证监会年报 title加上.pdf后缀

comData/annualReport/证监会-年报.py

-import json
+import json
@@ -99,9 +99,19 @@ def SpiderByZJH(url, payload, dic_info, num, start_time):
             pdf_url_info = td_list[2]
             # print(pdf_url)
             pdf_url = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[0].strip('\'')
-            name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[1].strip('\'')
+            name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[1].strip('\'') + '.pdf'
 
             pub_time = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[2].strip('\'')
+            # todo:判断发布日期是否是日期格式
+            pattern = r"^\d{4}-\d{2}-\d{2}$"  # 正则表达式匹配YYYY-MM-DD格式的日期
+            date_time_pattern = r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}"
+            if re.match(pattern, pub_time):
+                pass
+            else:
+                if re.match(date_time_pattern, pub_time):
+                    pass
+                else:
+                    continue
             # print(name)
             report_type = td_list[4].text.strip()
             # print(report_type)
@@ -154,7 +164,7 @@ def SpiderByZJH(url, payload, dic_info, num, start_time):
                         'origin': '证监会',
                         'publishDate': pub_time,
                         'sid': '1684032033495392257',
-                        'sourceAddress': '',  # 原文链接
+                        'sourceAddress': pdf_url,  # 原文链接
                         'summary': '',
                         'title': name_pdf,
                         'type': 1,