|
@@ 2397-2416 (lines=20) @@
|
| 2394 |
|
return link |
| 2395 |
|
return None |
| 2396 |
|
|
| 2397 |
|
@classmethod |
| 2398 |
|
def get_comic_info(cls, soup, link): |
| 2399 |
|
"""Get information about a particular comics.""" |
| 2400 |
|
title = soup.find('meta', attrs={'name': 'description'})["content"] |
| 2401 |
|
description = soup.find('div', itemprop='articleBody').text |
| 2402 |
|
author = soup.find('span', itemprop='author copyrightHolder').string |
| 2403 |
|
imgs = soup.find_all('img', itemprop='image') |
| 2404 |
|
assert all(i['title'] == i['alt'] for i in imgs) |
| 2405 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2406 |
|
date_str = soup.find('time', itemprop='datePublished')["datetime"] |
| 2407 |
|
day = string_to_date(date_str, "%Y-%m-%d %H:%M:%S") |
| 2408 |
|
return { |
| 2409 |
|
'img': [urljoin_wrapper(cls.url, i['src']) for i in imgs], |
| 2410 |
|
'month': day.month, |
| 2411 |
|
'year': day.year, |
| 2412 |
|
'day': day.day, |
| 2413 |
|
'author': author, |
| 2414 |
|
'title': title, |
| 2415 |
|
'alt': alt, |
| 2416 |
|
'description': description, |
| 2417 |
|
} |
| 2418 |
|
|
| 2419 |
|
|
|
@@ 2596-2614 (lines=19) @@
|
| 2593 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2594 |
|
get_navi_link = get_link_rel_next |
| 2595 |
|
|
| 2596 |
|
@classmethod |
| 2597 |
|
def get_comic_info(cls, soup, link): |
| 2598 |
|
"""Get information about a particular comics.""" |
| 2599 |
|
title = soup.find('h2', class_='post-title').string |
| 2600 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2601 |
|
date_str = soup.find("span", class_="post-date").string |
| 2602 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2603 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2604 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2605 |
|
assert len(imgs) <= 1 |
| 2606 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2607 |
|
return { |
| 2608 |
|
'img': [i['src'] for i in imgs], |
| 2609 |
|
'title': title, |
| 2610 |
|
'alt': alt, |
| 2611 |
|
'author': author, |
| 2612 |
|
'day': day.day, |
| 2613 |
|
'month': day.month, |
| 2614 |
|
'year': day.year |
| 2615 |
|
} |
| 2616 |
|
|
| 2617 |
|
|
|
@@ 2566-2584 (lines=19) @@
|
| 2563 |
|
get_first_comic_link = get_a_comicnavbase_comicnavfirst |
| 2564 |
|
get_navi_link = get_link_rel_next |
| 2565 |
|
|
| 2566 |
|
@classmethod |
| 2567 |
|
def get_comic_info(cls, soup, link): |
| 2568 |
|
"""Get information about a particular comics.""" |
| 2569 |
|
title = soup.find('h2', class_='post-title').string |
| 2570 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2571 |
|
date_str = soup.find("span", class_="post-date").string |
| 2572 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2573 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2574 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2575 |
|
assert len(imgs) <= 1 |
| 2576 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2577 |
|
return { |
| 2578 |
|
'img': [i['src'] for i in imgs], |
| 2579 |
|
'title': title, |
| 2580 |
|
'alt': alt, |
| 2581 |
|
'author': author, |
| 2582 |
|
'day': day.day, |
| 2583 |
|
'month': day.month, |
| 2584 |
|
'year': day.year |
| 2585 |
|
} |
| 2586 |
|
|
| 2587 |
|
|
|
@@ 2485-2503 (lines=19) @@
|
| 2482 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2483 |
|
get_navi_link = get_link_rel_next |
| 2484 |
|
|
| 2485 |
|
@classmethod |
| 2486 |
|
def get_comic_info(cls, soup, link): |
| 2487 |
|
"""Get information about a particular comics.""" |
| 2488 |
|
title = soup.find("h1", class_="entry-title").string |
| 2489 |
|
author = soup.find("span", class_="author vcard").find("a").string |
| 2490 |
|
date_str = soup.find("span", class_="entry-date").string |
| 2491 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2492 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2493 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2494 |
|
assert len(imgs) == 1 |
| 2495 |
|
alt = imgs[0]['alt'] |
| 2496 |
|
return { |
| 2497 |
|
'img': [i['src'] for i in imgs], |
| 2498 |
|
'title': title, |
| 2499 |
|
'alt': alt, |
| 2500 |
|
'author': author, |
| 2501 |
|
'day': day.day, |
| 2502 |
|
'month': day.month, |
| 2503 |
|
'year': day.year |
| 2504 |
|
} |
| 2505 |
|
|
| 2506 |
|
|
|
@@ 2011-2029 (lines=19) @@
|
| 2008 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2009 |
|
get_navi_link = get_a_navi_navinext |
| 2010 |
|
|
| 2011 |
|
@classmethod |
| 2012 |
|
def get_comic_info(cls, soup, link): |
| 2013 |
|
"""Get information about a particular comics.""" |
| 2014 |
|
title = soup.find('h2', class_='post-title').string |
| 2015 |
|
author = soup.find('span', class_='post-author').contents[1].string |
| 2016 |
|
date_str = soup.find('span', class_='post-date').string |
| 2017 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 2018 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 2019 |
|
assert imgs |
| 2020 |
|
alt = imgs[0]['title'] |
| 2021 |
|
assert all(i['title'] == i['alt'] == alt for i in imgs) |
| 2022 |
|
return { |
| 2023 |
|
'month': day.month, |
| 2024 |
|
'year': day.year, |
| 2025 |
|
'day': day.day, |
| 2026 |
|
'img': [i['src'] for i in imgs], |
| 2027 |
|
'title': title, |
| 2028 |
|
'alt': alt, |
| 2029 |
|
'author': author, |
| 2030 |
|
} |
| 2031 |
|
|
| 2032 |
|
|
|
@@ 2658-2675 (lines=18) @@
|
| 2655 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2656 |
|
get_navi_link = get_link_rel_next |
| 2657 |
|
|
| 2658 |
|
@classmethod |
| 2659 |
|
def get_comic_info(cls, soup, link): |
| 2660 |
|
"""Get information about a particular comics.""" |
| 2661 |
|
title = soup.find('h2', class_='post-title').string |
| 2662 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2663 |
|
date_str = soup.find("span", class_="post-date").string |
| 2664 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2665 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2666 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2667 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2668 |
|
return { |
| 2669 |
|
'img': [i['src'] for i in imgs], |
| 2670 |
|
'title': title, |
| 2671 |
|
'alt': alt, |
| 2672 |
|
'author': author, |
| 2673 |
|
'day': day.day, |
| 2674 |
|
'month': day.month, |
| 2675 |
|
'year': day.year |
| 2676 |
|
} |
| 2677 |
|
|
| 2678 |
|
|
|
@@ 2629-2646 (lines=18) @@
|
| 2626 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2627 |
|
get_navi_link = get_a_navi_comicnavnext_navinext |
| 2628 |
|
|
| 2629 |
|
@classmethod |
| 2630 |
|
def get_comic_info(cls, soup, link): |
| 2631 |
|
"""Get information about a particular comics.""" |
| 2632 |
|
title = soup.find('h2', class_='post-title').string |
| 2633 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2634 |
|
date_str = soup.find("span", class_="post-date").string |
| 2635 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2636 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2637 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 2638 |
|
alt = imgs[0]['alt'] if imgs else "" |
| 2639 |
|
return { |
| 2640 |
|
'img': [i['src'] for i in imgs], |
| 2641 |
|
'title': title, |
| 2642 |
|
'alt': alt, |
| 2643 |
|
'author': author, |
| 2644 |
|
'day': day.day, |
| 2645 |
|
'month': day.month, |
| 2646 |
|
'year': day.year |
| 2647 |
|
} |
| 2648 |
|
|
| 2649 |
|
|
|
@@ 2428-2445 (lines=18) @@
|
| 2425 |
|
get_first_comic_link = get_a_navi_navifirst |
| 2426 |
|
get_navi_link = get_a_rel_next |
| 2427 |
|
|
| 2428 |
|
@classmethod |
| 2429 |
|
def get_comic_info(cls, soup, link): |
| 2430 |
|
"""Get information about a particular comics.""" |
| 2431 |
|
title = soup.find('h2', class_='post-title').string |
| 2432 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 2433 |
|
date_str = soup.find("span", class_="post-date").string |
| 2434 |
|
day = string_to_date(date_str, "%B %d, %Y") |
| 2435 |
|
imgs = soup.find("div", id="comic").find_all("img") |
| 2436 |
|
alt = imgs[0]['alt'] |
| 2437 |
|
assert all(i['alt'] == i['title'] == alt for i in imgs) |
| 2438 |
|
return { |
| 2439 |
|
'img': [i['src'] for i in imgs], |
| 2440 |
|
'title': title, |
| 2441 |
|
'alt': alt, |
| 2442 |
|
'author': author, |
| 2443 |
|
'day': day.day, |
| 2444 |
|
'month': day.month, |
| 2445 |
|
'year': day.year |
| 2446 |
|
} |
| 2447 |
|
|
| 2448 |
|
|
|
@@ 934-951 (lines=18) @@
|
| 931 |
|
get_first_comic_link = get_div_navfirst_a |
| 932 |
|
get_navi_link = get_a_rel_next |
| 933 |
|
|
| 934 |
|
@classmethod |
| 935 |
|
def get_comic_info(cls, soup, link): |
| 936 |
|
"""Get information about a particular comics.""" |
| 937 |
|
title = soup.find('h2', class_='post-title').string |
| 938 |
|
author = soup.find("span", class_="post-author").find("a").string |
| 939 |
|
date_str = soup.find('span', class_='post-date').string |
| 940 |
|
day = string_to_date(date_str, '%B %d, %Y') |
| 941 |
|
imgs = soup.find('div', class_='comicpane').find_all('img') |
| 942 |
|
assert all(i['alt'] == i['title'] for i in imgs) |
| 943 |
|
title2 = imgs[0]['title'] |
| 944 |
|
return { |
| 945 |
|
'day': day.day, |
| 946 |
|
'month': day.month, |
| 947 |
|
'year': day.year, |
| 948 |
|
'img': [i['src'] for i in imgs], |
| 949 |
|
'title': title, |
| 950 |
|
'title2': title2, |
| 951 |
|
'author': author, |
| 952 |
|
} |
| 953 |
|
|
| 954 |
|
|
SylvainDe /
ComicBookMaker
