核心人员更新采集

comData/Tyc/CorePerson_Update.py

@@ -56,12 +56,11 @@ def get_html(tycid, driver, headers):
             return 0
 
 
-@retry(tries=5, delay=2)
+@retry(tries=5, delay=3)
 def get_page(url, s, headers):
     ip = baseCore.get_proxy()
-    res = s.get(url=url, headers=headers, proxies=ip)
+    res = s.get(url=url, headers=headers, proxies=ip, timeout=(5, 10))
     # res = s.get(url=url, headers=headers, verify=False)
-    time.sleep(1)
     if res.status_code != 200:
         raise
     data_page = res.json()
@@ -120,7 +119,7 @@ def doJob():
     url = 'https://www.tianyancha.com/'
     driver.get(url)
     driver.maximize_window()
-    for i in range(10):
+    for i in range(1000):
         # while True:
         # todo:设置cookies的使用
         headers = {
@@ -138,9 +137,9 @@ def doJob():
         else:
             continue
         # 根据从Redis中拿到的社会信用代码,在数据库中获取对应基本信息
-        # item = baseCore.redicPullData('UpdateCoreperson:SocialCode_CompanyName')
+        item = baseCore.redicPullData('UpdateCoreperson:SocialCode_CompanyName')
         # 判断 如果Redis中已经没有数据，则等待
-        item = '914403003060602251|深圳爱尔创口腔技术有限公司'
+        # social_code = '91110108780992804C'
         if item == None:
             time.sleep(30 * 60)
             continue
@@ -217,9 +216,11 @@ def doJob():
                 continue
             elif charge == -2:
                 # 该企业没有人员信息
+
                 token.updateTokeen(id_cookie, 2)
                 baseCore.rePutIntoR('UpdateCoreperson:SocialCode_CompanyName', item)
                 log.info(f"{id}---{xydm}----{tycid}----没有核心人员或需要滑动验证----重新放入redis")
+                time.sleep(5)
                 # log.info(f"{id}---{xydm}----{tycid}----没有核心人员")
                 continue
 
@@ -288,25 +289,22 @@ def doJob():
                     errorCode = data_page['errorCode']
                 else:
                     res = None
-                    for c in range(3):
-                        try:
                     for d in range(3):
                         ip = baseCore.get_proxy()
                         url_ = url.format(t, tycid, page)
                         # url_ = 'https://capi.tianyancha.com/cloud-company-background/company/dim/staff?_=1706765329671&gid=8715844&pageSize=20&pageNum=1'
-                                res = s.get(url_, headers=headers, proxies=ip)  # ,verify=False
-                                # res = s.get(url_, headers=headers)  # ,verify=False
-                                # res = requests.get(url_, headers=headers, verify=False)  # ,verify=False
-                                time.sleep(randint(2, 4))
+                        try:
+                            res = s.get(url_, headers=headers, proxies=ip, timeout=(5, 10))  # ,verify=False
+                        except requests.exceptions.RequestException as e:
+                            log.info(e)
+                            time.sleep(1)
+                            continue
                         data_page = res.json()
                         errorCode = res.json()['errorCode']
                         if errorCode != 0:
                             continue
                         else:
                             break
-                            break
-                        except:
-                            continue
                     res.close()
                 if errorCode == 0:
                     pass
@@ -329,9 +327,9 @@ def doJob():
                 # todo: 关闭连接
                 # res.close()
                 log.info(f'----flag:{flag}----')
+                log.info(f'-----list_all:{len(list_all)}----')
                 if flag == 1:
                     for one_info in list_all:
-
                         name = one_info['name']
                         sex = one_info['sex']
                         education = one_info['education']
@@ -433,13 +431,28 @@ def doJob():
 
                         person_id = one_info['id']
                         person_url = f'https://www.tianyancha.com/human/{person_id}-c{tycid}'
-                        # person_res = requests.get(person_url, headers=headers, proxies=ip)
-                        person_res = requests.get(person_url, headers=headers)
+                        person_soup = None
+                        while True:
+                            try:
+                                ip = baseCore.get_proxy()
+                                person_res = requests.get(person_url, headers=headers, proxies=ip, timeout=(5, 10))
                                 person_soup = BeautifulSoup(person_res.content, 'html.parser')
+                                break
+
+                            except requests.exceptions.Timeout:
+                                log.info('请求超时')
+                                time.sleep(1)
+                            except requests.exceptions.RequestException as e:
+                                log.info(e)
+                                time.sleep(1)
+                            except:
+                                log.info('简介请求失败')
+                                time.sleep(3)
                         try:
                             personInfo = person_soup.find('span', {'class': '_56d0a'}).text.strip()
                         except:
                             personInfo = ''
+
                         try:
                             person_img = one_info['logo']
                         except: