|
@@ 974-1000 (lines=27) @@
|
| 971 |
|
} |
| 972 |
|
|
| 973 |
|
|
| 974 |
|
class ImogenQuest(GenericNavigableComic): |
| 975 |
|
"""Class to retrieve Imogen Quest comics.""" |
| 976 |
|
# Also on http://imoquest.tumblr.com |
| 977 |
|
name = 'imogen' |
| 978 |
|
long_name = 'Imogen Quest' |
| 979 |
|
url = 'http://imogenquest.net' |
| 980 |
|
get_first_comic_link = get_div_navfirst_a |
| 981 |
|
get_navi_link = get_a_rel_next |
| 982 |
|
|
| 983 |
|
@classmethod |
| 984 |
|
def get_comic_info(cls, soup, link): |
| 985 |
|
"""Get information about a particular comics.""" |
| 986 |
|
title = soup.find('h2', class_='post-title').string |
| 987 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 988 |
|
date_str = soup.find('span', class_='post-date').string |
| 989 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 990 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 991 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 992 |
|
title2 = imgs[0]['title'] |
| 993 |
|
return { |
| 994 |
|
'day': day.day, |
| 995 |
|
'month': day.month, |
| 996 |
|
'year': day.year, |
| 997 |
|
'img': [i['src'] for i in imgs], |
| 998 |
|
'title': title, |
| 999 |
|
'title2': title2, |
| 1000 |
|
'author': author, |
| 1001 |
|
} |
| 1002 |
|
|
| 1003 |
|
|
|
@@ 1203-1226 (lines=24) @@
|
| 1200 |
|
url = 'http://english.bouletcorp.com' |
| 1201 |
|
|
| 1202 |
|
|
| 1203 |
|
class AmazingSuperPowers(GenericNavigableComic): |
| 1204 |
|
"""Class to retrieve Amazing Super Powers comics.""" |
| 1205 |
|
name = 'asp' |
| 1206 |
|
long_name = 'Amazing Super Powers' |
| 1207 |
|
url = 'http://www.amazingsuperpowers.com' |
| 1208 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1209 |
|
get_navi_link = get_a_navi_navinext |
| 1210 |
|
|
| 1211 |
|
@classmethod |
| 1212 |
|
def get_comic_info(cls, soup, link): |
| 1213 |
|
"""Get information about a particular comics.""" |
| 1214 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1215 |
|
date_str = soup.find('span', class_='post-date').string |
| 1216 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 1217 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1218 |
|
title = ' '.join(i['title'] for i in imgs) |
| 1219 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 1220 |
|
return { |
| 1221 |
|
'title': title, |
| 1222 |
|
'author': author, |
| 1223 |
|
'img': [img['src'] for img in imgs], |
| 1224 |
|
'day': day.day, |
| 1225 |
|
'month': day.month, |
| 1226 |
|
'year': day.year |
| 1227 |
|
} |
| 1228 |
|
|
| 1229 |
|
|
|
@@ 720-743 (lines=24) @@
|
| 717 |
|
} |
| 718 |
|
|
| 719 |
|
|
| 720 |
|
class OneOneOneOneComic(GenericComicNotWorking, GenericNavigableComic): |
| 721 |
|
"""Class to retrieve 1111 Comics.""" |
| 722 |
|
# Also on http://comics1111.tumblr.com |
| 723 |
|
# Also on https://tapastic.com/series/1111-Comics |
| 724 |
|
name = '1111' |
| 725 |
|
long_name = '1111 Comics' |
| 726 |
|
url = 'http://www.1111comics.me' |
| 727 |
|
_categories = ('ONEONEONEONE', ) |
| 728 |
|
get_first_comic_link = get_div_navfirst_a |
| 729 |
|
get_navi_link = get_link_rel_next |
| 730 |
|
|
| 731 |
|
@classmethod |
| 732 |
|
def get_comic_info(cls, soup, link): |
| 733 |
|
"""Get information about a particular comics.""" |
| 734 |
|
title = soup.find('h1', class_='comic-title').find('a').string |
| 735 |
|
date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string |
| 736 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 737 |
|
imgs = soup.find_all('meta', property='og:image') |
| 738 |
|
return { |
| 739 |
|
'title': title, |
| 740 |
|
'month': day.month, |
| 741 |
|
'year': day.year, |
| 742 |
|
'day': day.day, |
| 743 |
|
'img': [i['content'] for i in imgs], |
| 744 |
|
} |
| 745 |
|
|
| 746 |
|
|
|
@@ 948-970 (lines=23) @@
|
| 945 |
|
} |
| 946 |
|
|
| 947 |
|
|
| 948 |
|
class TheGentlemanArmchair(GenericNavigableComic): |
| 949 |
|
"""Class to retrieve The Gentleman Armchair comics.""" |
| 950 |
|
name = 'gentlemanarmchair' |
| 951 |
|
long_name = 'The Gentleman Armchair' |
| 952 |
|
url = 'http://thegentlemansarmchair.com' |
| 953 |
|
get_first_comic_link = get_a_navi_navifirst |
| 954 |
|
get_navi_link = get_link_rel_next |
| 955 |
|
|
| 956 |
|
@classmethod |
| 957 |
|
def get_comic_info(cls, soup, link): |
| 958 |
|
"""Get information about a particular comics.""" |
| 959 |
|
title = soup.find('h2', class_='post-title').string |
| 960 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 961 |
