|
@@ 2443-2462 (lines=20) @@
|
| 2440 |
|
return link |
| 2441 |
|
return None |
| 2442 |
|
|
| 2443 |
|
@classmethod |
| 2444 |
|
def get_comic_info(cls, soup, link): |
| 2445 |
|
"""Get information about a particular comics.""" |
| 2446 |
|
title = soup.find('meta', attrs={'name': 'description'})["content"] |
| 2447 |
|
description = soup.find('div', itemprop='articleBody').text |
| 2448 |
|
author = soup.find('span', itemprop='author copyrightHolder').string |
| 2449 |
|
imgs = soup.find_all('img', itemprop='image') |
| 2450 |
|
assert all(i['title'] == i['alt'] for i in imgs) |
| 2451 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2452 |
|
date_str = soup.find('time', itemprop='datePublished')["datetime"] |
| 2453 |
|
day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S") |
| 2454 |
|
return { |
| 2455 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 2456 |
|
'month': day.month, |
| 2457 |
|
'year': day.year, |
| 2458 |
|
'day': day.day, |
| 2459 |
|
'author': author, |
| 2460 |
|
'title': title, |
| 2461 |
|
'alt': alt, |
| 2462 |
|
'description': description, |
| 2463 |
|
} |
| 2464 |
|
|
| 2465 |
|
|
|
@@ 2642-2660 (lines=19) @@
|
| 2639 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2640 |
|
get_navi_link = get_link_rel_next |
| 2641 |
|
|
| 2642 |
|
@classmethod |
| 2643 |
|
def get_comic_info(cls, soup, link): |
| 2644 |
|
"""Get information about a particular comics.""" |
| 2645 |
|
title = soup.find('h2', class_='post-title').string |
| 2646 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2647 |
|
date_str = soup.find("span", class_="post-date").string |
| 2648 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2649 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2650 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2651 |
|
assert len(imgs) <= 1 |
| 2652 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2653 |
|
return { |
| 2654 |
|
'img': [i['src'] for i in imgs], |
| 2655 |
|
'title': title, |
| 2656 |
|
'alt': alt, |
| 2657 |
|
'author': author, |
| 2658 |
|
'day': day.day, |
| 2659 |
|
'month': day.month, |
| 2660 |
|
'year': day.year |
| 2661 |
|
} |
| 2662 |
|
|
| 2663 |
|
|
|
@@ 2612-2630 (lines=19) @@
|
| 2609 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2610 |
|
get_navi_link = get_link_rel_next |
| 2611 |
|
|
| 2612 |
|
@classmethod |
| 2613 |
|
def get_comic_info(cls, soup, link): |
| 2614 |
|
"""Get information about a particular comics.""" |
| 2615 |
|
title = soup.find('h2', class_='post-title').string |
| 2616 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2617 |
|
date_str = soup.find("span", class_="post-date").string |
| 2618 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2619 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2620 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2621 |
|
assert len(imgs) <= 1 |
| 2622 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2623 |
|
return { |
| 2624 |
|
'img': [i['src'] for i in imgs], |
| 2625 |
|
'title': title, |
| 2626 |
|
'alt': alt, |
| 2627 |
|
'author': author, |
| 2628 |
|
'day': day.day, |
| 2629 |
|
'month': day.month, |
| 2630 |
|
'year': day.year |
| 2631 |
|
} |
| 2632 |
|
|
| 2633 |
|
|
|
@@ 2531-2549 (lines=19) @@
|
| 2528 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2529 |
|
get_navi_link = get_link_rel_next |
| 2530 |
|
|
| 2531 |
|
@classmethod |
| 2532 |
|
def get_comic_info(cls, soup, link): |
| 2533 |
|
"""Get information about a particular comics.""" |
| 2534 |
|
title = soup.find("h1", class_="entry-title").string |
| 2535 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2536 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2537 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2538 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2539 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2540 |
|
assert len(imgs) == 1 |
| 2541 |
|
alt = imgs[0]['alt'] |
| 2542 |
|
return { |
| 2543 |
|
'img': [i['src'] for i in imgs], |
| 2544 |
|
'title': title, |
| 2545 |
|
'alt': alt, |
| 2546 |
|
'author': author, |
| 2547 |
|
'day': day.day, |
| 2548 |
|
'month': day.month, |
| 2549 |
|
'year': day.year |
| 2550 |
|
} |
| 2551 |
|
|
| 2552 |
|
|
|
@@ 2006-2024 (lines=19) @@
|
| 2003 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2004 |
|
get_navi_link = get_a_navi_navinext |
| 2005 |
|
|
| 2006 |
|
@classmethod |
| 2007 |
|
def get_comic_info(cls, soup, link): |
| 2008 |
|
"""Get information about a particular comics.""" |
| 2009 |
|
title = soup.find('h2', class_='post-title').string |
