
|
|
| 2119 |
|
|
| 2120 |
|
class DepressedAlien(GenericNavigableComic): |
| 2121 |
|
"""Class to retrieve Depressed Alien Comics.""" |
|
@@ 3156-3179 (lines=24) @@
|
| 3153 |
|
long_name = 'Sheldon Comics' |
| 3154 |
|
url = 'http://www.sheldoncomics.com' |
| 3155 |
|
|
| 3156 |
|
@classmethod |
| 3157 |
|
def get_first_comic_link(cls): |
| 3158 |
|
"""Get link to first comics.""" |
| 3159 |
|
return get_soup_at_url(cls.url).find("a", id="nav-first") |
| 3160 |
|
|
| 3161 |
|
@classmethod |
| 3162 |
|
def get_navi_link(cls, last_soup, next_): |
| 3163 |
|
"""Get link to next or previous comic.""" |
| 3164 |
|
for link in last_soup.find_all("a", id="nav-next" if next_ else "nav-prev"): |
| 3165 |
|
if link['href'] != 'http://www.sheldoncomics.com': |
| 3166 |
|
return link |
| 3167 |
|
return None |
| 3168 |
|
|
| 3169 |
|
@classmethod |
| 3170 |
|
def get_comic_info(cls, soup, link): |
| 3171 |
|
"""Get information about a particular comics.""" |
| 3172 |
|
imgs = soup.find("div", id="comic-foot").find_all("img") |
| 3173 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 3174 |
|
assert len(imgs) == 1 |
| 3175 |
|
title = imgs[0]['title'] |
| 3176 |
|
return { |
| 3177 |
|
'title': title, |
| 3178 |
|
'img': [i['src'] for i in imgs], |
| 3179 |
|
} |
| 3180 |
|
|
| 3181 |
|
|
| 3182 |
|
class Ubertool(GenericNavigableComic): |
|
@@ 648-670 (lines=23) @@
|
| 645 |
|
|
| 646 |
|
class PenelopeBagieu(GenericNavigableComic): |
| 647 |
|
"""Class to retrieve comics from Penelope Bagieu's blog.""" |
| 648 |
|
name = 'bagieu' |
| 649 |
|
long_name = 'Ma vie est tout a fait fascinante (Bagieu)' |
| 650 |
|
url = 'http://www.penelope-jolicoeur.com' |
| 651 |
|
_categories = ('FRANCAIS', ) |
| 652 |
|
get_navi_link = get_link_rel_next |
| 653 |
|
get_first_comic_link = simulate_first_link |
| 654 |
|
first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html' |
| 655 |
|
|
| 656 |
|
@classmethod |
| 657 |
|
def get_comic_info(cls, soup, link): |
| 658 |
|
"""Get information about a particular comics.""" |
| 659 |
|
date_str = soup.find('h2', class_='date-header').string |
| 660 |
|
day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8") |
| 661 |
|
imgs = soup.find('div', class_='entry-body').find_all('img') |
| 662 |
|
title = soup.find('h3', class_='entry-header').string |
| 663 |
|
return { |
| 664 |
|
'title': title, |
| 665 |
|
'img': [i['src'] for i in imgs], |
| 666 |
|
'month': day.month, |
| 667 |
|
'year': day.year, |
| 668 |
|
'day': day.day, |
| 669 |
|
} |
| 670 |
|
|
| 671 |
|
|
| 672 |
|
class OneOneOneOneComic(GenericEmptyComic, GenericNavigableComic): |
| 673 |
|
"""Class to retrieve 1111 Comics.""" |
|
@@ 1702-1722 (lines=21) @@
|
| 1699 |
|
|
| 1700 |
|
class WarehouseComic(GenericNavigableComic): |
| 1701 |
|
"""Class to retrieve Warehouse Comic comics.""" |
| 1702 |
|
name = 'warehouse' |
| 1703 |
|
long_name = 'Warehouse Comic' |
| 1704 |
|
url = 'http://warehousecomic.com' |
| 1705 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1706 |
|
get_navi_link = get_link_rel_next |
| 1707 |
|
|
| 1708 |
|
@classmethod |
| 1709 |
|
def get_comic_info(cls, soup, link): |
| 1710 |
|
"""Get information about a particular comics.""" |
