@@ 2403-2422 (lines=20) @@ | ||
2400 | return link |
|
2401 | return None |
|
2402 | ||
2403 | @classmethod |
|
2404 | def get_comic_info(cls, soup, link): |
|
2405 | """Get information about a particular comics.""" |
|
2406 | title = soup.find('meta', attrs={'name': 'description'})["content"] |
|
2407 | description = soup.find('div', itemprop='articleBody').text |
|
2408 | author = soup.find('span', itemprop='author copyrightHolder').string |
|
2409 | imgs = soup.find_all('img', itemprop='image') |
|
2410 | assert all(i['title'] == i['alt'] for i in imgs) |
|
2411 | alt = imgs[0]['alt'] if imgs else "" |
|
2412 | date_str = soup.find('time', itemprop='datePublished')["datetime"] |
|
2413 | day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S") |
|
2414 | return { |
|
2415 | 'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
|
2416 | 'month': day.month, |
|
2417 | 'year': day.year, |
|
2418 | 'day': day.day, |
|
2419 | 'author': author, |
|
2420 | 'title': title, |
|
2421 | 'alt': alt, |
|
2422 | 'description': description, |
|
2423 | } |
|
2424 | ||
2425 | ||
@@ 2602-2620 (lines=19) @@ | ||
2599 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
2600 | get_navi_link = get_link_rel_next |
|
2601 | ||
2602 | @classmethod |
|
2603 | def get_comic_info(cls, soup, link): |
|
2604 | """Get information about a particular comics.""" |
|
2605 | title = soup.find('h2', class_='post-title').string |
|
2606 | author = soup.find("span", class_="post-author").find("a").string |
|
2607 | date_str = soup.find("span", class_="post-date").string |
|
2608 | day = string_to_date(date_str, "%B %d, %Y") |
|
2609 | imgs = soup.find("div", id="comic").find_all("img") |
|
2610 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2611 | assert len(imgs) <= 1 |
|
2612 | alt = imgs[0]['alt'] if imgs else "" |
|
2613 | return { |
|
2614 | 'img': [i['src'] for i in imgs], |
|
2615 | 'title': title, |
|
2616 | 'alt': alt, |
|
2617 | 'author': author, |
|
2618 | 'day': day.day, |
|
2619 | 'month': day.month, |
|
2620 | 'year': day.year |
|
2621 | } |
|
2622 | ||
2623 | ||
@@ 2572-2590 (lines=19) @@ | ||
2569 | get_first_comic_link = get_a_comicnavbase_comicnavfirst |
|
2570 | get_navi_link = get_link_rel_next |
|
2571 | ||
2572 | @classmethod |
|
2573 | def get_comic_info(cls, soup, link): |
|
2574 | """Get information about a particular comics.""" |
|
2575 | title = soup.find('h2', class_='post-title').string |
|
2576 | author = soup.find("span", class_="post-author").find("a").string |
|
2577 | date_str = soup.find("span", class_="post-date").string |
|
2578 | day = string_to_date(date_str, "%B %d, %Y") |
|
2579 | imgs = soup.find("div", id="comic").find_all("img") |
|
2580 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2581 | assert len(imgs) <= 1 |
|
2582 | alt = imgs[0]['alt'] if imgs else "" |
|
2583 | return { |
|
2584 | 'img': [i['src'] for i in imgs], |
|
2585 | 'title': title, |
|
2586 | 'alt': alt, |
|
2587 | 'author': author, |
|
2588 | 'day': day.day, |
|
2589 | 'month': day.month, |
|
2590 | 'year': day.year |
|
2591 | } |
|
2592 | ||
2593 | ||
@@ 2491-2509 (lines=19) @@ | ||
2488 | get_first_comic_link = get_a_navi_navifirst |
|
2489 | get_navi_link = get_link_rel_next |
|
2490 | ||
2491 | @classmethod |
|
2492 | def get_comic_info(cls, soup, link): |
|
2493 | """Get information about a particular comics.""" |
|
2494 | title = soup.find("h1", class_="entry-title").string |
|
2495 | author = soup.find("span", class_="author vcard").find("a").string |
|
2496 | date_str = soup.find("span", class_="entry-date").string |
|
2497 | day = string_to_date(date_str, "%B %d, %Y") |
|
2498 | imgs = soup.find("div", id="comic").find_all("img") |
|
2499 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2500 | assert len(imgs) == 1 |
|
2501 | alt = imgs[0]['alt'] |
|
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 | ||
@@ 2017-2035 (lines=19) @@ | ||
2014 | get_first_comic_link = get_a_navi_navifirst |
|
2015 | get_navi_link = get_a_navi_navinext |
|
2016 | ||
2017 | @classmethod |
|
2018 | def get_comic_info(cls, soup, link): |
|
2019 | """Get information about a particular comics.""" |
|
2020 | title = soup.find('h2', class_='post-title').string |
|
2021 | author = soup.find('span', class_='post-author').contents[1].string |
|
2022 | date_str = soup.find('span', class_='post-date').string |
|
2023 | day = string_to_date(date_str, '%B %d, %Y') |
|
2024 | imgs = soup.find('div', class_='comicpane').find_all('img') |
|
2025 | assert imgs |
|
2026 | alt = imgs[0]['title'] |
|
2027 | assert all(i['title'] == i['alt'] == alt for i in imgs) |
|
2028 | return { |
|
2029 | 'month': day.month, |
|
2030 | 'year': day.year, |
|
2031 | 'day': day.day, |
|
2032 | 'img': [i['src'] for i in imgs], |
|
2033 | 'title': title, |
|
2034 | 'alt': alt, |
|
2035 | 'author': author, |
|
2036 | } |
|
2037 | ||
2038 | ||
@@ 2664-2681 (lines=18) @@ | ||
2661 | get_first_comic_link = get_a_navi_navifirst |
|
2662 | get_navi_link = get_link_rel_next |
|
2663 | ||
2664 | @classmethod |
|
2665 | def get_comic_info(cls, soup, link): |
|
2666 | """Get information about a particular comics.""" |
|
2667 | title = soup.find('h2', class_='post-title').string |
|
2668 | author = soup.find("span", class_="post-author").find("a").string |
|
2669 | date_str = soup.find("span", class_="post-date").string |
|
2670 | day = string_to_date(date_str, "%B %d, %Y") |
|
2671 | imgs = soup.find("div", id="comic").find_all("img") |
|
2672 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2673 | alt = imgs[0]['alt'] if imgs else "" |
|
2674 | return { |
|
2675 | 'img': [i['src'] for i in imgs], |
|
2676 | 'title': title, |
|
2677 | 'alt': alt, |
|
2678 | 'author': author, |
|
2679 | 'day': day.day, |
|
2680 | 'month': day.month, |
|
2681 | 'year': day.year |
|
2682 | } |
|
2683 | ||
2684 | ||
@@ 2635-2652 (lines=18) @@ | ||
2632 | get_first_comic_link = get_a_navi_navifirst |
|
2633 | get_navi_link = get_a_navi_comicnavnext_navinext |
|
2634 | ||
2635 | @classmethod |
|
2636 | def get_comic_info(cls, soup, link): |
|
2637 | """Get information about a particular comics.""" |
|
2638 | title = soup.find('h2', class_='post-title').string |
|
2639 | author = soup.find("span", class_="post-author").find("a").string |
|
2640 | date_str = soup.find("span", class_="post-date").string |
|
2641 | day = string_to_date(date_str, "%B %d, %Y") |
|
2642 | imgs = soup.find("div", id="comic").find_all("img") |
|
2643 | assert all(i['alt'] == i['title'] for i in imgs) |
|
2644 | alt = imgs[0]['alt'] if imgs else "" |
|
2645 | return { |
|
2646 | 'img': [i['src'] for i in imgs], |
|
2647 | 'title': title, |
|
2648 | 'alt': alt, |
|
2649 | 'author': author, |
|
2650 | 'day': day.day, |
|
2651 | 'month': day.month, |
|
2652 | 'year': day.year |
|
2653 | } |
|
2654 | ||
2655 | ||
@@ 2434-2451 (lines=18) @@ | ||
2431 | get_first_comic_link = get_a_navi_navifirst |
|
2432 | get_navi_link = get_a_rel_next |
|
2433 | ||
2434 | @classmethod |
|
2435 | def get_comic_info(cls, soup, link): |
|
2436 | """Get information about a particular comics.""" |
|
2437 | title = soup.find('h2', class_='post-title').string |
|
2438 | author = soup.find("span", class_="post-author").find("a").string |
|
2439 | date_str = soup.find("span", class_="post-date").string |
|
2440 | day = string_to_date(date_str, "%B %d, %Y") |
|
2441 | imgs = soup.find("div", id="comic").find_all("img") |
|
2442 | alt = imgs[0]['alt'] |
|
2443 | assert all(i['alt'] == i['title'] == alt for i in imgs) |
|
2444 | return { |
|
2445 | 'img': [i['src'] for i in imgs], |
|
2446 | 'title': title, |
|
2447 | 'alt': alt, |
|
2448 | 'author': author, |
|
2449 | 'day': day.day, |
|
2450 | 'month': day.month, |
|
2451 | 'year': day.year |
|
2452 | } |
|
2453 | ||
2454 | ||
@@ 933-950 (lines=18) @@ | ||
930 | get_first_comic_link = get_div_navfirst_a |
|
931 | get_navi_link = get_a_rel_next |
|
932 | ||
933 | @classmethod |
|
934 | def get_comic_info(cls, soup, link): |
|
935 | """Get information about a particular comics.""" |
|
936 | title = soup.find('h2', class_='post-title').string |
|
937 | author = soup.find("span", class_="post-author").find("a").string |
|
938 | date_str = soup.find('span', class_='post-date').string |
|
939 | day = string_to_date(date_str, '%B %d, %Y') |
|
940 | imgs = soup.find('div', class_='comicpane').find_all('img') |
|
941 | assert all(i['alt'] == i['title'] for i in imgs) |
|
942 | title2 = imgs[0]['title'] |
|
943 | return { |
|
944 | 'day': day.day, |
|
945 | 'month': day.month, |
|
946 | 'year': day.year, |
|
947 | 'img': [i['src'] for i in imgs], |
|
948 | 'title': title, |
|
949 | 'title2': title2, |
|
950 | 'author': author, |
|
951 | } |
|
952 | ||
953 |