PythonDemo/selectAll.py

import requests
from bs4 import BeautifulSoup
import csv
import datetime

# 发起请求获取网页内容
base_url = 'https://mxd.dvg.cn/items.php?search=1&st=1&words=&type=0&p='
min_pages = 1
max_pages = 1159

# 初始化一个空列表，用于存储结果
items = []
for page in range(min_pages, max_pages ):
    url = base_url + str(page)
    print(url)
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
# 遍历所有表格行
    for row in soup.find_all('tr'):
        cells = row.find_all('td')
        for i in range(0, len(cells), 2):
            try:
                # 提取 ID 和物品名称
                id_cell = cells[i]
                item_cell = cells[i + 1]
                br_tag = id_cell.find('br')
                if br_tag:
                    item_id = br_tag.find_next_sibling(text=True)
                # item_id = id_cell.get_text(strip=True).split('\n')[-1]
                item_name = item_cell.find('a').get_text(strip=True)
                
                items.append((item_id, item_name))

            except IndexError:
                # 跳过没有配对的单元格
                continue
now = datetime.datetime.now()
timestamp = now.strftime("%Y-%m-%d_%H-%M-%S")
filename = f"All-{timestamp}.csv"
# 保存到 CSV 文件
with open(filename, 'w', newline='', encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerow(['ID', '物品名称'])  # 写入表头
    writer.writerows(items)  # 写入数据

print("报表已成功导出为 '"+filename+"'")