41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
import pandas as pd
|
|
import requests
|
|
from tqdm import tqdm
|
|
from bs4 import BeautifulSoup
|
|
|
|
all_data_list = []
|
|
keys = ["门店","订单编号","产品类型","产品名称","型号","数量","采购单价","销售单价",
|
|
"采购金额","销售金额","毛利润","下单人","接单人","车牌号"]
|
|
reversed_keys = list(reversed(keys))
|
|
|
|
for i in tqdm(range(1, 2)):
|
|
url = f"http://rp.chezizhu.com/ReportServer?_=1745552902755&__boxModel__=true&op=page_content&sessionID=27200&pn={i}&__fit__=false"
|
|
|
|
header = {
|
|
"Referer": "http://rp.chezizhu.com/ReportServer?reportlet=czz/storage/prod_sale_dtl_jm.cpt&servicer_id=B9GC8C8oZpTAxmUR1YEp9q&hideexport=true&database=chezizhu_14",
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.0.0",
|
|
"X-Requested-With": "XMLHttpRequest"
|
|
}
|
|
|
|
res = requests.post(url, headers=header)
|
|
soup = BeautifulSoup(res.text, "html.parser")
|
|
|
|
# 定位真正的数据行（跳过标题行）
|
|
for tr in soup.select('tr:not(:has(th))'): # 排除包含表头的行
|
|
tds = [td.get_text(strip=True) for td in tr.find_all("td")]
|
|
reversed_tds = list(reversed(tds))
|
|
|
|
# 如果 reversed_tds 长度不够，填充空字符串
|
|
if len(reversed_tds) < len(reversed_keys):
|
|
reversed_tds += [""] * (len(reversed_keys) - len(reversed_tds))
|
|
elif len(reversed_tds) > len(reversed_keys):
|
|
reversed_tds = reversed_tds[:len(reversed_keys)]
|
|
|
|
# 构建字典（反转后的 keys 和 tds）
|
|
row_data = dict(zip(reversed_keys, reversed_tds))
|
|
all_data_list.append(row_data)
|
|
|
|
# break
|
|
print(all_data_list)
|
|
df = pd.DataFrame(all_data_list)
|
|
df.to_excel(r'D:\Idea Project\F6+宜搭+其它(1)\new\文件输出\大唛云销售明细.xlsx', index=False) |