103 lines
3.8 KiB
Python
103 lines
3.8 KiB
Python
from playwright.sync_api import sync_playwright
|
|
import time
|
|
import pandas as pd
|
|
|
|
|
|
def extract_table_data(page):
|
|
"""从当前页面提取表格数据"""
|
|
rows = page.query_selector_all("table.dg tbody tr")
|
|
data = []
|
|
for row in rows:
|
|
# 跳过表头和合计行
|
|
if row.query_selector("th") or "合计" in row.text_content():
|
|
continue
|
|
|
|
cells = row.query_selector_all("td")
|
|
if len(cells) < 12:
|
|
continue # 非数据行
|
|
|
|
record_id = row.query_selector("input[title]").get_attribute("title") or ""
|
|
car_no = cells[2].text_content().strip()
|
|
name = cells[3].text_content().strip()
|
|
card_no = cells[4].text_content().strip()
|
|
card_type = cells[5].text_content().strip()
|
|
package = cells[6].text_content().strip()
|
|
total_times = cells[7].text_content().strip()
|
|
consumed = cells[8].text_content().strip()
|
|
remaining = cells[9].text_content().strip()
|
|
remaining_cost = cells[10].text_content().strip()
|
|
expire_date = cells[11].text_content().strip()
|
|
|
|
data.append({
|
|
"ID": record_id,
|
|
"车牌": car_no,
|
|
"姓名": name,
|
|
"卡号": card_no,
|
|
"卡类型": card_type,
|
|
"套餐项目": package,
|
|
"总次数": total_times,
|
|
"消费": consumed,
|
|
"剩余": remaining,
|
|
"剩余成本": remaining_cost,
|
|
"到期日期": expire_date
|
|
})
|
|
return data
|
|
|
|
|
|
def main():
|
|
# ====== 手动设置页码范围 ======
|
|
start_page = 1 # 起始页（包含）
|
|
end_page = 5 # 结束页（包含）
|
|
# ============================
|
|
|
|
with sync_playwright() as p:
|
|
browser = p.chromium.launch(headless=False, slow_mo=300)
|
|
context = browser.new_context()
|
|
|
|
# 设置你的 Cookie（请根据实际情况更新）
|
|
context.add_cookies([
|
|
{"name": "ASP.NET_SessionId", "value": "knhs0hxsbmolk20gidmlis3j", "domain": "crm.zhongtukj.com",
|
|
"path": "/"},
|
|
{"name": "ztrjnew@4db97b96-12af-45b0-b232-fd1e9b7a672e@",
|
|
"value": "PassWord=wZn2IuvdWeE=&RememberPwd=RXv90LpPskw=&UserId=nzK31b3ZYVQ=&CSID=VjfeyHPOjnU=&UserName=fDfTOArNJXHmbGEeaShOsw==&SID=nkNRF6dD83c=&RoleId=1X5bqQAfxQY=&GroupId=KUxCDdt69t4=",
|
|
"domain": "crm.zhongtukj.com", "path": "/"}
|
|
])
|
|
|
|
page = context.new_page()
|
|
print(f"正在加载第 {start_page} 页（初始页）...")
|
|
page.goto("http://crm.zhongtukj.com/Boss/Customer/CustomerPackageList.aspx")
|
|
page.wait_for_load_state("networkidle")
|
|
time.sleep(2)
|
|
|
|
all_data = []
|
|
|
|
for current_page in range(start_page, end_page + 1):
|
|
if current_page == 1:
|
|
# 第 1 页已加载，直接提取
|
|
pass
|
|
else:
|
|
# 跳转到指定页码
|
|
print(f"正在跳转到第 {current_page} 页...")
|
|
page.evaluate(f"() => __doPostBack('AspNetPager', '{current_page}')")
|
|
page.wait_for_load_state("networkidle")
|
|
time.sleep(2) # 稳定等待
|
|
|
|
# 提取当前页数据
|
|
data = extract_table_data(page)
|
|
all_data.extend(data)
|
|
print(f" 第 {current_page} 页提取 {len(data)} 条记录")
|
|
|
|
browser.close()
|
|
|
|
# 保存结果
|
|
if all_data:
|
|
df = pd.DataFrame(all_data)
|
|
filename = f"D:\Idea Project\F6+宜搭+其它(1)\张阳脚本\文件输出\套餐卡_第{start_page}至{end_page}页.xlsx"
|
|
df.to_excel(filename, index=False)
|
|
print(f"\n✅ 共提取 {len(all_data)} 条记录，已保存到 '{filename}'")
|
|
else:
|
|
print("⚠️ 未提取到任何数据")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |