|
@@ 2461-2480 (lines=20) @@
|
| 2458 |
|
return link |
| 2459 |
|
return None |
| 2460 |
|
|
| 2461 |
|
@classmethod |
| 2462 |
|
def get_comic_info(cls, soup, link): |
| 2463 |
|
"""Get information about a particular comics.""" |
| 2464 |
|
title = soup.find('meta', attrs={'name': 'description'})["content"] |
| 2465 |
|
description = soup.find('div', itemprop='articleBody').text |
| 2466 |
|
author = soup.find('span', itemprop='author copyrightHolder').string |
| 2467 |
|
imgs = soup.find_all('img', itemprop='image') |
| 2468 |
|
assert all(i['title'] == i['alt'] for i in imgs) |
| 2469 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2470 |
|
date_str = soup.find('time', itemprop='datePublished')["datetime"] |
| 2471 |
|
day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S") |
| 2472 |
|
return { |
| 2473 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 2474 |
|
'month': day.month, |
| 2475 |
|
'year': day.year, |
| 2476 |
|
'day': day.day, |
| 2477 |
|
'author': author, |
| 2478 |
|
'title': title, |
| 2479 |
|
'alt': alt, |
| 2480 |
|
'description': description, |
| 2481 |
|
} |
| 2482 |
|
|
| 2483 |
|
|
|
@@ 2660-2678 (lines=19) @@
|
| 2657 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2658 |
|
get_navi_link = get_link_rel_next |
| 2659 |
|
|
| 2660 |
|
@classmethod |
| 2661 |
|
def get_comic_info(cls, soup, link): |
| 2662 |
|
"""Get information about a particular comics.""" |
| 2663 |
|
title = soup.find('h2', class_='post-title').string |
| 2664 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2665 |
|
date_str = soup.find("span", class_="post-date").string |
| 2666 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2667 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2668 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2669 |
|
assert len(imgs) <= 1, imgs |
| 2670 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2671 |
|
return { |
| 2672 |
|
'img': [i['src'] for i in imgs], |
| 2673 |
|
'title': title, |
| 2674 |
|
'alt': alt, |
| 2675 |
|
'author': author, |
| 2676 |
|
'day': day.day, |
| 2677 |
|
'month': day.month, |
| 2678 |
|
'year': day.year |
| 2679 |
|
} |
| 2680 |
|
|
| 2681 |
|
|
|
@@ 2630-2648 (lines=19) @@
|
| 2627 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2628 |
|
get_navi_link = get_link_rel_next |
| 2629 |
|
|
| 2630 |
|
@classmethod |
| 2631 |
|
def get_comic_info(cls, soup, link): |
| 2632 |
|
"""Get information about a particular comics.""" |
| 2633 |
|
title = soup.find('h2', class_='post-title').string |
| 2634 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2635 |
|
date_str = soup.find("span", class_="post-date").string |
| 2636 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2637 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2638 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2639 |
|
assert len(imgs) <= 1, imgs |
| 2640 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2641 |
|
return { |
| 2642 |
|
'img': [i['src'] for i in imgs], |
| 2643 |
|
'title': title, |
| 2644 |
|
'alt': alt, |
| 2645 |
|
'author': author, |
| 2646 |
|
'day': day.day, |
| 2647 |
|
'month': day.month, |
| 2648 |
|
'year': day.year |
| 2649 |
|
} |
| 2650 |
|
|
| 2651 |
|
|
|
@@ 2549-2567 (lines=19) @@
|
| 2546 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2547 |
|
get_navi_link = get_link_rel_next |
| 2548 |
|
|
| 2549 |
|
@classmethod |
| 2550 |
|
def get_comic_info(cls, soup, link): |
| 2551 |
|
"""Get information about a particular comics.""" |
| 2552 |
|
title = soup.find("h1", class_="entry-title").string |
| 2553 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2554 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2555 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2556 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2557 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2558 |
|
assert len(imgs) == 1, imgs |
| 2559 |
|
alt = imgs[0]['alt'] |
| 2560 |
|
return { |
| 2561 |
|
'img': [i['src'] for i in imgs], |
| 2562 |
|
'title': title, |
| 2563 |
|
'alt': alt, |
| 2564 |
|
'author': author, |
| 2565 |
|
'day': day.day, |
| 2566 |
|
'month': day.month, |
| 2567 |
|
'year': day.year |
| 2568 |
|
} |
| 2569 |
|
|
| 2570 |
|
|
|
@@ 2024-2042 (lines=19) @@
|
| 2021 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2022 |
|
get_navi_link = get_a_navi_navinext |
| 2023 |
|
|
| 2024 |
|
@classmethod |
| 2025 |
|
def get_comic_info(cls, soup, link): |
| 2026 |
|
"""Get information about a particular comics.""" |
| 2027 |
|
title = soup.find('h2', class_='post-title').string |
| 2028 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 2029 |
|
date_str = soup.find('span', class_='post-date').string |
| 2030 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 2031 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 2032 |
|
assert imgs |
| 2033 |
|
alt = imgs[0]['title'] |
| 2034 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 2035 |
|
return { |
| 2036 |
|
'month': day.month, |
| 2037 |
|
'year': day.year, |
| 2038 |
|
'day': day.day, |
| 2039 |
|
'img': [i['src'] for i in imgs], |
| 2040 |
|
'title': title, |
| 2041 |
|
'alt': alt, |
| 2042 |
|
'author': author, |
| 2043 |
|
} |
| 2044 |
|
|
| 2045 |
|
|
|
@@ 2722-2739 (lines=18) @@
|
| 2719 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2720 |
|
get_navi_link = get_link_rel_next |
| 2721 |
|
|
| 2722 |
|
@classmethod |
| 2723 |
|
def get_comic_info(cls, soup, link): |
| 2724 |
|
"""Get information about a particular comics.""" |
| 2725 |
|
title = soup.find('h2', class_='post-title').string |
| 2726 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2727 |
|
date_str = soup.find("span", class_="post-date").string |
| 2728 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2729 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2730 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2731 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2732 |
|
return { |
| 2733 |
|
'img': [i['src'] for i in imgs], |
| 2734 |
|
'title': title, |
| 2735 |
|
'alt': alt, |
| 2736 |
|
'author': author, |
| 2737 |
|
'day': day.day, |
| 2738 |
|
'month': day.month, |
| 2739 |
|
'year': day.year |
| 2740 |
|
} |
| 2741 |
|
|
| 2742 |
|
|
|
@@ 2693-2710 (lines=18) @@
|
| 2690 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2691 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2692 |
|
|
| 2693 |
|
@classmethod |
| 2694 |
|
def get_comic_info(cls, soup, link): |
| 2695 |
|
"""Get information about a particular comics.""" |
| 2696 |
|
title = soup.find('h2', class_='post-title').string |
| 2697 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2698 |
|
date_str = soup.find("span", class_="post-date").string |
| 2699 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2700 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2701 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2702 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2703 |
|
return { |
| 2704 |
|
'img': [i['src'] for i in imgs], |
| 2705 |
|
'title': title, |
| 2706 |
|
'alt': alt, |
| 2707 |
|
'author': author, |
| 2708 |
|
'day': day.day, |
| 2709 |
|
'month': day.month, |
| 2710 |
|
'year': day.year |
| 2711 |
|
} |
| 2712 |
|
|
| 2713 |
|
|
|
@@ 2492-2509 (lines=18) @@
|
| 2489 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2490 |
|
get_navi_link = get_a_rel_next |
| 2491 |
|
|
| 2492 |
|
@classmethod |
| 2493 |
|
def get_comic_info(cls, soup, link): |
| 2494 |
|
"""Get information about a particular comics.""" |
| 2495 |
|
title = soup.find('h2', class_='post-title').string |
| 2496 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2497 |
|
date_str = soup.find("span", class_="post-date").string |
| 2498 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2499 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2500 |
|
alt = imgs[0]['alt'] |
| 2501 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2502 |
|
return { |
| 2503 |
|
'img': [i['src'] for i in imgs], |
| 2504 |
|
'title': title, |
| 2505 |
|
'alt': alt, |
| 2506 |
|
'author': author, |
| 2507 |
|
'day': day.day, |
| 2508 |
|
'month': day.month, |
| 2509 |
|
'year': day.year |
| 2510 |
|
} |
| 2511 |
|
|
| 2512 |
|
|
|
@@ 983-1000 (lines=18) @@
|
| 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 |
|
|