420 lines
15 KiB
Python
420 lines
15 KiB
Python
import requests
|
||
import json
|
||
import time
|
||
import os
|
||
from lxml import html
|
||
import re
|
||
|
||
# ================= 1. 配置区域 =================
|
||
base_url = "http://111.198.24.44:88/index.php"
|
||
|
||
# 登录参数
|
||
login_payload = {
|
||
"module": "Users",
|
||
"action": "Authenticate",
|
||
"return_module": "Users",
|
||
"return_action": "Login",
|
||
"user_name": "TEST", # 在这里填入真实的用户名
|
||
"user_password": "test", # 在这里填入真实的密码
|
||
"login_theme": "newskin"
|
||
}
|
||
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||
"Referer": "http://111.198.24.44:88/index.php?module=SalesOrder&action=index"
|
||
}
|
||
|
||
|
||
# ================= 2. 辅助函数 =================
|
||
def get_current_action_id():
|
||
"""生成当前时间的13位时间戳"""
|
||
return int(time.time() * 1000)
|
||
|
||
|
||
def clean_html_tags(text):
|
||
"""清洗HTML标签，保留文本内容"""
|
||
if not text:
|
||
return ""
|
||
|
||
# 移除HTML标签
|
||
clean_text = re.sub(r'<[^>]+>', ' ', text)
|
||
|
||
# 替换HTML实体
|
||
clean_text = clean_text.replace(' ', ' ')
|
||
|
||
# 合并多个空格和换行符
|
||
clean_text = re.sub(r'\s+', ' ', clean_text)
|
||
|
||
# 去除首尾空格
|
||
clean_text = clean_text.strip()
|
||
|
||
return clean_text
|
||
|
||
|
||
def extract_html_content(html_content, xpath):
|
||
"""从HTML中提取指定XPath的内容"""
|
||
try:
|
||
# 解析HTML
|
||
tree = html.fromstring(html_content)
|
||
|
||
# 尝试提取指定XPath的内容
|
||
elements = tree.xpath(xpath)
|
||
|
||
if elements:
|
||
# 获取元素的HTML内容
|
||
element_html = html.tostring(elements[0], encoding='unicode', pretty_print=True)
|
||
|
||
# 清洗HTML标签
|
||
cleaned_text = clean_html_tags(element_html)
|
||
|
||
# 同时保留原始HTML和清洗后的文本
|
||
return {
|
||
"raw_html": element_html,
|
||
"cleaned_text": cleaned_text
|
||
}
|
||
else:
|
||
print(f" ⚠️ 未找到XPath: {xpath}")
|
||
return {
|
||
"raw_html": "",
|
||
"cleaned_text": ""
|
||
}
|
||
|
||
except Exception as e:
|
||
print(f" ❌ HTML解析错误: {e}")
|
||
return {
|
||
"raw_html": "",
|
||
"cleaned_text": ""
|
||
}
|
||
|
||
|
||
def fetch_html_detail(session, record_id, xpath):
|
||
"""获取HTML页面详情并提取指定XPath内容"""
|
||
try:
|
||
# 构造HTML详情页URL
|
||
html_url = f"http://111.198.24.44:88/index.php?module=SalesOrder&action=DetailView&record={record_id}"
|
||
|
||
# 获取HTML页面
|
||
html_response = session.get(html_url, headers=headers)
|
||
|
||
if html_response.status_code == 200:
|
||
# 提取指定XPath的内容
|
||
extracted_content = extract_html_content(html_response.content, xpath)
|
||
return extracted_content
|
||
else:
|
||
print(f" ❌ HTML页面请求失败: HTTP {html_response.status_code}")
|
||
return {
|
||
"raw_html": "",
|
||
"cleaned_text": ""
|
||
}
|
||
|
||
except Exception as e:
|
||
print(f" ❌ 获取HTML详情失败: {e}")
|
||
return {
|
||
"raw_html": "",
|
||
"cleaned_text": ""
|
||
}
|
||
|
||
|
||
def extract_crmid_from_search_result(html_content):
|
||
"""从搜索结果页面提取CRM ID - 修正版本"""
|
||
crmids = []
|
||
|
||
try:
|
||
# 解析HTML
|
||
tree = html.fromstring(html_content)
|
||
|
||
# 首先找到SalesOrder模块的div
|
||
sales_order_div = tree.xpath('//div[@class="collapse in" and @id="collapse-SalesOrder"]')
|
||
|
||
if not sales_order_div:
|
||
print(" ⚠️ 未找到SalesOrder模块的搜索结果")
|
||
# 保存HTML用于调试
|
||
with open("debug_no_salesorder.html", "w", encoding="utf-8") as f:
