import peter

seek/xinhuanet_com/content.py

@@ -0,0 +1,58 @@
+import datetime
+
+from DrissionPage.errors import ElementNotFoundError
+
+from database.tinformationsource.model import TInformationSource
+from database.tnews.model import TNews
+from log.log_manager import logger
+from seek.content_base import ContentBase
+
+
+class ArticleContent(ContentBase):
+    def __init__(self, news: TNews):
+        super().__init__(news)
+
+    def get_content(self):
+        content_ = ''
+        try:
+            content_ = self.session.s_ele('#detailContent').text
+        except ElementNotFoundError:
+            content_ = 'not found element'
+        return content_
+
+    def get_occurrence_date(self):
+        try:
+            header_time = self.session.s_ele('.header-time left')
+            year = header_time.s_ele('.year').text # 2023
+            day = header_time.s_ele('.day').text # 12/27
+            time = header_time.s_ele('.time').text # 08:05:11
+            occurrence_date_ = f'{year}/{day} {time}'
+            print(occurrence_date_)
+        except ElementNotFoundError:
+            occurrence_date_ = None
+        return occurrence_date_
+
+def get_content(information_source: TInformationSource) -> list:
+    article_content = ArticleContent(information_source)
+    result = article_content.get_content()
+    article_content.get_occurrence_date()
+    article_content.finish()
+    return result
+
+
+def content_task(news: TNews):
+    logger.info(f'{news.title} news_task start execute at {datetime.datetime.now()}', )
+    article_content = ArticleContent(news)
+    article_content.do_seek_task()
+    article_content.finish()
+    logger.info(f'{news.title} news_task end execute at {datetime.datetime.now()}')
+
+
+if __name__ == '__main__':
+    logger.info('This module is not for direct call!')
+    news_ = TNews()
+    news_.is_static = True
+    news_.url = 'https://www.news.cn/politics/leaders/20241227/90e76f85ad4a43ba94802b07c5736e00/c.html'
+    content = get_content(news_)
+    logger.info(content)
+    logger.info('Done.')

seek/xinhuanet_com/information.py

@@ -0,0 +1,59 @@
+import datetime
+
+from DrissionPage.errors import ElementNotFoundError
+
+from database.tinformationsource.model import TInformationSource
+from database.tnews.model import TNews
+from log.log_manager import logger
+from seek.seek_base import SeekBase
+
+
+class Information(SeekBase):
+    def __init__(self, information_source: TInformationSource):
+        super().__init__(information_source)
+
+    def get_news(self):
+        news_result = []
+        _news_list = self.session.s_ele('#focusListNews').s_eles('tag:li')
+        for _news in _news_list:
+            try:
+                rs_news = TNews()
+                rs_news.title = _news.s_ele('tag:a').text
+                rs_news.url = _news.s_ele('tag:a').link
+                # rs_news.summary = tmp_.s_eles('tag:a')[1].text
+                # rs_news.occurrence_date = self.process_time(tmp_.s_ele('.info__time').text)
+                rs_news.source = self.information_source.title
+                news_result.append(rs_news)
+            except ElementNotFoundError as e:
+                logger.error(f"ElementNotFoundError: {e} - Failed to find element in news item.")
+            except Exception as e:
+                logger.error(f'Unexpected error occurred: {e}')
+        return news_result
+
+
+def get_news(information_source: TInformationSource) -> list:
+    instance = Information(information_source)
+    news_list = instance.get_news()
+    instance.finish()
+    return news_list
+
+
+def news_task(information_source: TInformationSource):
+    logger.info(f'{information_source.title} news_task start execute at {datetime.datetime.now()}', )
+    instance = Information(information_source)
+    instance.do_seek_task()
+    instance.finish()
+    logger.info(f'{information_source.title} news_task end execute at {datetime.datetime.now()}')
+
+
+if __name__ == '__main__':
+    logger.info('This module is not for direct call!')
+    information_source_ = TInformationSource()
+    information_source_.is_static = True
+    information_source_.url = 'http://www.xinhuanet.com/'
+    information_source_.title = '资讯_新华网'
+    news_task(information_source_)
+    # news_list_ = get_news(information_source_)
+    # for news in news_list_:
+    #     print(news)
+    logger.info('Done.')