Spaces:
Paused
Paused
| from bs4 import BeautifulSoup | |
| from others import * | |
| def get_info_sankaku(soup: BeautifulSoup): | |
| # Find the artist information | |
| artist_tag = soup.find('li', class_='tag-type-artist') | |
| artist = artist_tag.find('a')['href'].split('=')[-1] | |
| artist = artist.replace('_', ' ').title() | |
| # Find the series information | |
| series_tag = soup.find('li', class_='tag-type-copyright') | |
| series = series_tag.find('a')['href'].split('=')[-1] | |
| series = series.replace('_', ' ').title() | |
| # Find the characters information | |
| characters_tags = soup.find_all('li', class_='tag-type-character') | |
| characters = [] | |
| for tag in characters_tags: | |
| character = tag.find('a')['href'].split('=')[-1] | |
| character = character.replace('_', ' ').title() | |
| characters.append(character) | |
| characters = ', '.join(characters) | |
| # Find the link information | |
| link_tag = soup.find('source') | |
| link = 'https:' + link_tag['src'] | |
| return artist, series, characters, link |