|
date_str = soup.find('span', class_='post-date').string |
| 962 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 963 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 964 |
|
return { |
| 965 |
|
'img': [i['src'] for i in imgs], |
| 966 |
|
'title': title, |
| 967 |
|
'author': author, |
| 968 |
|
'month': day.month, |
| 969 |
|
'year': day.year, |
| 970 |
|
'day': day.day, |
| 971 |
|
} |
| 972 |
|
|
| 973 |
|
|
|
@@ 747-768 (lines=22) @@
|
| 744 |
|
} |
| 745 |
|
|
| 746 |
|
|
| 747 |
|
class AngryAtNothing(GenericDeletedComic, GenericNavigableComic): |
| 748 |
|
"""Class to retrieve Angry at Nothing comics.""" |
| 749 |
|
# Also on http://tapastic.com/series/Comics-yeah-definitely-comics- |
| 750 |
|
# Also on http://angryatnothing.tumblr.com |
| 751 |
|
name = 'angry' |
| 752 |
|
long_name = 'Angry At Nothing' |
| 753 |
|
url = 'http://www.angryatnothing.net' |
| 754 |
|
get_first_comic_link = get_div_navfirst_a |
| 755 |
|
get_navi_link = get_a_rel_next |
| 756 |
|
|
| 757 |
|
@classmethod |
| 758 |
|
def get_comic_info(cls, soup, link): |
| 759 |
|
"""Get information about a particular comics.""" |
| 760 |
|
title = soup.find('h1', class_='comic-title').find('a').string |
| 761 |
|
date_str = soup.find('header', class_='comic-meta entry-meta').find('a').string |
| 762 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 763 |
|
imgs = soup.find_all('meta', property='og:image') |
| 764 |
|
return { |
| 765 |
|
'title': title, |
| 766 |
|
'month': day.month, |
| 767 |
|
'year': day.year, |
| 768 |
|
'day': day.day, |
| 769 |
|
'img': [i['content'] for i in imgs], |
| 770 |
|
} |
| 771 |
|
|
|
@@ 1904-1930 (lines=27) @@
|
| 1901 |
|
} |
| 1902 |
|
|
| 1903 |
|
|
| 1904 |
|
class PicturesInBoxes(GenericNavigableComic): |
| 1905 |
|
"""Class to retrieve Pictures In Boxes comics.""" |
| 1906 |
|
# Also on https://picturesinboxescomic.tumblr.com |
| 1907 |
|
name = 'picturesinboxes' |
| 1908 |
|
long_name = 'Pictures in Boxes' |
| 1909 |
|
url = 'http://www.picturesinboxes.com' |
| 1910 |
|
get_navi_link = get_a_navi_navinext |
| 1911 |
|
get_first_comic_link = simulate_first_link |
| 1912 |
|
first_url = 'http://www.picturesinboxes.com/2013/10/26/tetris/' |
| 1913 |
|
|
| 1914 |
|
@classmethod |
| 1915 |
|
def get_comic_info(cls, soup, link): |
| 1916 |
|
"""Get information about a particular comics.""" |
| 1917 |
|
title = soup.find('h2', class_='post-title').string |
| 1918 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1919 |
|
date_str = soup.find('span', class_='post-date').string |
| 1920 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1921 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 1922 |
|
assert imgs |
| 1923 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 1924 |
|
return { |
| 1925 |
|
'day': day.day, |
| 1926 |
|
'month': day.month, |
| 1927 |
|
'year': day.year, |
| 1928 |
|
'img': [i['src'] for i in imgs], |
| 1929 |
|
'title': title, |
| 1930 |
|
'author': author, |
| 1931 |
|
} |
| 1932 |
|
|
| 1933 |
|
|
|
@@ 1792-1816 (lines=25) @@
|
| 1789 |
|
} |
| 1790 |
|
|
| 1791 |
|
|
| 1792 |
|
class MouseBearComedy(GenericComicNotWorking): # Website has changed |
| 1793 |
|
"""Class to retrieve Mouse Bear Comedy comics.""" |
| 1794 |
|
# Also on http://mousebearcomedy.tumblr.com |
| 1795 |
|
name = 'mousebear' |
| 1796 |
|
long_name = 'Mouse Bear Comedy' |
| 1797 |
|
url = 'http://www.mousebearcomedy.com' |
| 1798 |
|
get_first_comic_link = get_a_navi_navifirst |
| 1799 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 1800 |
|
|
| 1801 |
|
@classmethod |
| 1802 |
|
def get_comic_info(cls, soup, link): |
| 1803 |
|
"""Get information about a particular comics.""" |
| 1804 |
|
title = soup.find('h2', class_='post-title').string |
| 1805 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 1806 |
|
date_str = soup.find("span", class_="post-date").string |
| 1807 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1808 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 1809 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 1810 |
|
return { |
| 1811 |
|
'day': day.day, |
| 1812 |
|
'month': day.month, |
| 1813 |
|
'year': day.year, |
| 1814 |
|
'img': [i['src'] for i in imgs], |
| 1815 |
|
'title': title, |
| 1816 |
|
'author': author, |
| 1817 |
|
} |
| 1818 |
|
|
| 1819 |
|
|
|
@@ 2883-2907 (lines=25) @@
|
| 2880 |
|
first_url = 'http://www.commitstrip.com/fr/2012/02/22/interview/' |
