spider_work/cgc_spider/demo.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/9/25 11:26
import requests
import user_agent
from parsel import Selector

# headers = {
#     "accept": "application/json, text/plain, */*",
#     "referer": "https://www.jihuanshe.com/",
#     "user-agent": user_agent.generate_user_agent()
# }
# url = "https://api.jihuanshe.com/api/market/share/auction-product"
# params = {
#     "auction_product_id": 26,
#     "url": f"https://www.jihuanshe.com/app/auction?auctionProductId={26}"
# }
# response = requests.get(url, headers=headers, params=params, timeout=5)
# print(response.json())
# print(response)
# print(response.url)

HEADERS = {
    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
    "user-agent": user_agent.generate_user_agent()
}

COOKIES = {
    "CaptchaValue": "eyJhbGdvcml0aG0iOiJTSEEtMjU2IiwiY2hhbGxlbmdlIjoiNTZlNTBmMzU4MWRlMGYyNGQ5OGI2MTBhYTJlMTdmNjIzNzU4MDdmZjExOWM2MjNjYTRhNzUyY2MxMmU3ZDNmYyIsIm51bWJlciI6NDUxMTcsInNhbHQiOiJmNWU0ODBkZWNhMDNmYmJmNzdiN2UyYmYiLCJzaWduYXR1cmUiOiI3ZjlkMTc3NjllOTMwM2I3NTM5OTRlNzRlZDg0MzU3NTZkMzljMzU5YTFhMzBmODAzODNlMWI4YjA0MGZhZDVjIiwidG9vayI6ODJ9",
    "saved-language": "zh-CN",
    "SessionID": "dd60b7e4-f638-41cd-bb56-e2e4929aee27",
    "_ga": "GA1.1.706688626.1757584379",
    "AltchaSessionID": "1622a445-bf77-43e5-be67-13b76ff8e5ca",
    "_ga_55FF3CQQK2": "GS2.1.s1758539017$o6$g0$t1758539017$j60$l0$h0"
}


url = f"https://cards.cgccards.cn/certlookup/6060110001/"
resp =requests.get(url, headers=HEADERS, cookies=COOKIES)
print(resp.text)
print(resp.status_code)

selector = Selector(resp.text)
tag_dl_list = selector.xpath('//div[@class="results-pane"]/div[@class="certlookup-intro"]//dl')

# 初始化变量
data_dict = {
    "rating_number": None,
    "year": None,
    "manufacturer": None,
    "card_set": None,
    "card_no": None,
    "player": None,
    # "belonging": None,
    "grade": None,
    "image_front": None,
    "image_back": None
}

# 提取详细信息
for tag_dl in tag_dl_list:
    dt_text = tag_dl.xpath('./dt/text()').get()
    dd_text = tag_dl.xpath('./dd/text()').get()

    if dt_text == "评级号码":
        data_dict["rating_number"] = dd_text.strip() if dd_text else None
    elif dt_text == "年份":
        data_dict["year"] = dd_text
    elif dt_text == "制造商":
        data_dict["manufacturer"] = dd_text
    elif dt_text == "套装":
        data_dict["card_set"] = dd_text
    elif dt_text == "卡牌编号":
        data_dict["card_no"] = dd_text
    elif dt_text == "球员":
        data_dict["player"] = dd_text
    # elif dt_text == "归属":
    #     data_dict["belonging"] = dd_text
    elif dt_text == "评级等级":
        data_dict["grade"] = dd_text.strip() if dd_text else None

# 提取图片链接
tag_img_list = selector.xpath('//div[@class="results-pane"]//div[@class="certlookup-images-item"]/a/@href').getall()
if len(tag_img_list) >= 2:
    data_dict["image_front"] = tag_img_list[0]
    data_dict["image_back"] = tag_img_list[1]
elif len(tag_img_list) == 1:
    data_dict["image_front"] = tag_img_list[0]

print(data_dict)