| 1711 |
|
title = soup.find('h2', class_='post-title').string |
| 1712 |
|
date_str = soup.find('span', class_='post-date').string |
| 1713 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 1714 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1715 |
|
return { |
| 1716 |
|
'img': [i['src'] for i in imgs], |
| 1717 |
|
'title': title, |
| 1718 |
|
'day': day.day, |
| 1719 |
|
'month': day.month, |
| 1720 |
|
'year': day.year, |
| 1721 |
|
} |
| 1722 |
|
|
| 1723 |
|
|
| 1724 |
|
class JustSayEh(GenericNavigableComic): |
| 1725 |
|
"""Class to retrieve Just Say Eh comics.""" |
|
@@ 2583-2611 (lines=29) @@
|
| 2580 |
|
return { |
| 2581 |
|
'img': [i['src'] for i in imgs], |
| 2582 |
|
'title': title, |
| 2583 |
|
'day': day.day, |
| 2584 |
|
'month': day.month, |
| 2585 |
|
'year': day.year |
| 2586 |
|
} |
| 2587 |
|
|
| 2588 |
|
|
| 2589 |
|
class PleasantThoughts(GenericNavigableComic): |
| 2590 |
|
"""Class to retrieve Pleasant Thoughts comics.""" |
| 2591 |
|
name = 'pleasant' |
| 2592 |
|
long_name = 'Pleasant Thoughts' |
| 2593 |
|
url = 'http://pleasant-thoughts.com' |
| 2594 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2595 |
|
get_navi_link = get_link_rel_next |
| 2596 |
|
|
| 2597 |
|
@classmethod |
| 2598 |
|
def get_comic_info(cls, soup, link): |
| 2599 |
|
"""Get information about a particular comics.""" |
| 2600 |
|
post = soup.find('div', class_='post-content') |
| 2601 |
|
title = post.find('h2', class_='post-title').string |
| 2602 |
|
imgs = post.find("div", class_="entry").find_all("img") |
| 2603 |
|
return { |
| 2604 |
|
'title': title, |
| 2605 |
|
'img': [i['src'] for i in imgs], |
| 2606 |
|
} |
| 2607 |
|
|
| 2608 |
|
|
| 2609 |
|
class MisterAndMe(GenericNavigableComic): |
| 2610 |
|
"""Class to retrieve Mister & Me Comics.""" |
| 2611 |
|
# Also on http://www.gocomics.com/mister-and-me |
| 2612 |
|
# Also on https://tapastic.com/series/Mister-and-Me |
| 2613 |
|
name = 'mister' |
| 2614 |
|
long_name = 'Mister & Me' |
|
@@ 360-382 (lines=23) @@
|
| 357 |
|
return [] |
| 358 |
|
|
| 359 |
|
|
| 360 |
|
class ExtraFabulousComics(GenericNavigableComic): |
| 361 |
|
"""Class to retrieve Extra Fabulous Comics.""" |
| 362 |
|
name = 'efc' |
| 363 |
|
long_name = 'Extra Fabulous Comics' |
| 364 |
|
url = 'http://extrafabulouscomics.com' |
| 365 |
|
get_first_comic_link = get_a_navi_navifirst |
| 366 |
|
get_navi_link = get_link_rel_next |
| 367 |
|
|
| 368 |
|
@classmethod |
| 369 |
|
def get_comic_info(cls, soup, link): |
| 370 |
|
"""Get information about a particular comics.""" |
| 371 |
|
img_src_re = re.compile('^%s/wp-content/uploads/' % cls.url) |
| 372 |
|
imgs = soup.find_all('img', src=img_src_re) |
| 373 |
|
title = soup.find('meta', property='og:title')['content'] |
| 374 |
|
date_str = soup.find('meta', property='article:published_time')['content'][:10] |
| 375 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 376 |
|
return { |
| 377 |
|
'title': title, |
| 378 |
|
'img': [i['src'] for i in imgs], |
| 379 |
|
'month': day.month, |
| 380 |
|
'year': day.year, |
| 381 |
|
'day': day.day, |
| 382 |
|
'prefix': title + '-' |
| 383 |
|
} |
| 384 |
|
|
| 385 |
|
|