| 2881 |
|
|
| 2882 |
|
|
| 2883 |
|
class CommitStripEn(GenericCommitStrip): |
| 2884 |
|
"""Class to retrieve Commit Strips in English.""" |
| 2885 |
|
name = 'commit_en' |
| 2886 |
|
long_name = 'Commit Strip (En)' |
| 2887 |
|
url = 'http://www.commitstrip.com/en' |
| 2888 |
|
first_url = 'http://www.commitstrip.com/en/2012/02/22/interview/' |
| 2889 |
|
|
| 2890 |
|
|
| 2891 |
|
class GenericBoumerie(GenericNavigableComic): |
| 2892 |
|
"""Generic class to retrieve Boumeries comics in different languages.""" |
| 2893 |
|
# Also on http://boumeries.tumblr.com |
| 2894 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2895 |
|
get_navi_link = get_link_rel_next |
| 2896 |
|
date_format = NotImplemented |
| 2897 |
|
lang = NotImplemented |
| 2898 |
|
|
| 2899 |
|
@classmethod |
| 2900 |
|
def get_comic_info(cls, soup, link): |
| 2901 |
|
"""Get information about a particular comics.""" |
| 2902 |
|
title = soup.find('h2', class_='post-title').string |
| 2903 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 2904 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2905 |
|
date_str = soup.find('span', class_='post-date').string |
| 2906 |
|
day = string_to_date(date_str, cls.date_format, cls.lang) |
| 2907 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2908 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2909 |
|
return { |
| 2910 |
|
'short_url': short_url, |
|
@@ 2629-2654 (lines=26) @@
|
| 2626 |
|
return { |
| 2627 |
|
'img': [i['src'] for i in imgs], |
| 2628 |
|
'title': title, |
| 2629 |
|
'alt': alt, |
| 2630 |
|
'author': author, |
| 2631 |
|
'day': day.day, |
| 2632 |
|
'month': day.month, |
| 2633 |
|
'year': day.year |
| 2634 |
|
} |
| 2635 |
|
|
| 2636 |
|
|
| 2637 |
|
class TheAwkwardYeti(GenericNavigableComic): |
| 2638 |
|
"""Class to retrieve The Awkward Yeti comics.""" |
| 2639 |
|
# Also on http://www.gocomics.com/the-awkward-yeti |
| 2640 |
|
# Also on http://larstheyeti.tumblr.com |
| 2641 |
|
# Also on https://tapastic.com/series/TheAwkwardYeti |
| 2642 |
|
name = 'yeti' |
| 2643 |
|
long_name = 'The Awkward Yeti' |
| 2644 |
|
url = 'http://theawkwardyeti.com' |
| 2645 |
|
_categories = ('YETI', ) |
| 2646 |
|
get_first_comic_link = get_a_navi_navifirst |
| 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 |
|
date_str = soup.find("span", class_="post-date").string |
| 2654 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2655 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2656 |
|
assert all(idx > 0 or i['alt'] == i['title'] for idx, i in enumerate(imgs)) |
| 2657 |
|
return { |
|
@@ 2571-2595 (lines=25) @@
|
| 2568 |
|
return { |
| 2569 |
|
'img': [i['src'] for i in imgs], |
| 2570 |
|
'title': title, |
| 2571 |
|
'alt': alt, |
| 2572 |
|
'author': author, |
| 2573 |
|
'day': day.day, |
| 2574 |
|
'month': day.month, |
| 2575 |
|
'year': day.year |
| 2576 |
|
} |
| 2577 |
|
|
| 2578 |
|
|
| 2579 |
|
class EveryDayBlues(GenericDeletedComic, GenericNavigableComic): |
| 2580 |
|
"""Class to retrieve EveryDayBlues Comics.""" |
| 2581 |
|
name = "blues" |
| 2582 |
|
long_name = "Every Day Blues" |
| 2583 |
|
url = "http://everydayblues.net" |
| 2584 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2585 |
|
get_navi_link = get_link_rel_next |
| 2586 |
|
|
| 2587 |
|
@classmethod |
| 2588 |
|
def get_comic_info(cls, soup, link): |
| 2589 |
|
"""Get information about a particular comics.""" |
| 2590 |
|
title = soup.find("h2", class_="post-title").string |
| 2591 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2592 |
|
date_str = soup.find("span", class_="post-date").string |
| 2593 |
|
day = string_to_date(date_str, "%d. %B %Y", "de_DE.utf8") |
| 2594 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2595 |
|
assert all(i['alt'] == i['title'] == title for i in imgs) |
| 2596 |
|
assert len(imgs) <= 1, imgs |
| 2597 |
|
return { |
| 2598 |
|
'img': [i['src'] for i in imgs], |
|
@@ 2740-2768 (lines=29) @@
|
| 2737 |
|
return { |
| 2738 |
|
'img': [i['src'] for i in imgs], |
| 2739 |
|
'title': title, |
| 2740 |
|
'alt': alt, |
| 2741 |
|
'author': author, |
| 2742 |
|
'day': day.day, |
| 2743 |
|
'month': day.month, |
| 2744 |
|
'year': day.year |
| 2745 |
|
} |
| 2746 |
|
|
| 2747 |
|
|
| 2748 |
|
class TalesOfAbsurdity(GenericNavigableComic): |
| 2749 |
|
"""Class to retrieve Tales Of Absurdity comics.""" |
| 2750 |
|
# Also on http://tapastic.com/series/Tales-Of-Absurdity |
| 2751 |
|
# Also on http://talesofabsurdity.tumblr.com |
| 2752 |
|
name = 'absurdity' |
| 2753 |
|
long_name = 'Tales of Absurdity' |
| 2754 |
|
url = 'http://talesofabsurdity.com' |
| 2755 |
|
_categories = ('ABSURDITY', ) |
| 2756 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2757 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2758 |
|
|
| 2759 |
|
@classmethod |
| 2760 |
|
def get_comic_info(cls, soup, link): |
| 2761 |
|
"""Get information about a particular comics.""" |
| 2762 |
|
title = soup.find('h2', class_='post-title').string |
| 2763 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2764 |
|
date_str = soup.find("span", class_="post-date").string |
| 2765 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2766 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2767 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2768 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2769 |
|
return { |
| 2770 |
|
'img': [i['src'] for i in imgs], |
| 2771 |
|
'title': title, |
|
@@ 2678-2706 (lines=29) @@
|
| 2675 |
|
def get_comic_info(cls, soup, link): |
| 2676 |
|
"""Get information about a particular comics.""" |
| 2677 |
|
post = soup.find('div', class_='post-content') |
| 2678 |
|
title = post.find('h2', class_='post-title').string |
| 2679 |
|
imgs = post.find("div", class_="entry").find_all("img") |
| 2680 |
|
return { |
| 2681 |
|
'title': title, |
| 2682 |
|
'img': [i['src'] for i in imgs], |
| 2683 |
|
} |
| 2684 |
|
|
| 2685 |
|
|
| 2686 |
|
class MisterAndMe(GenericNavigableComic): |
| 2687 |
|
"""Class to retrieve Mister & Me Comics.""" |
| 2688 |
|
# Also on http://www.gocomics.com/mister-and-me |
| 2689 |
|
# Also on https://tapastic.com/series/Mister-and-Me |
| 2690 |
|
name = 'mister' |
| 2691 |
|
long_name = 'Mister & Me' |
| 2692 |
|
url = 'http://www.mister-and-me.com' |
| 2693 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2694 |
|
get_navi_link = get_link_rel_next |
| 2695 |
|
|
| 2696 |
|
@classmethod |
| 2697 |
|
def get_comic_info(cls, soup, link): |
| 2698 |
|
"""Get information about a particular comics.""" |
| 2699 |
|
title = soup.find('h2', class_='post-title').string |
| 2700 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2701 |
|
date_str = soup.find("span", class_="post-date").string |
| 2702 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2703 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2704 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2705 |
|
assert len(imgs) <= 1, imgs |
| 2706 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2707 |
|
return { |
| 2708 |
|
'img': [i['src'] for i in imgs], |
| 2709 |
|
'title': title, |
|
@@ 2966-2992 (lines=27) @@
|
| 2963 |
|
return { |
| 2964 |
|
'title': title, |
| 2965 |
|
'description': desc, |
| 2966 |
|
'url2': short_url, |
| 2967 |
|
'img': [i['src'] for i in imgs], |
| 2968 |
|
'month': day.month, |
| 2969 |
|
'year': day.year, |
| 2970 |
|
'day': day.day, |
| 2971 |
|
} |
| 2972 |
|
|
| 2973 |
|
|
| 2974 |
|
class Optipess(GenericNavigableComic): |
| 2975 |
|
"""Class to retrieve Optipess comics.""" |
| 2976 |
|
name = 'optipess' |
| 2977 |
|
long_name = 'Optipess' |
| 2978 |
|
url = 'http://www.optipess.com' |
| 2979 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2980 |
|
get_navi_link = get_link_rel_next |
| 2981 |
|
|
| 2982 |
|
@classmethod |
| 2983 |
|
def get_comic_info(cls, soup, link): |
| 2984 |
|
"""Get information about a particular comics.""" |
| 2985 |
|
title = soup.find('h2', class_='post-title').string |
| 2986 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2987 |
|
comic = soup.find('div', id='comic') |
| 2988 |
|
imgs = comic.find_all('img') if comic else [] |
| 2989 |
|
alt = imgs[0]['title'] if imgs else "" |
| 2990 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2991 |
|
date_str = soup.find('span', class_='post-date').string |
| 2992 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2993 |
|
return { |
| 2994 |
|
'title': title, |
| 2995 |
|
'alt': alt, |
|
@@ 2599-2625 (lines=27) @@
|
| 2596 |
|
assert len(imgs) <= 1, imgs |
| 2597 |
|
return { |
| 2598 |
|
'img': [i['src'] for i in imgs], |
| 2599 |
|
'title': title, |
| 2600 |
|
'author': author, |
| 2601 |
|
'day': day.day, |
| 2602 |
|
'month': day.month, |
| 2603 |
|
'year': day.year |
| 2604 |
|
} |
| 2605 |
|
|
| 2606 |
|
|
| 2607 |
|
class BiterComics(GenericNavigableComic): |
| 2608 |
|
"""Class to retrieve Biter Comics.""" |
| 2609 |
|
name = "biter" |
| 2610 |
|
long_name = "Biter Comics" |
| 2611 |
|
url = "http://www.bitercomics.com" |
| 2612 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2613 |
|
get_navi_link = get_link_rel_next |
| 2614 |
|
|
| 2615 |
|
@classmethod |
| 2616 |
|
def get_comic_info(cls, soup, link): |
| 2617 |
|
"""Get information about a particular comics.""" |
| 2618 |
|
title = soup.find("h1", class_="entry-title").string |
| 2619 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2620 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2621 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2622 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2623 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2624 |
|
assert len(imgs) == 1, imgs |
| 2625 |
|
alt = imgs[0]['alt'] |
| 2626 |
|
return { |
| 2627 |
|
'img': [i['src'] for i in imgs], |
| 2628 |
|
'title': title, |
|
@@ 2049-2075 (lines=27) @@
|
| 2046 |
|
_categories = ('TUNEYTOONS', ) |
| 2047 |
|
|
| 2048 |
|
|
| 2049 |
|
class CompletelySeriousComics(GenericNavigableComic): |
| 2050 |
|
"""Class to retrieve Completely Serious comics.""" |
| 2051 |
|
name = 'completelyserious' |
| 2052 |
|
long_name = 'Completely Serious Comics' |
| 2053 |
|
url = 'http://completelyseriouscomics.com' |
| 2054 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2055 |
|
get_navi_link = get_a_navi_navinext |
| 2056 |
|
|
| 2057 |
|
@classmethod |
| 2058 |
|
def get_comic_info(cls, soup, link): |
| 2059 |
|
"""Get information about a particular comics.""" |
| 2060 |
|
title = soup.find('h2', class_='post-title').string |
| 2061 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 2062 |
|
date_str = soup.find('span', class_='post-date').string |
| 2063 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 2064 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 2065 |
|
assert imgs |
| 2066 |
|
alt = imgs[0]['title'] |
| 2067 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 2068 |
|
return { |
| 2069 |
|
'month': day.month, |
| 2070 |
|
'year': day.year, |
| 2071 |
|
'day': day.day, |
| 2072 |
|
'img': [i['src'] for i in imgs], |
| 2073 |
|
'title': title, |
| 2074 |
|
'alt': alt, |
| 2075 |
|
'author': author, |
| 2076 |
|
} |
| 2077 |
|
|
| 2078 |
|
|
|
@@ 2772-2797 (lines=26) @@
|
| 2769 |
|
return { |
| 2770 |
|
'img': [i['src'] for i in imgs], |
| 2771 |
|
'title': title, |
| 2772 |
|
'alt': alt, |
| 2773 |
|
'author': author, |
| 2774 |
|
'day': day.day, |
| 2775 |
|
'month': day.month, |
| 2776 |
|
'year': day.year |
| 2777 |
|
} |
| 2778 |
|
|
| 2779 |
|
|
| 2780 |
|
class EndlessOrigami(GenericComicNotWorking, GenericNavigableComic): # Nav not working |
| 2781 |
|
"""Class to retrieve Endless Origami Comics.""" |
| 2782 |
|
name = "origami" |
| 2783 |
|
long_name = "Endless Origami" |
| 2784 |
|
url = "http://endlessorigami.com" |
| 2785 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2786 |
|
get_navi_link = get_link_rel_next |
| 2787 |
|
|
| 2788 |
|
@classmethod |
| 2789 |
|
def get_comic_info(cls, soup, link): |
| 2790 |
|
"""Get information about a particular comics.""" |
| 2791 |
|
title = soup.find('h2', class_='post-title').string |
| 2792 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2793 |
|
date_str = soup.find("span", class_="post-date").string |
| 2794 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2795 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2796 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2797 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2798 |
|
return { |
| 2799 |
|
'img': [i['src'] for i in imgs], |
| 2800 |
|
'title': title, |
|
@@ 2260-2285 (lines=26) @@
|
| 2257 |
|
return reversed(get_soup_at_url(archive_url).find('tbody').find_all('tr')) |
| 2258 |
|
|
| 2259 |
|
|
| 2260 |
|
class HappleTea(GenericNavigableComic): |
| 2261 |
|
"""Class to retrieve Happle Tea Comics.""" |
| 2262 |
|
name = 'happletea' |
| 2263 |
|
long_name = 'Happle Tea' |
| 2264 |
|
url = 'http://www.happletea.com' |
| 2265 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2266 |
|
get_navi_link = get_link_rel_next |
| 2267 |
|
|
| 2268 |
|
@classmethod |
| 2269 |
|
def get_comic_info(cls, soup, link): |
| 2270 |
|
"""Get information about a particular comics.""" |
| 2271 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2272 |
|
post = soup.find('div', class_='post-content') |
| 2273 |
|
title = post.find('h2', class_='post-title').string |
| 2274 |
|
author = post.find('a', rel='author').string |
| 2275 |
|
date_str = post.find('span', class_='post-date').string |
| 2276 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2277 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2278 |
|
return { |
| 2279 |
|
'title': title, |
| 2280 |
|
'img': [i['src'] for i in imgs], |
| 2281 |
|
'alt': ''.join(i['alt'] for i in imgs), |
| 2282 |
|
'month': day.month, |
| 2283 |
|
'year': day.year, |
| 2284 |
|
'day': day.day, |
| 2285 |
|
'author': author, |
| 2286 |
|
} |
| 2287 |
|
|
| 2288 |
|
|
|
@@ 2441-2465 (lines=25) @@
|
| 2438 |
|
} |
| 2439 |
|
|
| 2440 |
|
|
| 2441 |
|
class LonnieMillsap(GenericNavigableComic): |
| 2442 |
|
"""Class to retrieve Lonnie Millsap's comics.""" |
| 2443 |
|
name = 'millsap' |
| 2444 |
|
long_name = 'Lonnie Millsap' |
| 2445 |
|
url = 'http://www.lonniemillsap.com' |
| 2446 |
|
get_navi_link = get_link_rel_next |
| 2447 |
|
get_first_comic_link = simulate_first_link |
| 2448 |
|
first_url = 'http://www.lonniemillsap.com/?p=42' |
| 2449 |
|
|
| 2450 |
|
@classmethod |
| 2451 |
|
def get_comic_info(cls, soup, link): |
| 2452 |
|
"""Get information about a particular comics.""" |
| 2453 |
|
title = soup.find('h2', class_='post-title').string |
| 2454 |
|
post = soup.find('div', class_='post-content') |
| 2455 |
|
author = post.find("span", class_="post-author").find("a").string |
| 2456 |
|
date_str = post.find("span", class_="post-date").string |
| 2457 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2458 |
|
imgs = post.find("div", class_="entry").find_all("img") |
| 2459 |
|
return { |
| 2460 |
|
'title': title, |
| 2461 |
|
'author': author, |
| 2462 |
|
'img': [i['src'] for i in imgs], |
| 2463 |
|
'month': day.month, |
| 2464 |
|
'year': day.year, |
| 2465 |
|
'day': day.day, |
| 2466 |
|
} |
| 2467 |
|
|
| 2468 |
|
|
|
@@ 2137-2161 (lines=25) @@
|
| 2134 |
|
} |
| 2135 |
|
|
| 2136 |
|
|
| 2137 |
|
class ChuckleADuck(GenericNavigableComic): |
| 2138 |
|
"""Class to retrieve Chuckle-A-Duck comics.""" |
| 2139 |
|
name = 'chuckleaduck' |
| 2140 |
|
long_name = 'Chuckle-A-duck' |
| 2141 |
|
url = 'http://chuckleaduck.com' |
| 2142 |
|
get_first_comic_link = get_div_navfirst_a |
| 2143 |
|
get_navi_link = get_link_rel_next |
| 2144 |
|
|
| 2145 |
|
@classmethod |
| 2146 |
|
def get_comic_info(cls, soup, link): |
| 2147 |
|
"""Get information about a particular comics.""" |
| 2148 |
|
date_str = soup.find('span', class_='post-date').string |
| 2149 |
|
day = string_to_date(remove_st_nd_rd_th_from_date(date_str), "%B %d, %Y") |
| 2150 |
|
author = soup.find('span', class_='post-author').string |
| 2151 |
|
div = soup.find('div', id='comic') |
| 2152 |
|
imgs = div.find_all('img') if div else [] |
| 2153 |
|
title = imgs[0]['title'] if imgs else "" |
| 2154 |
|
assert all(i['title'] == i['alt'] == title for i in imgs) |
| 2155 |
|
return { |
| 2156 |
|
'month': day.month, |
| 2157 |
|
'year': day.year, |
| 2158 |
|
'day': day.day, |
| 2159 |
|
'img': [i['src'] for i in imgs], |
| 2160 |
|
'title': title, |
| 2161 |
|
'author': author, |
| 2162 |
|
} |
| 2163 |
|
|
| 2164 |
|
|
|
@@ 3294-3317 (lines=24) @@
|
| 3291 |
|
@classmethod |
| 3292 |
|
def get_comic_info(cls, soup, link): |
| 3293 |
|
"""Get information about a particular comics.""" |
| 3294 |
|
title = soup.find('title').string |
| 3295 |
|
imgs = soup.find_all('meta', property='og:image') |
| 3296 |
|
return { |
| 3297 |
|
'img': [i['content'] for i in imgs], |
| 3298 |
|
'title': title, |
| 3299 |
|
} |
| 3300 |
|
|
| 3301 |
|
|
| 3302 |
|
class Ubertool(GenericNavigableComic): |
| 3303 |
|
"""Class to retrieve Ubertool comics.""" |
| 3304 |
|
# Also on https://ubertool.tumblr.com |
| 3305 |
|
# Also on https://tapastic.com/series/ubertool |
| 3306 |
|
name = 'ubertool' |
| 3307 |
|
long_name = 'Ubertool' |
| 3308 |
|
url = 'http://ubertoolcomic.com' |
| 3309 |
|
_categories = ('UBERTOOL', ) |
| 3310 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 3311 |
|
get_navi_link = get_a_comicnavbase_comicnavnext |
| 3312 |
|
|
| 3313 |
|
@classmethod |
| 3314 |
|
def get_comic_info(cls, soup, link): |
| 3315 |
|
"""Get information about a particular comics.""" |
| 3316 |
|
title = soup.find('h2', class_='post-title').string |
| 3317 |
|
date_str = soup.find('span', class_='post-date').string |
| 3318 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 3319 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 3320 |
|
return { |
|
@@ 694-716 (lines=23) @@
|
| 691 |
|
} |
| 692 |
|
|
| 693 |
|
|
| 694 |
|
class PenelopeBagieu(GenericNavigableComic): |
| 695 |
|
"""Class to retrieve comics from Penelope Bagieu's blog.""" |
| 696 |
|
name = 'bagieu' |
| 697 |
|
long_name = 'Ma vie est tout a fait fascinante (Bagieu)' |
| 698 |
|
url = 'http://www.penelope-jolicoeur.com' |
| 699 |
|
_categories = ('FRANCAIS', ) |
| 700 |
|
get_navi_link = get_link_rel_next |
| 701 |
|
get_first_comic_link = simulate_first_link |
| 702 |
|
first_url = 'http://www.penelope-jolicoeur.com/2007/02/ma-vie-mon-oeuv.html' |
| 703 |
|
|
| 704 |
|
@classmethod |
| 705 |
|
def get_comic_info(cls, soup, link): |
| 706 |
|
"""Get information about a particular comics.""" |
| 707 |
|
date_str = soup.find('h2', class_='date-header').string |
| 708 |
|
day = string_to_date(date_str, "%A %d %B %Y", "fr_FR.utf8") |
| 709 |
|
imgs = soup.find('div', class_='entry-body').find_all('img') |
| 710 |
|
title = soup.find('h3', class_='entry-header').string |
| 711 |
|
return { |
| 712 |
|
'title': title, |
| 713 |
|
'img': [i['src'] for i in imgs], |
| 714 |
|
'month': day.month, |
| 715 |
|
'year': day.year, |
| 716 |
|
'day': day.day, |
| 717 |
|
} |
| 718 |
|
|
| 719 |
|
|
|
@@ 3567-3587 (lines=21) @@
|
| 3564 |
|
'day': day.day, |
| 3565 |
|
'month': day.month, |
| 3566 |
|
'year': day.year, |
| 3567 |
|
} |
| 3568 |
|
|
| 3569 |
|
|
| 3570 |
|
class GenericBlogspotComic(GenericNavigableComic): |
| 3571 |
|
"""Generic class to retrieve comics from Blogspot.""" |
| 3572 |
|
get_first_comic_link = simulate_first_link |
| 3573 |
|
first_url = NotImplemented |
| 3574 |
|
_categories = ('BLOGSPOT', ) |
| 3575 |
|
|
| 3576 |
|
@classmethod |
| 3577 |
|
def get_navi_link(cls, last_soup, next_): |
| 3578 |
|
"""Get link to next or previous comic.""" |
| 3579 |
|
return last_soup.find('a', id='Blog1_blog-pager-newer-link' if next_ else 'Blog1_blog-pager-older-link') |
| 3580 |
|
|
| 3581 |
|
|
| 3582 |
|
class TuMourrasMoinsBete(GenericBlogspotComic): |
| 3583 |
|
"""Class to retrieve Tu Mourras Moins Bete comics.""" |
| 3584 |
|
name = 'mourrasmoinsbete' |
| 3585 |
|
long_name = 'Tu Mourras Moins Bete' |
| 3586 |
|
url = 'http://tumourrasmoinsbete.blogspot.fr' |
| 3587 |
|
_categories = ('FRANCAIS', ) |
| 3588 |
|
first_url = 'http://tumourrasmoinsbete.blogspot.fr/2008/06/essai.html' |
| 3589 |
|
|
| 3590 |
|
@classmethod |
|
@@ 2801-2821 (lines=21) @@
|
| 2798 |
|
return { |
| 2799 |
|
'img': [i['src'] for i in imgs], |
| 2800 |
|
'title': title, |
| 2801 |
|
'alt': alt, |
| 2802 |
|
'author': author, |
| 2803 |
|
'day': day.day, |
| 2804 |
|
'month': day.month, |
| 2805 |
|
'year': day.year |
| 2806 |
|
} |
| 2807 |
|
|
| 2808 |
|
|
| 2809 |
|
class PlanC(GenericNavigableComic): |
| 2810 |
|
"""Class to retrieve Plan C comics.""" |
| 2811 |
|
name = 'planc' |
| 2812 |
|
long_name = 'Plan C' |
| 2813 |
|
url = 'http://www.plancomic.com' |
| 2814 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2815 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2816 |
|
|
| 2817 |
|
@classmethod |
| 2818 |
|
def get_comic_info(cls, soup, link): |
| 2819 |
|
"""Get information about a particular comics.""" |
| 2820 |
|
title = soup.find('h2', class_='post-title').string |
| 2821 |
|
date_str = soup.find("span", class_="post-date").string |
| 2822 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2823 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 2824 |
|
return { |
|
@@ 1934-1959 (lines=26) @@
|
| 1931 |
|
} |
| 1932 |
|
|
| 1933 |
|
|
| 1934 |
|
class Penmen(GenericComicNotWorking, GenericNavigableComic): |
| 1935 |
|
"""Class to retrieve Penmen comics.""" |
| 1936 |
|
name = 'penmen' |
| 1937 |
|
long_name = 'Penmen' |
| 1938 |
|
url = 'http://penmen.com' |
| 1939 |
|
get_navi_link = get_link_rel_next |
| 1940 |
|
get_first_comic_link = simulate_first_link |
| 1941 |
|
first_url = 'http://penmen.com/index.php/2016/09/12/penmen-announces-grin-big-brand-clothing/' |
| 1942 |
|
|
| 1943 |
|
@classmethod |
| 1944 |
|
def get_comic_info(cls, soup, link): |
| 1945 |
|
"""Get information about a particular comics.""" |
| 1946 |
|
title = soup.find('title').string |
| 1947 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 1948 |
|
short_url = soup.find('link', rel='shortlink')['href'] |
| 1949 |
|
tags = ' '.join(t.string for t in soup.find_all('a', rel='tag')) |
