def parse_row(row):
tds = [td.text for td in row.select("td")]
img = thumbnails.select_one(f'a[title="{tds[1]}"] img')
data = {
'id':
tds[0],
'name':
tds[1],
'rarity':
tds[2],
'type':
tds[3],
'affiliation':
tds[4],
'stats': {
'firepower': tds[5],
'health': tds[6],
'antiAir': tds[7],
'speed': tds[8],
'airPower': tds[9],
'torpedo': tds[10]
},
'url':
build_url(row.select_one('a')['href']),
'thumbnail':
build_url(
img['srcset'].split()[0] if img.has_attr('srcset') else img['src'])
}
return data
def extract_pictures(html):
return {
'images': [
extract_skin(tab)
for tab in html.select('div.shiparttabbernew .tabbertab')
],
'icon':
build_url(html.select_one('img')['src'])
if html.select_one('img') else '',
'chibi':
build_url(html.select_one('#talkingchibi img')['src'])
if html.select_one('#talkingchibi img') else ''
}
def extract_skin(tab):
image_path = tab.select_one('img')['srcset'].split(' ')[-2]
return {'name': tab['title'], 'url': build_url(image_path)}
from requests import get
from shared import save_fixture, build_url
from bs4 import BeautifulSoup
html = get('https://azurlane.koumakan.jp/Equipment_List').text
fp = BeautifulSoup(html, 'lxml')
category_urls = [link['href'] for link in fp.find('ul').select('a')]
for category_url in category_urls:
category_html = get(build_url(category_url)).text
table = BeautifulSoup(category_html, 'lxml').select_one('.tabbertab table')
paths = set([
row.find('a')['href'] for row in table.find_all('tr')
if not row.find('th')
])
for path in paths:
name = path[1:]
if 'w/index.php?' in name:
continue
print(name)
save_fixture('equipment', name, get(build_url(path)).text)
def extract_picture(html):
img = html.find('img')
path = img['srcset'].split(' ')[-2] if img.has_attr(
'srcset') else img['src']
return build_url(path)
from requests import get
from shared import save_fixture, build_url
from bs4 import BeautifulSoup
html = get('https://azurlane.koumakan.jp/List_of_Ships').text
fp = BeautifulSoup(html, 'lxml')
rows = fp.select('.mw-parser-output .wikitable tr')
urls = [build_url(row.find('a')['href']) for row in rows if not row.find('th')]
for url in urls:
name = url.split('/')[-1]
print(name)
save_fixture('ships_long', name, get(url).text)