python-qlv-helper 0.2.0__py3-none-any.whl → 0.6.0__py3-none-any.whl

qlv_helper/http/order_page.py

@@ -10,8 +10,10 @@
 # ---------------------------------------------------------------------------------------------------------
 """
 import re
+import json
 import aiohttp
 from datetime import datetime
+from urllib.parse import quote
 from bs4 import BeautifulSoup, Tag
 from collections import OrderedDict
 from typing import Dict, Any, Optional, List
@@ -22,8 +24,8 @@ from qlv_helper.utils.type_utils import get_key_by_index, get_value_by_index, sa
 
 
 async def get_order_page_html(
-        order_id: int, domain: str, protocol: str = "http", retry: int = 1, timeout: int = 5, enable_log: bool = True,
-        cookie_jar: Optional[aiohttp.CookieJar] = None, playwright_state: Dict[str, Any] = None
+        *, order_id: int, domain: str, protocol: str = "http", retry: int = 1, timeout: int = 5,
+        enable_log: bool = True, cookie_jar: Optional[aiohttp.CookieJar] = None, playwright_state: Dict[str, Any] = None
 ) -> Dict[str, Any]:
     order_http_client = HttpClientFactory(
         protocol=protocol if protocol == "http" else "https",
@@ -41,6 +43,47 @@ async def get_order_page_html(
     )
 
 
+async def fill_procurement_info_with_http(
+        *, order_id: int, qlv_domain: str, amount: float, pre_order_id: str, platform_user_id: str, user_password: str,
+        passengers: List[str], fids: str, pids: List[str], transaction_id: str, qlv_protocol: str = "http",
+        retry: int = 1, timeout: int = 5, enable_log: bool = True, cookie_jar: Optional[aiohttp.CookieJar] = None,
+        playwright_state: Dict[str, Any] = None, data_list: Optional[List[Dict[str, Any]]] = None
+) -> Dict[str, Any]:
+    client = HttpClientFactory(
+        protocol=qlv_protocol, domain=qlv_domain, timeout=timeout, enable_log=enable_log, retry=retry,
+        cookie_jar=cookie_jar or aiohttp.CookieJar(),
+        playwright_state=playwright_state
+    )
+
+    headers = {
+        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
+        "Referer": f"{qlv_protocol}://{qlv_domain}/OrderProcessing/NewTicket/{order_id}?&r={datetime.now().strftime("%Y%m%d%H%M%S")}",
+    }
+    if data_list:
+        data = data_list
+    else:
+        remark = f"{platform_user_id}/{user_password}"
+        pName = "," + ",".join(passengers) + ","
+        pids = ",".join(pids)
+        data = [
+            {"tradingDat": datetime.now().strftime("%Y-%m-%d %H:%M"), "outTktPF": "G航司官网", "outTktLoginCode": "",
+             "typeName": "VCC", "accountID": "8", "accountName": "VCC", "transactionAmount": f"{amount}",
+             "mainCheckNumber": "", "airCoOrderID": f"{pre_order_id}", "QuotaResultAmount": "0.00",
+             "remark": f"{quote(remark)}", "flightIdx": ",1,", "pName": f"{pName}", "orderID": f"{order_id}",
+             "businessTypeName": "机票", "tradingItems": "机票支出", "actualAmount": 0, "pType": "成人",
+             "fids": f"{fids}", "pids": f"{pids}", "iscandel": "true", "isbatch": "false",
+             "MainCheckNumberValus": f"{transaction_id}",
+             "OfficeNo": "", "PriceStdActual": "0.00", "ReturnAmount": "0.0000", "OffsetReturnAmount": "0.00",
+             "profitRemark": "", "preSaleType": "", "ErrorType": "", "OutTktPFTypeID": "34", "OutTicketAccount": "",
+             "OutTicketAccountID": "", "OutTicketPWD": "", "OutTicketTel": "", "OutTicketPNR": ""}
+        ]
+    data = f"list={json.dumps(data)}&isPayAll=true&delTransactionids=&OutTicketLossType&OutTicketLossRemark="
+    return await client.request(
+        method="POST", url="/OrderProcessing/PurchaseInfoSave",
+        headers=headers, is_end=True, data=data.encode("utf-8")
+    )
+
+
 def order_info_static_headers() -> OrderedDict[str, str]:
     return OrderedDict([
         ("receipted_ota", "OTA实收"),  # 0
@@ -55,40 +98,73 @@ def order_info_static_headers() -> OrderedDict[str, str]:
 
 def parser_order_info(html: str) -> Dict[str, Any]:
     soup = BeautifulSoup(html, "html.parser")
-    # 找到目标 table
-    table = soup.find("table", class_="table no_border")
-    if not table:
+    # 找到目标 table_border
+    table_border = soup.find("table", class_="table no_border")
+    if not table_border:
+        return {}
+
+    table_flight = soup.find("table", class_="info_flight")
+    if not table_border:
         return {}
 
     # 所有 td
-    tds = table.find_all("td")
+    tds_border = table_border.find_all("td")
     result = {}
 
-    for td in tds:
-        text = td.get_text(strip=True)
-        # 如果 td 内没有冒号、也不是按钮，跳过
-        if "：" not in text:
-            continue
-        # 按 "：" 进行分割
+    for td in tds_border:
         try:
-            key, value = text.split("：", 1)
-        except (Exception, ValueError):
-            continue
-        # 去掉换行符、空格
-        key = key.strip()
-        value = value.strip()
-
-        # 如果 value 为空，尝试取 <b> 或其他控件内文本
-        if not value:
-            b = td.find("b")
-            if b:
-                value = b.get_text(strip=True)
-
-        # 去掉尾部不需要的空格
-        value = value.replace("\u00a0", "").strip()
-        value = value[1:] if isinstance(value, str) and value.startswith("[") else value
-        value = value[:-1] if isinstance(value, str) and value.endswith("]") else value
-        result[key] = safe_convert_advanced(value)
+            text = td.get_text(strip=True)
+            # 如果 td 内没有冒号、也不是按钮，跳过
+            if "：" not in text:
+                continue
+            # 按 "：" 进行分割
+            try:
+                key, value = text.split("：", 1)
+            except (Exception, ValueError):
+                continue
+            # 去掉换行符、空格
+            key = key.strip()
+            value = value.strip()
+
+            # 如果 value 为空，尝试取 <b> 或其他控件内文本
+            if not value:
+                b = td.find("b")
+                if b:
+                    value = b.get_text(strip=True)
+
+            # 去掉尾部不需要的空格
+            value = value.replace("\u00a0", "").strip()
+            value = value[1:] if isinstance(value, str) and value.startswith("[") else value
+            value = value[:-1] if isinstance(value, str) and value.endswith("]") else value
+            result[key] = safe_convert_advanced(value)
+        except (Exception,):
+            pass
+
+    # 所有 td
+    tds_flight = table_flight.find_all("td")
+
+    for td in tds_flight:
+        try:
+            dat_dep = td.find("span", class_="DatDep")
+            if dat_dep:
+                text = dat_dep.get_text(strip=True)
+                result["dat_dep"] = text + ":00"
+            city_dep = td.find("span", class_="CityDep")
+            if city_dep:
+                text = city_dep.get_text(strip=True)
+                city_dep = text.split("【")[0].strip()
+                result["city_dep"] = city_dep
+            dat_arr = td.find("p", class_="DatArr")
+            if dat_arr:
+                text = dat_arr.get_text(strip=True)
+                result["dat_arr"] = text + ":00"
+            city_arr = td.find("span", class_="CityArr")
+            if city_arr:
+                text = city_arr.get_text(strip=True)
+                city_arr = text.split("【")[0].strip()
+                result["city_arr"] = city_arr
+        except (Exception,):
+            pass
     return convert_cn_to_en(data=result, header_map=order_info_static_headers())
 
 
@@ -121,6 +197,8 @@ def flight_extend_headers() -> OrderedDict[str, str]:
         ("id_valid_dat", " 证件有效期"),  # 9
         ("code_dep", " 起飞机场"),  # 10
         ("code_arr", " 抵达机场"),  # 11
+        ("pid", "乘客ID"),  # 12
+        ("fid", "航段ID"),  # 13
     ])
 
 
@@ -236,7 +314,20 @@ def parse_order_flight_table_passenger_info(raw: Tag, headers: OrderedDict[str,
     nationality = guobies[0].get_text(strip=True) if len(guobies) > 0 else ""
     issue_country = guobies[1].get_text(strip=True) if len(guobies) > 1 else ""
 
-    return {
+    a1 = raw.find("a", id=lambda x: x and x.startswith("IDNo_"))
+    a2 = raw.find("a", id=lambda x: x and x.startswith("detrni_"))
+    a3 = raw.find("a", id=lambda x: x and x.startswith("detrnif_"))
+    pid = None
+    if a1:
+        full_id = a1["id"]  # IDNo_279778
+        pid = full_id.split("_")[-1]
+    elif a2:
+        full_id = a2["id"]  # detrni_279778
+        pid = full_id.split("_")[-1]
+    elif a3:
+        full_id = a3["id"]  # detrnif_279778
+        pid = full_id.split("_")[-1]
+    result = {
         get_key_by_index(index=0, ordered_dict=headers): name,  # 姓名
         get_key_by_index(index=1, ordered_dict=headers): ptype,  # 类型: 成人/儿童
         get_key_by_index(index=2, ordered_dict=headers): id_type,  # 证件类型
@@ -246,8 +337,12 @@ def parse_order_flight_table_passenger_info(raw: Tag, headers: OrderedDict[str,
         get_key_by_index(index=6, ordered_dict=headers): sex,  # 性别
         get_key_by_index(index=7, ordered_dict=headers): nationality,  # 国籍
         get_key_by_index(index=8, ordered_dict=headers): issue_country,  # 签发国
-        get_key_by_index(index=9, ordered_dict=headers): id_valid  # 证件有效期
+        get_key_by_index(index=9, ordered_dict=headers): id_valid,  # 证件有效期
     }
+    if pid is not None:
+        #  乘客ID
+        result[get_key_by_index(index=12, ordered_dict=headers)] = pid
+    return result
 
 
 def parse_order_flight_table_row(
@@ -255,8 +350,7 @@ def parse_order_flight_table_row(
 ) -> Dict[str, Any]:
     """解析航班表每一行的数据"""
     tds = tr.find_all("td", recursive=False)
-    values = {}
-
+    values = {get_key_by_index(index=12, ordered_dict=extend_headers): tr["pid"]}
     for idx, td in enumerate(tds):
         if idx >= len(headers):
             continue
@@ -270,6 +364,14 @@ def parse_order_flight_table_row(
         else:
             raw = clean_order_flight_table(html=td)
             if "行程" in value:
+                fid = ""
+                input_tag = td.find('input', {'name': 'fid'})
+                fid_key = get_key_by_index(index=13, ordered_dict=extend_headers)
+                if input_tag:
+                    match = re.search(r'\d+', input_tag.get('value'))
+                    if match:
+                        fid = match.group()
+                    values[fid_key] = fid
                 code_dep_key = get_key_by_index(index=10, ordered_dict=extend_headers)
                 code_arr_key = get_key_by_index(index=11, ordered_dict=extend_headers)
                 raw_slice = raw.split("-")
@@ -280,7 +382,6 @@ def parse_order_flight_table_row(
                 values[key] = raw
             else:
                 values[key] = safe_convert_advanced(raw)
-
     return values
 
 
@@ -293,6 +394,8 @@ def extract_structured_table_data(table: Tag) -> List[Optional[Dict[str, Any]]]:
     for tr in table.find_all("tr")[1:]:  # 跳过表头
         rows.append(parse_order_flight_table_row(tr=tr, headers=headers, extend_headers=extend))
 