|
||
f.write(html.tostring(tree, encoding='unicode', pretty_print=True))
|
||
return crmids
|
||
|
||
print(" ✅ 找到SalesOrder模块")
|
||
|
||
# 在新的div下查找特定的XPath模式
|
||
# 基础XPath：/html/body/div[1]/div/div[2]/div/div/div[5]/div/div/div/div/div[3]/div[2]/div[2]/a
|
||
# 我们需要找到所有符合这个模式的链接，其中倒数第二个div的索引会变化
|
||
|
||
# 方法1：使用通用XPath匹配模式
|
||
# 匹配所有符合 /html/body/div[1]/div/div[2]/div/div/div[5]/div/div/div/div/div[3]/div[n]/div[2]/a 的链接
|
||
# 其中n从2开始递增
|
||
|
||
# 构建通用XPath：查找所有在特定层级下的a标签
|
||
base_path = "/html/body/div[1]/div/div[2]/div/div/div[5]/div/div/div/div/div[3]"
|
||
|
||
# 查找所有可能的div[n]层级
|
||
n = 2
|
||
while True:
|
||
xpath_pattern = f"{base_path}/div[{n}]/div[2]/a"
|
||
elements = tree.xpath(xpath_pattern)
|
||
|
||
if not elements:
|
||
# 如果这个n没有找到，尝试下一个n+1
|
||
# 但我们先检查一下，如果n>10还没找到，可能就没有了
|
||
if n > 20: # 设置一个上限
|
||
break
|
||
n += 1
|
||
continue
|
||
|
||
# 找到元素，提取record值
|
||
for element in elements:
|
||
onclick_attr = element.get('onclick', '')
|
||
if onclick_attr:
|
||
# 从onclick中提取record值
|
||
match = re.search(r"record=(\d+)", onclick_attr)
|
||
if match:
|
||
crmid = match.group(1)
|
||
if crmid not in crmids:
|
||
crmids.append(crmid)
|
||
print(f" 从XPath {xpath_pattern} 找到CRM ID: {crmid}")
|
||
|
||
n += 1
|
||
|
||
# 方法2：备用方法 - 查找所有包含module=SalesOrder的链接
|
||
if not crmids:
|
||
print(" 尝试备用方法查找CRM ID...")
|
||
salesorder_links = tree.xpath('//a[contains(@onclick, "module=SalesOrder")]')
|
||
for link in salesorder_links:
|
||
onclick_attr = link.get('onclick', '')
|
||
if onclick_attr:
|
||
match = re.search(r"record=(\d+)", onclick_attr)
|
||
if match:
|
||
crmid = match.group(1)
|
||
if crmid not in crmids:
|
||
crmids.append(crmid)
|
||
|
||
print(f" 备用方法找到 {len(crmids)} 个CRM ID")
|
||
|
||
# 去重并返回
|
||
unique_crmids = list(set(crmids))
|
||
print(f" 去重后找到 {len(unique_crmids)} 个唯一的CRM ID")
|
||
|
||
return unique_crmids
|
||
|
||
except Exception as e:
|
||
print(f" ❌ 解析搜索结果失败: {e}")
|
||
import traceback
|
||
traceback.print_exc()
|
||
return crmids
|
||
|
||
|
||
def perform_search(session, query_string):
|
||
"""执行搜索并返回CRM ID列表"""
|
||
try:
|
||
# 构造搜索URL
|
||
search_url = f"http://111.198.24.44:88/index.php?module=Home&action=UnifiedSearch&selectedmodule=undefined&query_string={query_string}"
|
||
|
||
print(f" 正在搜索: {query_string}")
|
||
print(f" 搜索URL: {search_url}")
|
||
|
||
# 获取搜索结果页面
|
||
search_response = session.get(search_url, headers=headers)
|
||
|
||
if search_response.status_code != 200:
|
||
print(f" ❌ 搜索请求失败: HTTP {search_response.status_code}")
|
||
return []
|
||
|
||
# 保存搜索结果用于调试
|
||
with open("debug_search_result.html", "w", encoding="utf-8") as f:
|
||
f.write(search_response.text)
|
||
print(" 搜索结果已保存到 debug_search_result.html")
|
||
|
||
# 提取CRM ID
|
||
crmids = extract_crmid_from_search_result(search_response.content)
|
||
|
||
return crmids
|
||
|
||
except Exception as e:
|
||
print(f" ❌ 搜索失败: {e}")
|
||
return []
|
||
|
||
|
||
# ================= 3. 主程序逻辑 =================
|
||
def main():
|
||
session = requests.Session()
|
||
|
||
# 指定要提取的XPath
|
||
target_xpath = "/html/body/div[1]/div/div[2]/div[2]/form/div[1]/div[1]/div[2]"
|
||
|
||
try:
|
||
# --- 第一步：登录 ---
|
||
print("1. 正在登录...")
