@@ 2479-2498 (lines=20) @@ | ||
2476 | return link |
|
2477 | return None |
|
2478 | ||
2479 | @classmethod |
|
2480 | def get_comic_info(cls, soup, link): |
|
2481 | """Get information about a particular comics.""" |
|
2482 | title = soup.find('meta', attrs={'name': 'description'})["content"] |
|
2483 | description = soup.find('div', itemprop='articleBody').text |
|
2484 | author = soup.find('span', itemprop='author copyrightHolder').string |
|
2485 | imgs = soup.find_all('img', itemprop='image') |
|
2486 | assert all(i['title'] == i['alt'] for i in imgs) |
|
2487 | alt = imgs[0]['alt'] if imgs else "" |
|
2488 | date_str = soup.find('time', itemprop='datePublished')["datetime"] |
|
2489 | day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S") |
|
2490 | return { |
|
2491 | 'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
|
2492 | 'month': day.month, |
|
2493 | 'year': day.year, |
|
2494 | 'day': day.day, |
|
2495 | 'author': author, |
|
2496 | 'title': title, |
|
2497 | 'alt': alt, |
|
2498 | 'description': description, |
|
2499 | } |
|
2500 | ||
2501 | ||
@@ 2678-2696 (lines=19) @@ | ||
2675 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
2676 | get_navi_link = get_link_rel_next |
|
2677 | ||
2678 | @classmethod |
|
2679 | def get_comic_info(cls, soup, link): |
|
2680 | """Get information about a particular comics.""" |
|
2681 | title = soup.find('h2', class_='post-title').string |
|
2682 | author = soup.find("span", class_="post-author").find("a").string |
|
2683 | date_str = soup.find("span", class_="post-date").string |
|
2684 | day = string_to_date(date_str, "%B %d, %Y") |
|
2685 | imgs = soup.find("div", id="comic").find_all("img") |
|
2686 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2687 | assert len(imgs) <= 1 |
|
2688 | alt = imgs[0]['alt'] if imgs else "" |
|
2689 | return { |
|
2690 | 'img': [i['src'] for i in imgs], |
|
2691 | 'title': title, |
|
2692 | 'alt': alt, |
|
2693 | 'author': author, |
|
2694 | 'day': day.day, |
|
2695 | 'month': day.month, |
|
2696 | 'year': day.year |
|
2697 | } |
|
2698 | ||
2699 | ||
@@ 2648-2666 (lines=19) @@ | ||
2645 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
2646 | get_navi_link = get_link_rel_next |
|
2647 | ||
2648 | @classmethod |
|
2649 | def get_comic_info(cls, soup, link): |
|
2650 | """Get information about a particular comics.""" |
|
2651 | title = soup.find('h2', class_='post-title').string |
|
2652 | author = soup.find("span", class_="post-author").find("a").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(i['alt'] == i['title'] for i in imgs) |
|
2657 | assert len(imgs) <= 1 |
|
2658 | alt = imgs[0]['alt'] if imgs else "" |
|
2659 | return { |
|
2660 | 'img': [i['src'] for i in imgs], |
|
2661 | 'title': title, |
|
2662 | 'alt': alt, |
|
2663 | 'author': author, |
|
2664 | 'day': day.day, |
|
2665 | 'month': day.month, |
|
2666 | 'year': day.year |
|
2667 | } |
|
2668 | ||
2669 | ||
@@ 2567-2585 (lines=19) @@ | ||
2564 | get_first_comic_link = get_a_navi_navifirst |
|
2565 | get_navi_link = get_link_rel_next |
|
2566 | ||
2567 | @classmethod |
|
2568 | def get_comic_info(cls, soup, link): |
|
2569 | """Get information about a particular comics.""" |
|
2570 | title = soup.find("h1", class_="entry-title").string |
|
2571 | author = soup.find("span", class_="author vcard").find("a").string |
|
2572 | date_str = soup.find("span", class_="entry-date").string |
|
2573 | day = string_to_date(date_str, "%B %d, %Y") |
|
2574 | imgs = soup.find("div", id="comic").find_all("img") |
|
2575 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2576 | assert len(imgs) == 1 |
|
2577 | alt = imgs[0]['alt'] |
|
2578 | return { |
|
2579 | 'img': [i['src'] for i in imgs], |
|
2580 | 'title': title, |
|
2581 | 'alt': alt, |
|
2582 | 'author': author, |
|
2583 | 'day': day.day, |
|
2584 | 'month': day.month, |
|
2585 | 'year': day.year |
|
2586 | } |
|
2587 | ||
2588 | ||
@@ 2041-2059 (lines=19) @@ | ||
2038 | get_first_comic_link = get_a_navi_navifirst |
|
2039 | get_navi_link = get_a_navi_navinext |
|
2040 | ||
2041 | @classmethod |
|
2042 | def get_comic_info(cls, soup, link): |
|
2043 | """Get information about a particular comics.""" |
|