+    if rows:
+        rows = list({i["id_no"]: i for i in sorted(rows, key=lambda x: bool(x.get("fid")))}.values())
     return rows
 
 
@@ -300,14 +403,12 @@ def parser_order_flight_table(html: str) -> List[Optional[Dict[str, Any]]]:
     """解析航班表"""
     soup = BeautifulSoup(html, 'html.parser')
     # 三个主要的order_sort div
-    order_sections = soup.find_all('div', class_='order_sort')
-    section = order_sections[3] if len(order_sections) > 3 else Tag(name="")
+    table_sections = soup.find_all('table', class_='table table_border table_center')
+    table = table_sections[2] if len(table_sections) > 2 else Tag(name="")
     results = list()
 
-    tables = section.find_all('table', class_='table table_border table_center')
-    for table in tables:
-        table_data = extract_structured_table_data(table)
-        if table_data:
-            results.extend(table_data)
+    table_data = extract_structured_table_data(table)
+    if table_data:
+        results.extend(table_data)
 
     return results

qlv_helper/http/order_table_page.py

@@ -81,10 +81,34 @@ async def get_domestic_ticket_outed_page_html(
         json_data["PageCountFormPage"] = pages
         return await order_http_client.request(method="post", url=url, is_end=is_end, json_data=json_data)
 
+async def get_domestic_unticketed_order_page_html(
+        domain: str, protocol: str = "http", retry: int = 1, timeout: int = 5, enable_log: bool = True,
+        cookie_jar: Optional[aiohttp.CookieJar] = None, playwright_state: Dict[str, Any] = None, current_page: int = 1,
+        pages: int = 1, order_http_client: HttpClientFactory = None, is_end: bool = True
+) -> Dict[str, Any]:
+    if not order_http_client:
+        order_http_client = HttpClientFactory(
+            protocol=protocol if protocol == "http" else "https",
+            domain=domain,
+            timeout=timeout,
+            retry=retry,
+            enable_log=enable_log,
+            cookie_jar=cookie_jar,
+            playwright_state=playwright_state
+        )
+    url = "/OrderList/GuoNei_TicketOutUndo"
+    if current_page == 1:
+        return await order_http_client.request(method="get", url=url, is_end=is_end)
+    else:
+        json_data = deepcopy(kwargs)
+        json_data["JumpPageFromPage"] = current_page
+        json_data["PageCountFormPage"] = pages
+        return await order_http_client.request(method="post", url=url, is_end=is_end, json_data=json_data)
+
 
 def processing_static_headers() -> OrderedDict[str, str]:
     return OrderedDict([
-        ("source_ota", "来源"),  # 0
+        ("source_name", "来源"),  # 0
         ("id", "订单号"),  # 1
         ("raw_order_no", "平台订单号"),  # 2
         ("adult_pnr", "成人PNR"),  # 3
@@ -104,7 +128,7 @@ def processing_static_headers() -> OrderedDict[str, str]:
 
 def completed_static_headers() -> OrderedDict[str, str]:
     return OrderedDict([
-        ("source_ota", "来源"),  # 0
+        ("source_name", "来源"),  # 0
         ("id", "订单号"),  # 1
         ("raw_order_no", "平台订单号"),  # 2
         ("adult_pnr", "成人PNR"),  # 3
@@ -274,8 +298,10 @@ def parse_order_row(cells: ResultSet[Tag], headers: OrderedDict, extend_headers:
                 total_child_key = get_key_by_index(ordered_dict=extend_headers, index=7)
                 order_data[total_adult_key] = safe_convert_advanced(cell_text_slice[1])
                 order_data[total_child_key] = safe_convert_advanced(cell_text_slice[2])
-            else:
+            elif header_key == "receipted":
                 order_data[header_key] = safe_convert_advanced(cell_text)
+            else:
+                order_data[header_key] = cell_text
 
             # 提取特殊属性
             extract_special_attributes(cells=cells, order_data=order_data, header=headers)
@@ -317,7 +343,7 @@ def parse_order_table(html: str, table_state: str = "proccessing") -> List[Optio
         cells = row.find_all(['td', 'th'])
 
         order_data = parse_order_row(cells, headers=headers, extend_headers=extend, row_index=i)
-        if order_data:
+        if order_data and order_data.get("id") is not None:
             orders.append(order_data)
 
     return orders

qlv_helper/po/domestic_activity_order_page.py

@@ -10,8 +10,8 @@
 # ---------------------------------------------------------------------------------------------------------
 """
 from bs4 import BeautifulSoup
-from qlv_helper.po.base_po import BasePo
 from typing import Tuple, Union, List, Any, Dict
+from playwright_helper.libs.base_po import BasePo
 from playwright.async_api import Page, TimeoutError as PlaywrightTimeoutError, Locator
 
 
@@ -105,13 +105,11 @@ class DomesticActivityOrderPage(BasePo):
                 # 解析当前页的数据
                 rows = self.parse_tbody_rows(tbody_html=tbody_html, headers=headers)
                 all_rows.extend(rows)
-                print(all_rows)
 
                 # --- 2. 获取当前页数与总页数 ---
                 current_page: int = int(await self.__page.locator('//label[@id="Lab_PageIndex"][1]').inner_text())
                 pages: int = int(await self.__page.locator('//label[@id="Lab_PageCount"][1]').inner_text())
 
-                print(current_page, pages)
                 # --- 3. 如果到最后一页，退出 ---
                 if current_page >= pages:
                     break
@@ -122,7 +120,7 @@ class DomesticActivityOrderPage(BasePo):
                 # 等待页面刷新（简单但稳）
                 await self.__page.wait_for_timeout(timeout=refresh_wait_time)
             except PlaywrightTimeoutError:
-                all_rows.append(dict(error_message=f"元素 '{self.__table_selector}' 未在 {timeout} 秒内找到"))
+                all_rows.append(dict(error_message=f"元素 '{self.__table_selector}' 未在 {refresh_wait_time} 秒内找到"))
             except Exception as e:
                 all_rows.append(dict(error_message=f"检查元素时发生错误: {str(e)}"))
 

qlv_helper/po/login_page.py

@@ -10,7 +10,7 @@
 # ---------------------------------------------------------------------------------------------------------
 """
 from typing import Tuple, Union
-from qlv_helper.po.base_po import BasePo
+from playwright_helper.libs.base_po import BasePo
 from qlv_helper.utils.ocr_helper import get_image_text
 from playwright.async_api import Page, TimeoutError as PlaywrightTimeoutError, Locator
 

qlv_helper/po/main_page.py

@@ -10,8 +10,7 @@
 # ---------------------------------------------------------------------------------------------------------
 """
 from typing import Tuple, Union
-from qlv_helper.po.base_po import BasePo
-from qlv_helper.utils.ocr_helper import get_image_text
+from playwright_helper.libs.base_po import BasePo
 from playwright.async_api import Page, TimeoutError as PlaywrightTimeoutError, Locator
 
 
@@ -42,7 +41,7 @@ class MainPage(BasePo):
         except Exception as e:
             return False, f"检查元素时发生错误: {str(e)}"
 
-    async def get_level1_menu_order_checkout(self) -> Tuple[bool, Union[Locator, str]]:
+    async def get_level1_menu_order_checkout(self, timeout: float = 5.0) -> Tuple[bool, Union[Locator, str]]:
         selector: str = "//span[contains(normalize-space(), '订单出票')]"
         try:
             locator = self.__page.locator(selector)
@@ -56,7 +55,7 @@ class MainPage(BasePo):
         except Exception as e:
             return False, f"检查元素时发生错误: {str(e)}"
 
-    async def get_level2_menu_order_checkout(self) -> Tuple[bool, Union[Locator, str]]:
+    async def get_level2_menu_order_checkout(self, timeout: float = 5.0) -> Tuple[bool, Union[Locator, str]]:
         selector: str = "//a[@menuname='国内活动订单']"
         try:
             locator = self.__page.locator(selector)