#update crawler

QUANTAXIS/QACmd/__init__.py

@@ -234,8 +234,8 @@ def do_save(self, arg):
                 QA_SU_save_stock_list('tdx')
                 QA_SU_save_stock_block('tdx')
                 # QA_SU_save_stock_info('tdx')
-                QA_SU_save_report_calendar_his()
-                QA_SU_save_stock_divyield_his()
+                # QA_SU_save_report_calendar_his()
+                # QA_SU_save_stock_divyield_his()
 
             elif len(arg) == 1 and arg[0] == 'day':
                 if QA_Setting().client.quantaxis.user_list.find({'username': 'admin'}).count() == 0:
@@ -251,8 +251,8 @@ def do_save(self, arg):
                 QA_SU_save_index_list('tdx')
                 QA_SU_save_stock_list('tdx')
                 QA_SU_save_stock_block('tdx')
-                QA_SU_save_stock_divyield_day()
-                QA_SU_save_report_calendar_day()
+                # QA_SU_save_stock_divyield_day()
+                # QA_SU_save_report_calendar_day()
 
             elif len(arg) == 1 and arg[0] == 'min':
                 if QA_Setting().client.quantaxis.user_list.find({'username': 'admin'}).count() == 0:

QUANTAXIS/QAWeb/backtesthandles.py

@@ -45,7 +45,7 @@
 
 
 class BacktestHandler(QAWebSocketHandler):
-
+    
     client={}
     def open(self):
         self.client.add(self)

QUANTAXIS_CRAWLY/gecko_example.py

@@ -0,0 +1,39 @@
+import time
+
+import pandas as pd
+from selenium import webdriver
+
+"""这里我给了一个同花顺的页面爬虫 用于gecko_driver  也就是 火狐浏览器内核爬虫的教学
+
+推荐使用火狐浏览器的内核 配置方便
+"""
+
+opener = webdriver.Firefox()  # should make sure the gekkodriver.exe in path
+data = []
+
+
+for item in ['gn', 'dy', 'thshy', 'zjhhy']:
+    opener.get('http://q.10jqka.com.cn/{}/'.format(item))
+
+    hpage = opener.page_source
+
+    # opener.save_screenshot('page_gn.png')
+    try:
+        if opener.find_element_by_class_name('cate_toggle.boxShadow').text == '收起':
+            pass
+        else:
+            opener.find_element_by_class_name('cate_toggle.boxShadow').click()
+    except:
+        pass
+
+    res = opener.find_elements_by_xpath('/html/body/div/div/div/div/div/a')
+
+    data.extend([[res.text, res.get_attribute('href'), item] for res in res])
+
+    time.sleep(1)
+
+
+res = pd.DataFrame(data)
+print(res)
+opener.close()
+res.to_csv('ths.csv')

config/update_x.py

@@ -58,6 +58,6 @@
 QA_SU_save_stock_list('tdx')
 QA_SU_save_stock_block('tdx')
 QA_SU_save_stock_info('tdx')
-QA_SU_save_stock_divyield_day()
-QA_SU_save_report_calendar_day()
+# QA_SU_save_stock_divyield_day()
+# QA_SU_save_report_calendar_day()