福建省人民政府

REITs专题数据/policy-fujian.py

-import time
+import time
@@ -52,6 +52,7 @@ def getContent(num, url, publishDate):
     url_ = url.replace(url_, '')
 
     soup = getSoup(url)
+    policy.paserUrl(soup, url)
     contentWithTag = soup.find('div', class_='TRS_Editor')
     try:
         scripts = contentWithTag.find_all('script')
@@ -65,10 +66,13 @@ def getContent(num, url, publishDate):
             style.decompose()
     except:
         pass
-    a_list = contentWithTag.find_all('a')
+    a_list = soup.find('div', class_='xl_list1').find_all('a')
     for a in a_list:
-        fj_href = a.get('href').replace('./', url_)
-
+        fj_href = a.get('href')
+        if fj_href:
+            pass
+        else:
+            continue
         fj_title = a.text.lstrip().strip()
         category = os.path.splitext(fj_href)[1]
         if category not in fj_title: