daideliangxing

REITs专题数据/cushman.py

-import re
+import re
@@ -88,34 +88,9 @@ def doJob():
                 log.error(f'第{page}页==={name}===连接失败')
                 continue
             title = name.replace('/',' ').replace('|',' ').replace('？',' ').replace('"','”')
-            file = f'./研究咨询/戴德梁兴/行业视角-研究报告/{title}.pdf'
-            num_ = 2
-            while True:
-                flg = os.path.isfile(file)
-                if flg:
-                    log.info(f'{name}===有重名')
-                    title_ = f'{title}-{num_}'
-                    file = f'./研究咨询/戴德梁兴/行业视角-研究报告/{title_}.pdf'
-                    num_ += 1
-                else:
-                    try:
-                        title = title_
-                    except:
-                        pass
-                    break
-            try:
-                with open(file, 'wb') as f:
-                    f.write(content)
-                log.info(f'{name}===成功')
-                fjtitle_list += title + '\n'
-                fjhref_list += href + '\n'
-                data = [num, name, origin, href, summary, fjtitle_list, fjhref_list]
-                data_list.append(data)
-            except:
-                log.error(f'第{page}页==={name}===保存失败')
-    df = pd.DataFrame(np.array(data_list))
-    df.columns = ['序号', '标题', '来源', '原文链接', '摘要', '附件名称', '附件连接']
-    df.to_excel('./研究咨询/戴德梁兴/行业视角-研究报告.xlsx', index=False)
+
+
+
 
 
 if __name__ == '__main__':