''

amazon_spider/other_job/spider/access_api.py

@@ -161,7 +161,7 @@ class AccessApi(object):
     def __init__(self):
         # self.cookie_dict = {}
         self.seed_key = 'finance:cds_account_queue'
-        self.seeds = [[{"@class":"com.alibaba.fastjson.JSONObject","u_key":65,"pwd":"CDS14102021","account":"831380418759"}]]
+        self.seeds = [[{'@class': 'com.alibaba.fastjson.JSONObject', 'phoneSuffix': '6793', 'u_key': 54, 'pwd': 'TBI15092022', 'account': '335829635920'}]]
 
     def get_seed(self):
         # seeds = self.seeds.pop()
@@ -430,10 +430,10 @@ class AccessApi(object):
                 msg = rq.post(url, data=data, headers=headers, files=files, timeout=60).json()
                 time.sleep(3)
                 if msg.get('code') in [400, 200]:
-                    logging.info(f"文件上传成功 {seed.get('account')} {msg}")
+                    logging.info(f"html文件上传成功 {seed.get('account')} {msg}")
                     return True
                 else:
-                    logging.info(f"文件上传失败重试")
+                    logging.info(f"html文件上传失败重试")
                     continue
             except curl.CurlError as e:
                 if e.code == const.CurlECode.OPERATION_TIMEDOUT:
@@ -470,8 +470,8 @@ class AccessApi(object):
         }
         response = self.request_dis(url=url, method="GET", headers=headers, cookies=cookies, params=params, timeout=10)
         # ukey_c79 / c88_时间戳.html
-        with open(f"./tax_htmls/{seed.get('u_key')}_c88_{int(time.time())}.html", "w", encoding='utf-8') as f:
-            f.write(response.text)
+        # with open(f"./tax_htmls/{seed.get('u_key')}_c88_{int(time.time())}.html", "w", encoding='utf-8') as f:
+        #     f.write(response.text)
         # response = requests.get(url, headers=headers, cookies=cookies, proxies=proxies, params=params, timeout=10)
 
         sel = Selector(text=response.text, type="html")
@@ -518,8 +518,8 @@ class AccessApi(object):
         url = "https://www.tax.service.gov.uk/customs/documents/import-vat"
         # response = requests.get(url, headers=headers, cookies=cookies, proxies=proxies, timeout=10)
         response = self.request_dis(url=url, method="GET", headers=headers, cookies=cookies, timeout=10)
-        with open(f"./tax_htmls/{seed.get('u_key')}_c79_{int(time.time())}.html", "w", encoding='utf-8') as f:
-            f.write(response.text)
+        # with open(f"./tax_htmls/{seed.get('u_key')}_c79_{int(time.time())}.html", "w", encoding='utf-8') as f:
+        #     f.write(response.text)
         sel = Selector(text=response.text, type="html")
 
         c79_dict = {}
@@ -774,13 +774,17 @@ class AccessApi(object):
                 #         logging.info(f"代理ip请求失败{seed.get('account')}")
                 #         return False
                 #     continue
-
-            for k, v in c88_dict.items():
-                c78_dict[k].update(v)
+            all_keys = set(c88_dict.keys()).union(c78_dict.keys())
+            merged = {}
+            for key in all_keys:
+                merged[key] = {
+                    'file_c88': c88_dict.get(key, {}).get('file_c88', None),
+                    'file_c79': c78_dict.get(key, {}).get('file_c79', None)
+                }
             logging.info(f"长度 {len(c78_dict)} {c78_dict}")
             if self.push_file_new(c78_dict, seed):
                 self.error_msg_seed("下载完成", seed)
-                logging.info(f"上传成功{seed}")
+                logging.info(f"CDS上传成功{seed}")
                 return True
             else:
                 self.error_msg_seed("已失效", seed)
@@ -850,6 +854,7 @@ class AccessApi(object):
             if seeds:
                 threads = []
                 for i in seeds:
+                    # thread = threading.Thread(target=self.run, args=(i,))
                     thread = threading.Thread(target=self.run, args=(json.loads(i),))
                     threads.append(thread)
                     thread.start()