| 2010 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 2011 |
|
date_str = soup.find('span', class_='post-date').string |
| 2012 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 2013 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 2014 |
|
assert imgs |
| 2015 |
|
alt = imgs[0]['title'] |
| 2016 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 2017 |
|
return { |
| 2018 |
|
'month': day.month, |
| 2019 |
|
'year': day.year, |
| 2020 |
|
'day': day.day, |
| 2021 |
|
'img': [i['src'] for i in imgs], |
| 2022 |
|
'title': title, |
| 2023 |
|
'alt': alt, |
| 2024 |
|
'author': author, |
| 2025 |
|
} |
| 2026 |
|
|
| 2027 |
|
|
|
@@ 2704-2721 (lines=18) @@
|
| 2701 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2702 |
|
get_navi_link = get_link_rel_next |
| 2703 |
|
|
| 2704 |
|
@classmethod |
| 2705 |
|
def get_comic_info(cls, soup, link): |
| 2706 |
|
"""Get information about a particular comics.""" |
| 2707 |
|
title = soup.find('h2', class_='post-title').string |
| 2708 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2709 |
|
date_str = soup.find("span", class_="post-date").string |
| 2710 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2711 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2712 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2713 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2714 |
|
return { |
| 2715 |
|
'img': [i['src'] for i in imgs], |
| 2716 |
|
'title': title, |
| 2717 |
|
'alt': alt, |
| 2718 |
|
'author': author, |
| 2719 |
|
'day': day.day, |
| 2720 |
|
'month': day.month, |
| 2721 |
|
'year': day.year |
| 2722 |
|
} |
| 2723 |
|
|
| 2724 |
|
|
|
@@ 2675-2692 (lines=18) @@
|
| 2672 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2673 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2674 |
|
|
| 2675 |
|
@classmethod |
| 2676 |
|
def get_comic_info(cls, soup, link): |
| 2677 |
|
"""Get information about a particular comics.""" |
| 2678 |
|
title = soup.find('h2', class_='post-title').string |
| 2679 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2680 |
|
date_str = soup.find("span", class_="post-date").string |
| 2681 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2682 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2683 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2684 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2685 |
|
return { |
| 2686 |
|
'img': [i['src'] for i in imgs], |
| 2687 |
|
'title': title, |
| 2688 |
|
'alt': alt, |
| 2689 |
|
'author': author, |
| 2690 |
|
'day': day.day, |
| 2691 |
|
'month': day.month, |
| 2692 |
|
'year': day.year |
| 2693 |
|
} |
| 2694 |
|
|
| 2695 |
|
|
|
@@ 2474-2491 (lines=18) @@
|
| 2471 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2472 |
|
get_navi_link = get_a_rel_next |
| 2473 |
|
|
| 2474 |
|
@classmethod |
| 2475 |
|
def get_comic_info(cls, soup, link): |
| 2476 |
|
"""Get information about a particular comics.""" |
| 2477 |
|
title = soup.find('h2', class_='post-title').string |
| 2478 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2479 |
|
date_str = soup.find("span", class_="post-date").string |
| 2480 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2481 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2482 |
|
alt = imgs[0]['alt'] |
| 2483 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2484 |
|
return { |
| 2485 |
|
'img': [i['src'] for i in imgs], |
| 2486 |
|
'title': title, |
| 2487 |
|
'alt': alt, |
| 2488 |
|
'author': author, |
| 2489 |
|
'day': day.day, |
| 2490 |
|
'month': day.month, |
| 2491 |
|
'year': day.year |
| 2492 |
|
} |
| 2493 |
|
|
| 2494 |
|
|
|
@@ 965-982 (lines=18) @@
|
| 962 |
|
get_first_comic_link = get_div_navfirst_a |
| 963 |
|
get_navi_link = get_a_rel_next |
| 964 |
|
|
| 965 |
|
@classmethod |
| 966 |
|
def get_comic_info(cls, soup, link): |
| 967 |
|
"""Get information about a particular comics.""" |
| 968 |
|
title = soup.find('h2', class_='post-title').string |
| 969 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 970 |
|
date_str = soup.find('span', class_='post-date').string |
| 971 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 972 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 973 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 974 |
|
title2 = imgs[0]['title'] |
| 975 |
|
return { |
| 976 |
|
'day': day.day, |
| 977 |
|
'month': day.month, |
| 978 |
|
'year': day.year, |
| 979 |
|
'img': [i['src'] for i in imgs], |
| 980 |
|
'title': title, |
| 981 |
|
'title2': title2, |
| 982 |
|
'author': author, |
| 983 |
|
} |
| 984 |
|
|
| 985 |
|
|