求是网作者调整

qiushi_leaderspeech.py

@@ -113,16 +113,20 @@ if __name__=='__main__':
                         author = new.find('font', face='楷体').text.replace('/', '').replace('\u3000', ' ').replace('\xa0', '')
                     except:
                         continue
-                    if len(author)>4:
-                        continue
+                    # if len(author)>4:
+                    #     continue
                     # if '（' in author or '本刊' in author or '国家' in author\
                     #     or '中共' in author or '记者' in author or '新闻社' in author\
                     #     or '党委' in author or '调研组' in author or '研究中心' in author\
                     #     or '委员会' in author or '博物' in author or '大学' in author or '联合会' in author :
-                    if '（' in author or '本刊' in author or '国家' in author \
-                            or '中共' in author or '记者' in author or '新闻社' in author \
-                            or '党委' in author or '”' in author\
-                            or '大学' in author or '洛桑江村' in author:
+                    # if '（' in author or '本刊' in author  \
+                    #         or '记者' in author or '新闻社' in author \
+                    #         or '”' in author\
+                    #         or '大学' in author or '洛桑江村' in author:
+                    #     continue
+                    if '国资委党委' in author:
+                        pass
+                    else:
                         continue
                     new_href = new.find('a')['href']
                     is_member = r.sismember('qiushileaderspeech::' + period_title, new_href)
@@ -159,7 +163,7 @@ if __name__=='__main__':
                     'sourceAddress': new_href,
                     "createDate": nowDate
                 }
-                # log.info(dic_news)
+                log.info(dic_news)
                 if sendKafka(dic_news):
                     r.sadd('qiushileaderspeech::' + period_title, new_href)
                     log.info(f'采集成功----{dic_news["sourceAddress"]}')

求是网领导讲话采集说明.md

+qiushi_leaderspeech.py
+qiushi_leaderspeech.py
+11.06:
+    部署到231上 任务计划程序，定时7点每天执行
+    todo:需要进一步确定索要领导的名单，包括习、国资委、其他部委领导
+    部署的暂时只有领导人
+本地上传的作者是国务院国资委
\ No newline at end of file