2044 | title = soup.find('h2', class_='post-title').string |
|
2045 | author = soup.find('span', class_='post-author').contents[1].string |
|
2046 | date_str = soup.find('span', class_='post-date').string |
|
2047 | day = string_to_date(date_str, '%B %d, %Y') |
|
2048 | imgs = soup.find('div', class_='comicpane').find_all('img') |
|
2049 | assert imgs |
|
2050 | alt = imgs[0]['title'] |
|
2051 | assert all(i['title'] == i['alt'] == alt for i in imgs) |
|
2052 | return { |
|
2053 | 'month': day.month, |
|
2054 | 'year': day.year, |
|
2055 | 'day': day.day, |
|
2056 | 'img': [i['src'] for i in imgs], |
|
2057 | 'title': title, |
|
2058 | 'alt': alt, |
|
2059 | 'author': author, |
|
2060 | } |
|
2061 | ||
2062 | ||
@@ 2740-2757 (lines=18) @@ | ||
2737 | get_first_comic_link = get_a_navi_navifirst |
|
2738 | get_navi_link = get_link_rel_next |
|
2739 | ||
2740 | @classmethod |
|
2741 | def get_comic_info(cls, soup, link): |
|
2742 | """Get information about a particular comics.""" |
|
2743 | title = soup.find('h2', class_='post-title').string |
|
2744 | author = soup.find("span", class_="post-author").find("a").string |
|
2745 | date_str = soup.find("span", class_="post-date").string |
|
2746 | day = string_to_date(date_str, "%B %d, %Y") |
|
2747 | imgs = soup.find("div", id="comic").find_all("img") |
|
2748 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2749 | alt = imgs[0]['alt'] if imgs else "" |
|
2750 | return { |
|
2751 | 'img': [i['src'] for i in imgs], |
|
2752 | 'title': title, |
|
2753 | 'alt': alt, |
|
2754 | 'author': author, |
|
2755 | 'day': day.day, |
|
2756 | 'month': day.month, |
|
2757 | 'year': day.year |
|
2758 | } |
|
2759 | ||
2760 | ||
@@ 2711-2728 (lines=18) @@ | ||
2708 | get_first_comic_link = get_a_navi_navifirst |
|
2709 | get_navi_link = get_a_navi_comicnavnext_navinext |
|
2710 | ||
2711 | @classmethod |
|
2712 | def get_comic_info(cls, soup, link): |
|
2713 | """Get information about a particular comics.""" |
|
2714 | title = soup.find('h2', class_='post-title').string |
|
2715 | author = soup.find("span", class_="post-author").find("a").string |
|
2716 | date_str = soup.find("span", class_="post-date").string |
|
2717 | day = string_to_date(date_str, "%B %d, %Y") |
|
2718 | imgs = soup.find("div", id="comic").find_all("img") |
|
2719 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2720 | alt = imgs[0]['alt'] if imgs else "" |
|
2721 | return { |
|
2722 | 'img': [i['src'] for i in imgs], |
|
2723 | 'title': title, |
|
2724 | 'alt': alt, |
|
2725 | 'author': author, |
|
2726 | 'day': day.day, |
|
2727 | 'month': day.month, |
|
2728 | 'year': day.year |
|
2729 | } |
|
2730 | ||
2731 | ||
@@ 2510-2527 (lines=18) @@ | ||
2507 | get_first_comic_link = get_a_navi_navifirst |
|
2508 | get_navi_link = get_a_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, "%B %d, %Y") |
|
2517 | imgs = soup.find("div", id="comic").find_all("img") |
|
2518 | alt = imgs[0]['alt'] |
|
2519 | assert all(i['alt'] == i['title'] == alt for i in imgs) |
|
2520 | return { |
|
2521 | 'img': [i['src'] for i in imgs], |
|
2522 | 'title': title, |
|
2523 | 'alt': alt, |
|
2524 | 'author': author, |
|
2525 | 'day': day.day, |
|
2526 | 'month': day.month, |
|
2527 | 'year': day.year |
|
2528 | } |
|
2529 | ||
2530 | ||
@@ 964-981 (lines=18) @@ | ||
961 | get_first_comic_link = get_div_navfirst_a |
|
962 | get_navi_link = get_a_rel_next |
|
963 | ||
964 | @classmethod |
|
965 | def get_comic_info(cls, soup, link): |
|
966 | """Get information about a particular comics.""" |
|
967 | title = soup.find('h2', class_='post-title').string |
|
968 | author = soup.find("span", class_="post-author").find("a").string |
|
969 | date_str = soup.find('span', class_='post-date').string |
|
970 | day = string_to_date(date_str, '%B %d, %Y') |
|
971 | imgs = soup.find('div', class_='comicpane').find_all('img') |
|
972 | assert all(i['alt'] == i['title'] for i in imgs) |
|
973 | title2 = imgs[0]['title'] |
|
974 | return { |
|
975 | 'day': day.day, |
|
976 | 'month': day.month, |
|
977 | 'year': day.year, |
|
978 | 'img': [i['src'] for i in imgs], |
|
979 | 'title': title, |
|
980 | 'title2': title2, |
|
981 | 'author': author, |
|
982 | } |
|
983 | ||
984 |