lewen/X25020501_card_book
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(card): 优化卡片新增、修复搜卡改版、卡不存在抛异常 其他卡片支持自定义卡片名 修复psa页面改版 修复ccg卡不存在抛异常

Browse Source
This commit is contained in:
xingc
2025-04-25 17:09:18 +08:00
parent 5dd7910167
commit 0f21491ec2
3 changed files with 44 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
core/routers/card/scraper.py
View File

@@ -85,13 +85,13 @@ class SiteApi:
@async_retry(exceptions=(SearchCardRetry,))
async def psa(self, cert_number: str | int):
"""PSA"""
url = f'https://www.psacard.com/cert/{cert_number}'
url = f'https://www.psacard.com/cert/{cert_number}/psa'
headers = {
# 'X-Requested-With': 'XMLHttpRequest',
'Origin': 'https://www.psacard.com',
'Referer': f'https://www.psacard.com/cert/{cert_number}',
}
r = await self.get(url, headers=headers, use_abroad_proxy=True)
r = await self.get(url, headers=headers, impersonate="chrome131", use_abroad_proxy=True)
chck_string = 'Just a moment...'
if chck_string in r.text:
raise SearchCardRetry(chck_string)
@@ -191,16 +191,16 @@ class CardScraper:
"""PSA"""
r = await self.api.psa(cert_number)
html = Selector(r.text)
if html.xpath('//div[contains(@class, "alert-danger")]/p[contains(string(), "not found")]').get() is not None:
if html.xpath('//div[contains(@class, "wrapper")]//h1/text()').get() is not None:
return
info_elements = html.xpath('//main[@id="mainContent"]/div/table[contains(@class, "text-medium")]//tr')
info_elements = html.xpath('//div[@hidden and @id]/div[contains(@class, "py-3")]')
info = dict()
for info_element in info_elements:
name = info_element.xpath('./th[1]').xpath('string()').get()
name = info_element.xpath('./dt[1]').xpath('string()').get() or info_element.xpath('./dt/template/@id').get() or ''
name = re.sub(r'\(|\)', '', name)
name = name.lower().replace(' ', '_').replace('/', '_')
value = info_element.xpath('./td[1]').xpath('string()').get()
value = info_element.xpath('./dd[1]').xpath('string()').get()
info[name.strip()] = value.strip()
picture_elements = info_elements.xpath('.//img')
info['pictures'] = [
@@ -212,35 +212,29 @@ class CardScraper:
item = dict(cert_number=None)
# 评级卡号
item['cert_number'] = info['certification_number']
item['cert_number'] = info['cert_number']
# 年份
item['card_year'] = info.get('year')
# 卡片品牌
item['card_brand'] = info.get('brand')
item['card_brand'] = info.get('brand_title')
# 卡片评分
card_grade = info.get('card_grade') or info.get('grade') or ''
card_grade = info.get('item_grade') or ''
item['card_score'] = regx_match(r'(\d+)', card_grade, first=True)
# 签字评分
auto_score = info.get('autograph_grade') or ''
item['auto_score'] = regx_match(r'(\d+)', auto_score, first=True)
# 卡片名称
item['card_name'] = info.get('player')
item['card_name'] = info.get('subject') or info.get('p:16')
# 卡片编号
item['card_number'] = info.get('card_number')
# 卡片类型
item['card_type'] = info.get('sport')
images_id = html.xpath(
'//script[contains(text(), "getPSACertImages")]/text()'
).re_first(r'getPSACertImages\(\'(\d+)\'\);')
item['card_type'] = info.get('category')
# 卡片正、反图片（远程）
item['card_spare_picture'] = {
'front_picture': html.xpath('//div[contains(@class, "flex")]//span/noscript/img[@alt="left"]/@src').get(),
'reverse_picture': html.xpath('//div[contains(@class, "flex")]//span/noscript/img[@alt="right"]/@src').get()
}
if images_id:
r = await self.api.psa_images(cert_number, images_id)
result = r.json()
# 卡片正、反图片（远程）
item['card_spare_picture'] = {
'front_picture': jsonpath(result, '$.PSACertImages[0].OriginalImageUrl', first=True),
'reverse_picture': jsonpath(result, '$.PSACertImages[1].OriginalImageUrl', first=True)
}
# 来源
item['source'] = 'psa'
return {
@@ -368,7 +362,7 @@ class CardScraper:
"""重庆藏卡"""
r = await self.api.ccg(cert_number)
result = r.json()
if result.get('code') != '200':
if result.get('code') != '200' or not result['data']:
return
item = dict(cert_number=None)