幻塔抽卡概率统计 v1.0

幻塔抽卡概率统计.py

# 起因：https://nga.178.com/read.php?tid=30008586
# 依赖库：pip install requests lxml cssselect

import re
import requests
from lxml import etree

headers = {
    'authority': 'nga.178.com',
    'pragma': 'no-cache',
    'cache-control': 'no-cache',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.192 Safari/537.36 OPR/74.0.3911.218',
    '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=0.9',
    'sec-fetch-site': 'same-origin',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-user': '?1',
    'sec-fetch-dest': 'document',
    'referer': 'https://nga.178.com/read.php?tid=30008586&_ff=836',
    'accept-language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
    'cookie': '',  # cookeis 写自己的
}


# 单条数据处理

def result_solve(x):
    if x:
        return list(map(int, x))


def match_pattern1(txt):
    try:
        return re.search(r'抽卡[：:]?(\d+?)[抽|发]\s?(\d+?)金', txt).groups()
    except:
        pass
    try:
        return re.search(r'金[核河][：:]?\s?(\d+?)[抽|发]\s?(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'金[：:](\d+?)\s(\d+?)', txt).groups()
    except:
        pass
    try:
        return re.search(r'金[核河](\d+?)[抽|发]，(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'金\s[：:]\s(\d+?)\s(\d+?)', txt).groups()
    except:
        pass
    try:
        return re.search(r'(\d+?)[抽|发]\s?(\d+?)(?:金|ssr)', txt).groups()
    except:
        pass

    try:
        return re.search(r'金核[：:]?(\d+)\s?(\d+?)金?', txt).groups()
    except:
        pass


def match_pattern2(txt):
    try:
        return re.search(r'黑核[：:]?(\d+?)页\s?(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑[：:]?(\d+?)\s(\d+?)', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑核[：:]?(\d+?)页出了\s?(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑核[：:]?\s?(\d+)页\s?(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑\s[：:]\s(\d+?)\s(\d+?)', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑[：:]?\s?(\d+?)页(\d+?)', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑核(\d+?)页，(\d+?)金?', txt).groups()
    except:
        pass
    try:
        return re.search(r'黑核[：:]?刚到(\d+?)页\s?(\d+?)金?', txt).groups()
    except:
        pass


def solve_item(item):
    txt = '\n'.join(item.itertext())

    floor = int(item.get('id')[len('postcontent'):])
    draw_ssr = result_solve(match_pattern1(txt)) or [0, 0]
    black_ssr = result_solve(match_pattern2(txt)) or [0, 0]
    
    attach = bool(item.getparent().getparent().xpath("span[contains(@id, 'postattach')]"))
    is_data = not (draw_ssr == [0, 0] and black_ssr == [0, 0])

    if is_data:
        print(f'{floor}楼: {draw_ssr[0]}抽{draw_ssr[1]}金，{black_ssr[0]}页黑核{black_ssr[1]}金，图 {"有" if attach else "无"}')

    return { 'floor': floor, 'draw_ssr': draw_ssr, 'black_ssr': black_ssr, 'attach': attach, 'is_data': is_data }


# 每页抓取

def fetch_page(page):
    params = (
        ('tid', '30008586'),
        ('_ff', '836'),
        ('page', page)
    )

    resp = requests.get('https://nga.178.com/read.php', headers=headers, params=params)
    page = etree.HTML(resp.text)
    
    items = page.cssselect("span.postcontent")

    data = []
    for i in items:
        data.append(solve_item(i))
    return data



# main
all_data = []
for i in range(1, 8):
    all_data.extend(fetch_page(i))

# 导出excel
import csv
import time


with open('幻塔概率统计-%s.csv' % time.strftime('%Y-%m-%d %H_%M_%S', time.localtime())
, 'w', newline='', encoding='utf_8_sig') as f:
    writer = csv.writer(f)  # BOM utf-8, 这样excel不乱码
    writer.writerow(['楼层', '抽卡(金/红)', '抽卡SSR数', '黑核抽数', '黑核SSR数', '带图', '存在数据'])
    for i in all_data:
        writer.writerow([i['floor'], i['draw_ssr'][0], i['draw_ssr'][1], i['black_ssr'][0], i['black_ssr'][1], i['attach'], i['is_data']])