|
||
login_response = session.post(base_url, data=login_payload, headers=headers)
|
||
|
||
# 检查是否拿到 Cookie
|
||
if 'PHPSESSID' not in session.cookies:
|
||
print("⚠️ 警告：未检测到 PHPSESSID，登录可能失败，后续操作可能会出错。")
|
||
else:
|
||
print(" ✅ 登录成功，Cookie 已获取。")
|
||
|
||
# --- 第二步：获取用户搜索输入 ---
|
||
print("\n2. 请输入搜索内容:")
|
||
query_string = input(" 搜索关键词: ").strip()
|
||
|
||
if not query_string:
|
||
print(" ❌ 未输入搜索内容，程序退出。")
|
||
return
|
||
|
||
# 对查询字符串进行URL编码
|
||
import urllib.parse
|
||
encoded_query = urllib.parse.quote(query_string)
|
||
|
||
# --- 第三步：执行搜索并提取CRM ID ---
|
||
print(f"\n3. 正在执行搜索并提取CRM ID...")
|
||
crmids = perform_search(session, encoded_query)
|
||
|
||
if not crmids:
|
||
print(" ❌ 未找到任何CRM ID，程序退出。")
|
||
return
|
||
|
||
print(f" ✅ 成功提取到 {len(crmids)} 个CRM ID: {crmids}")
|
||
|
||
# --- 第四步：循环获取每个CRM ID的详情 ---
|
||
print(f"\n4. 开始逐个获取订单详情...")
|
||
success_count = 0
|
||
orders_data = []
|
||
|
||
for index, crmid in enumerate(crmids):
|
||
print(f"\n [{index + 1}/{len(crmids)}] 处理CRM ID: {crmid}")
|
||
|
||
# 1. 获取JSON详情 (产品详情)
|
||
json_detail = None
|
||
detail_payload = {
|
||
"module": "Plugins",
|
||
"pluginName": "DetailProductTable",
|
||
"action": "getTableData",
|
||
"moduleName": "SalesOrder",
|
||
"record": crmid,
|
||
"actionId": get_current_action_id(),
|
||
"isTool": "1"
|
||
}
|
||
|
||
try:
|
||
# 请求JSON详情
|
||
detail_resp = session.post(base_url, data=detail_payload, headers=headers)
|
||
json_detail = detail_resp.json()
|
||
print(f" ✅ JSON详情获取成功")
|
||
except Exception as e:
|
||
print(f" ❌ JSON详情获取失败: {e}")
|
||
json_detail = {"error": str(e)}
|
||
|
||
# 2. 获取HTML详情并提取指定XPath内容
|
||
print(f" 正在获取HTML详情...")
|
||
html_content = fetch_html_detail(session, crmid, target_xpath)
|
||
|
||
# 3. 构建订单数据
|
||
order_data = {
|
||
"crmid": crmid,
|
||
"json_details": json_detail,
|
||
"html_details": html_content,
|
||
"combined_data": {
|
||
"crmid": crmid,
|
||
"json_data": json_detail,
|
||
"html_extracted_text": html_content.get("cleaned_text", ""),
|
||
"html_raw": html_content.get("raw_html", "")
|
||
}
|
||
}
|
||
|
||
orders_data.append(order_data)
|
||
success_count += 1
|
||
print(f" ✅ CRM ID {crmid} 处理完成")
|
||
|
||
# 礼貌性延时，避免请求过快
|
||
time.sleep(0.5)
|
||
|
||
# --- 第五步：保存结果 ---
|
||
print(f"\n5. 正在保存结果...")