| 1950 |
|
date_str = soup.find('time')['datetime'][:10] |
| 1951 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 1952 |
|
return { |
| 1953 |
|
'title': title, |
| 1954 |
|
'short_url': short_url, |
| 1955 |
|
'img': [i['src'] for i in imgs], |
| 1956 |
|
'tags': tags, |
| 1957 |
|
'month': day.month, |
| 1958 |
|
'year': day.year, |
| 1959 |
|
'day': day.day, |
| 1960 |
|
} |
| 1961 |
|
|
| 1962 |
|
|
|
@@ 1875-1900 (lines=26) @@
|
| 1872 |
|
} |
| 1873 |
|
|
| 1874 |
|
|
| 1875 |
|
class SafelyEndangered(GenericNavigableComic): |
| 1876 |
|
"""Class to retrieve Safely Endangered comics.""" |
| 1877 |
|
# Also on http://tumblr.safelyendangered.com |
| 1878 |
|
name = 'endangered' |
| 1879 |
|
long_name = 'Safely Endangered' |
| 1880 |
|
url = 'http://www.safelyendangered.com' |
| 1881 |
|
get_navi_link = get_link_rel_next |
| 1882 |
|
get_first_comic_link = simulate_first_link |
| 1883 |
|
first_url = 'http://www.safelyendangered.com/comic/ignored/' |
| 1884 |
|
|
| 1885 |
|
@classmethod |
| 1886 |
|
def get_comic_info(cls, soup, link): |
| 1887 |
|
"""Get information about a particular comics.""" |
| 1888 |
|
title = soup.find('h2', class_='post-title').string |
| 1889 |
|
date_str = soup.find('span', class_='post-date').string |
| 1890 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 1891 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1892 |
|
alt = imgs[0]['alt'] |
| 1893 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 1894 |
|
return { |
| 1895 |
|
'day': day.day, |
| 1896 |
|
'month': day.month, |
| 1897 |
|
'year': day.year, |
| 1898 |
|
'img': [i['src'] for i in imgs], |
| 1899 |
|
'title': title, |
| 1900 |
|
'alt': alt, |
| 1901 |
|
} |
| 1902 |
|
|
| 1903 |
|
|
|
@@ 1230-1256 (lines=27) @@
|
| 1227 |
|
} |
| 1228 |
|
|
| 1229 |
|
|
| 1230 |
|
class ToonHole(GenericNavigableComic): |
| 1231 |
|
"""Class to retrieve Toon Holes comics.""" |
| 1232 |
|
# Also on http://tapastic.com/series/TOONHOLE |
| 1233 |
|
name = 'toonhole' |
| 1234 |
|
long_name = 'Toon Hole' |
| 1235 |
|
url = 'http://www.toonhole.com' |
| 1236 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 1237 |
|
get_navi_link = get_a_comicnavbase_comicnavnext |
| 1238 |
|
|
| 1239 |
|
@classmethod |
| 1240 |
|
def get_comic_info(cls, soup, link): |
| 1241 |
|
"""Get information about a particular comics.""" |
| 1242 |
|
date_str = soup.find('div', class_='entry-meta').contents[0].strip() |
| 1243 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 1244 |
|
imgs = soup.find('div', id='comic').find_all('img') |
| 1245 |
|
if imgs: |
| 1246 |
|
img = imgs[0] |
| 1247 |
|
title = img['alt'] |
| 1248 |
|
assert img['title'] == title |
| 1249 |
|
else: |
| 1250 |
|
title = "" |
| 1251 |
|
return { |
| 1252 |
|
'title': title, |
| 1253 |
|
'month': day.month, |
| 1254 |
|
'year': day.year, |
| 1255 |
|
'day': day.day, |
| 1256 |
|
'img': [convert_iri_to_plain_ascii_uri(i['src']) for i in imgs], |
| 1257 |
|
} |
| 1258 |
|
|
| 1259 |
|
|
|
@@ 3476-3500 (lines=25) @@
|
| 3473 |
|
@classmethod |
| 3474 |
|
def get_comic_info(cls, soup, link): |
| 3475 |
|
"""Get information about a particular comics.""" |
| 3476 |
|
title = soup.find("h1", class_="entry-title").string |
| 3477 |
|
imgs = soup.find('div', class_='entry-content').find_all('img') |
| 3478 |
|
return { |
| 3479 |
|
'title': title, |
| 3480 |
|
'img': [i['src'] for i in imgs], |
| 3481 |
|
} |
| 3482 |
|
|
| 3483 |
|
|
| 3484 |
|
class MacadamValley(GenericNavigableComic): |
| 3485 |
|
"""Class to retrieve Macadam Valley comics.""" |
| 3486 |
|
name = 'macadamvalley' |
| 3487 |
|
long_name = 'Macadam Valley' |
| 3488 |
|
url = 'http://macadamvalley.com' |
| 3489 |
|
get_navi_link = get_a_rel_next |
| 3490 |
|
get_first_comic_link = simulate_first_link |
| 3491 |
|
first_url = 'http://macadamvalley.com/le-debut-de-la-fin/' |
| 3492 |
|
|
| 3493 |
|
@classmethod |
| 3494 |
|
def get_comic_info(cls, soup, link): |
| 3495 |
|
"""Get information about a particular comics.""" |
| 3496 |
|
title = soup.find("h1", class_="entry-title").string |
| 3497 |
|
img = soup.find('div', class_='entry-content').find('img') |
| 3498 |
|
date_str = soup.find('time', class_='entry-date')['datetime'] |
| 3499 |
|
date_str = date_str[:10] |
| 3500 |
|
day = string_to_date(date_str, "%Y-%m-%d") |
| 3501 |
|
author = soup.find('a', rel='author').string |
| 3502 |
|
return { |
| 3503 |
|
'title': title, |