|
||
|
||
# 创建存储目录
|
||
import datetime
|
||
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||
output_dir = f"crm_data_search_{timestamp}"
|
||
os.makedirs(output_dir, exist_ok=True)
|
||
|
||
# 保存搜索查询信息
|
||
search_info = {
|
||
"query_string": query_string,
|
||
"encoded_query": encoded_query,
|
||
"search_time": time.strftime("%Y-%m-%d %H:%M:%S"),
|
||
"crmids_found": crmids,
|
||
"total_count": len(crmids)
|
||
}
|
||
|
||
with open(os.path.join(output_dir, "search_info.json"), 'w', encoding='utf-8') as f:
|
||
json.dump(search_info, f, ensure_ascii=False, indent=4)
|
||
|
||
# 保存完整的合并数据
|
||
full_filename = os.path.join(output_dir, "all_orders_combined.json")
|
||
with open(full_filename, 'w', encoding='utf-8') as f:
|
||
json.dump(orders_data, f, ensure_ascii=False, indent=4)
|
||
|
||
# 同时按crmid分别存储
|
||
print(f" 正在按CRM ID分别存储文件...")
|
||
for order in orders_data:
|
||
record_id = order.get('crmid')
|
||
if record_id:
|
||
# 单独保存每个crmid的数据
|
||
single_filename = os.path.join(output_dir, f"crm_{record_id}.json")
|
||
with open(single_filename, 'w', encoding='utf-8') as f:
|
||
json.dump(order, f, ensure_ascii=False, indent=4)
|
||
|
||
# 保存提取的文本内容为文本文件，便于查看
|
||
text_filename = os.path.join(output_dir, "extracted_texts.txt")
|
||
with open(text_filename, 'w', encoding='utf-8') as f:
|
||
f.write(f"=== 搜索查询: {query_string} ===\n")
|
||
f.write(f"=== 提取时间: {time.strftime('%Y-%m-%d %H:%M:%S')} ===\n")
|
||
f.write(f"=== 共找到 {len(crmids)} 个结果 ===\n\n")
|
||
|
||
for order in orders_data:
|
||
record_id = order.get('crmid')
|
||
if record_id:
|
||
extracted_text = order.get('html_details', {}).get('cleaned_text', '')
|
||
if extracted_text:
|
||
f.write(f"\n--- CRM ID: {record_id} ---\n")
|
||
f.write(f"{extracted_text}\n")
|
||
f.write("-" * 50 + "\n")
|
||
|
||
# 创建CSV格式的摘要文件
|
||
csv_filename = os.path.join(output_dir, "summary.csv")
|
||
with open(csv_filename, 'w', encoding='utf-8') as f:
|
||
f.write("CRM ID,提取文本长度,JSON数据状态\n")
|
||
for order in orders_data:
|
||
record_id = order.get('crmid')
|
||
text_length = len(order.get('html_details', {}).get('cleaned_text', ''))
|
||
json_status = "成功" if order.get('json_details') and not order.get('json_details').get(
|
||
'error') else "失败"
|
||
f.write(f"{record_id},{text_length},{json_status}\n")
|
||
|
||
print(f"\n✅ 全部完成！")
|
||
print(f" 成功处理: {success_count}/{len(crmids)} 个CRM ID")
|
||
print(f" 文件保存目录: {os.path.abspath(output_dir)}")
|
||
print(f" 主要文件:")
|
||
print(f" - search_info.json (搜索信息)")
|
||
print(f" - all_orders_combined.json (所有数据)")
|
||
print(f" - extracted_texts.txt (提取的文本)")
|
||
print(f" - summary.csv (数据摘要)")
|
||
print(f" - 按CRM ID单独存储的 {success_count} 个JSON文件")
|
||
|
||
# 显示提取的文本预览
|
||
print(f"\n=== 提取文本预览 ===")
|
||
for i, order in enumerate(orders_data[:3]): # 只显示前3个
|
||
record_id = order.get('crmid')
|
||
extracted_text = order.get('html_details', {}).get('cleaned_text', '')
|
||
preview = extracted_text[:100] + "..." if len(extracted_text) > 100 else extracted_text
|
||
print(f"CRM ID {record_id}: {preview}")
|
||
|
||
if len(orders_data) > 3:
|
||
print(f"... 还有 {len(orders_data) - 3} 个未显示")
|
||
|
||
except Exception as e:
|
||
print(f"\n❌ 程序发生未捕获的错误: {e}")
|
||
import traceback
|
||
traceback.print_exc()
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main() |